> ## Documentation Index
> Fetch the complete documentation index at: https://support.metaview.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Prompt Library
> Best-in-class prompts for Notetaker templates, Sourcing, Sequences, Deep Research, Reports and MCP — ready to copy, paste and adapt.
Recruiting is a context problem. Every hiring conversation is data — the richest, most honest signal your organisation has about the talent market, your candidates, and your own process.
This library contains customizable prompts created by the Metaview team for use across the Metaview platform. They are examples designed to inspire and guide you. You remain responsible for how you configure Metaview’s AI features, the prompts you use, the conversations you apply them to, and any decisions you make based on the outputs.
**Placeholders.** Anywhere you see `[Company]`, `[role]`, `[your name]` or `{COMPANY_NAME}`, swap in your own details before running. Where a prompt references an attached document, upload your JD, competency framework or scorecard alongside the transcript.
**These prompts examples produce drafts for you to review.** Notetaker captures and organises what was said in a conversation; it does not evaluate candidates, infer traits, or make hiring decisions. Every prompt below is designed to surface evidence — you decide what that evidence means. See [Best practices for Notes](/account-management/privacy-and-security/ai-best-practices) before rolling any of these out to your team.
## What's inside
| Section | What it's for |
| --------------------------------------- | ------------------------------------------------------------------------ |
| [Prompting guide](#the-prompting-guide) | The fundamentals of what makes a good prompt. |
| [1. Notetaker](#1-notetaker-templates) | Structured note templates for screens, debriefs, kick-offs and coaching. |
| [2. Sourcing](#2-sourcing) | Natural-language prompts to find candidates and companies. |
| [3. Sequences](#3-sequences) | Personalised candidate outreach at scale. |
| [4. Deep Research](#4-deep-research) | Long-form research: market maps, talent intel, competitor benchmarking. |
| [5. Reports](#5-reports) | AI columns that extract structured signal at scale. |
| [6. MCP](#6-mcp) | Automation and analysis across your whole hiring operation. |
***
## The prompting guide
A prompt is a written instruction that tells the AI **what to extract** from your transcript, **which sources to use**, and **how to format** the result. Think of it as briefing a very fast, very literal junior teammate — the more precise you are, the better the output.
### The six core prompting principles
Ask *how*, *what*, and *with what result* — not yes/no questions. The AI defaults to the broadest interpretation, so specifics reduce the chance of it filling gaps.
Tell the AI who it is — e.g. *"Act as a senior technical recruiter."* It frames everything that follows.
Metaview can pull context from several places, so be explicit — e.g. *"Refer to both the transcript and the job description."*
Be clear on what it should *not* do — e.g. *"Do not infer or speculate — only return what was explicitly mentioned in the transcript."* Always define what to return when a topic didn't come up (`N/A`, `Not discussed`, or a blank cell).
This is the highest-leverage line in any prompt. A missing fallback is what turns silence into a false negative.
Spell out the format — bullets vs prose, exact labels, and whether to include direct quotes.
Run a template on 2–3 real interviews and spot-check the citations before rolling it out widely.
### The prompt builder
Writing a prompt from scratch? Fill in these five lines and you'll have a solid prompt every time.
| Section | Ask yourself | Example |
| ----------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Role** | Who should the AI act as? | "You are a senior recruiter at \[company], familiar with our values and culture." |
| **Goal** | What are you trying to achieve? | "I want to capture what the candidate said in relation to our core values." |
| **Context** | What does it need to do this well? | "Our values are \[X], \[Y], \[Z], defined as \[…]. Refer to the attached context for how each shows up in practice." |
| **Task** | What exactly should it do? | "From the transcript, list what the candidate said relating to each value, quoting where possible. Write 'Not discussed' where a value didn't come up." |
| **Output** | How should the result look? | "Use bullet points and short sentences. Follow this format: • **\[Value]:** \[what they said]." |
Notice what the Goal and Task lines *don't* say. They ask the AI to capture and quote, not to judge whether the candidate "aligns". Alignment is your call — the prompt's job is to put the evidence in front of you.
***
# 1. Notetaker Templates
Notetaker templates turn any interview, intake or debrief call into a structured summary. Build one once, share it with the team, and reuse it across every conversation of that type.
Templates marked with **`*`** are designed for use with [multi-source](/using-ai-notes/ai-notes#multi-source).
**Formatting your output.** Templates render in Markdown, so you control how notes look: `**bold**` for titles, tools and company names; `*italic*` for skill or project types; `underline` to flag blockers; and `-` for bullet lists.
Keep section headings factual and focused on what was said. Avoid fields that ask the AI to infer personal traits, emotions or "fit" — see [best practice guidelines for custom templates](/account-management/privacy-and-security/ai-best-practices#best-practice-guidelines-for-custom-templates).
### 1.1 — Build a template with AI (meta-prompt)
**What it's for:** Have any LLM draft a Metaview template from a plain-English description.
```text expandable theme={null}
Help me make a Metaview template. Essentially a Metaview template is sections of prompts applied against an interview transcript. There are no overarching prompts, only sections. Each section has a title and a prompt that gets applied against the transcript from the interview.
Really basic example:
Title: Summary
Prompt: Give a summary of the candidate
Metaview templates use markdown formatting for the output. For each section, include: "output in Markdown like below" and then define how you want the output to look. Sometimes heavy structure is useful (e.g. housekeeping sections):
Output in markdown exactly like below:
- **Compensation Expectations:**
- **Notice Period:**
At other times, where there is more nuance, output in prose:
Output in markdown like below:
<2-3 sentences on what the candidate said motivates them>
For each prompt, include a description of what this section is about, details on how to find what is being looked for, exclusions, and output format and structure. Every section must say what to return when the topic was not discussed.
Keep section prompts non-evaluative: capture what was said rather than judging it.
[Describe the goal of the prompt]
```
### 1.2 — Role kick-off / intake call (HM call)
**What it's for:** Capture every detail from a hiring manager intake so the search starts aligned. Each block below is a separate template section.
```text expandable theme={null}
Provide an overview of the following details for the role. Format as a maximum 1-sentence summary per point, each on its own line:
- Job title: [e.g. Account Manager]
- Job level: [e.g. Mid-level]
- Role type: [permanent, FTC, contract]
- Location: [city, country OR remote]
- Ideal start date: [when is ideal for the role to be filled?]
- Backfill vs. new role: [backfill or newly created position?]
- Internal pipeline: [any internal candidates being considered?]
```
```text expandable theme={null}
What is the compensation for this role? Include the role budget in one line with currency, then any benefits / full comp details on a separate line.
- Budget: [$/£/€ x]
- Comp package: [pension, shares, sign-on bonus, commission structure, etc.]
```
```text expandable theme={null}
Provide an overview of the purpose of the role and the team. Which strategic pillar, company goal, or metric does this role impact? Then create a short elevator pitch for the recruiter to sell the role.
- Role overview: [brief overview of purpose and impact]
- Role pitch: [short elevator pitch selling value, impact and purpose]
```
```text expandable theme={null}
Provide an overview on what this role entails on a day to day. Outline the scope of the work & day to day. Who are the key stakeholders or departments/teams this role will work closely with?
Return as follows:
- Key responsibilities: [list of day to day responsibilities of the role]
- Scope of work: [what key projects will this role be working on? What is the scope of work?]
- Key stakeholders: [who will this role work closest with? List the titles and/or teams.]
```
```text expandable theme={null}
List all required skills, qualifications, training and prior experience needed to succeed in this role.
- Add only one skill per bullet point.
- Label each skill "nice to have" or "must have" depending on what the hiring manager discussed.
- For any skill the hiring manager calls "highest priority", state this next to the skill.
- Only include requirements the hiring manager actually stated. Do not add requirements they did not mention.
```
```text expandable theme={null}
List all the reasons why a candidate would be excited to take on this role, what are the selling points of this role? What makes this role unique? Additionally, list what are the biggest challenges in this role.
Return as follows:
- [key selling point/unique area #1]
- [key selling point/unique area #2]
- [key selling point/unique area #3]
etc
Role challenges:
- [key challenge of the role #1]
- [key challenge of the role #2]
etc
```
```text expandable theme={null}
Detail the interview process for this role:
- Number of interviews: [number]
- Stakeholders involved: [name, title]
- Interview task: [details]
- Timelines: [when should interviews be kicked off]
```
```text expandable theme={null}
Any other key details that were discussed that don't fit into the above sections (Role specifics, Compensation, Role Overview, Role Responsibilities, Role Selling Points, Ideal Candidate or Interview Plan) add in here.
```
### 1.3 — Client kick-off call (search firm)
**What it's for:** A thorough intake one-pager for agency and search teams.
```text expandable theme={null}
Summarize the logistical and contextual details discussed with the hiring manager about the open role.
Expected Output:
- **Reason for Opening:** Describe why this role is being hired (e.g., new position, backfill, expansion, succession).
- **Position Title:** Capture the official title as discussed.
- **Department:** Identify which department or division the role sits in.
- **Hiring Manager:** Specify who leads the hiring process.
- **Location for Role:** Include the work site or primary location for this role.
- **Recruiter:** Capture the assigned recruiter's name if mentioned.
- **Type of Recruitment:** Clarify whether the search is external only, or mixed.
- **Travel Required for Role:** Describe travel expectations, frequency, or approximate percentage.
- **Salary Range:** Summarize the discussed compensation range (including currency).
- **Relocation Offered:** Indicate if relocation assistance is available.
- **In Office/Hybrid/Remote:** Note whether the role is onsite, hybrid, or remote.
Important: Present the information in bullet-point markdown format, clearly separating each line item.
Format Instruction:
- Refer to the hiring manager, recruiter, and HR partner by name where possible
- Use markdown with **bold** for key facts (e.g., "**Hybrid role based in St. Louis, MO**")
- Be concise and factual; summarize what was discussed without adding interpretation
- If any detail was not mentioned, note it as "Not specified"
```
```text expandable theme={null}
Using evidence from the transcript and attached documents when relevant (i.e., resume/CV, job description, role intake notes, etc.), summarize the **company and product context** discussed, ensuring **every field from the Company & Product Info document is explicitly covered**. For funding, list **each funding series separately**, with **Investors** and **Angel Investors nested under the corresponding round**.
Expected Output:
**Founded:**
- Year founded and any origin context discussed
**HQ / Offices:**
- Primary headquarters location
- Additional offices or remote footprint if mentioned
**Funding Series:**
- **Series A**
- Date and amount raised if stated
- **Investors:**
- **Angel Investors:**
- **Series B** (include only if discussed)
- Date and amount raised if stated
- **Investors:**
- **Angel Investors:**
**Valuation:**
- Valuation details if explicitly discussed
**Leadership:**
- Key executives, founders, or leadership roles referenced
**# Employees:**
- Approximate employee count or team size mentioned
**Industry / Space:**
- Industry, market, or problem space the company operates in
**Buyer:**
- Primary buyer persona (e.g., SMB, enterprise, function-specific)
**Product:**
- High-level description of what the product does
- Core value proposition or use cases mentioned
**Customers:**
- Customer types, segments, or notable examples discussed
**Competition:**
- Competitors referenced
- Differentiation or positioning if discussed
Important: Present the information in bullet-point markdown format, clearly separating each line item
Format Instruction:
- For **Funding Series**, create a **separate sub-block for each round mentioned** (e.g., Series A, Series B)
- Nest **Investors** and **Angel Investors** directly under their respective funding round
- Bold **labels only** (everything before the colon)
- Use **4 spaces** for all sub-bullet indentation
- Base all details strictly on what is stated — **do not infer or assume**
- If a detail is not mentioned, leave it blank or omit that specific sub-bullet
- Keep tone concise, factual, and recruiter-ready
- Write so the section can stand alone when shared with a hiring manager
```
```text expandable theme={null}
Summarize what the hiring manager shared about the role's purpose, scope, challenges, team structure, and career path.
Expected Output:
- **Key Position Responsibilities:** Provide a detailed summary of the role's key objectives, deliverables, and success measures.
- Include specific examples of ongoing work, major projects, or strategic initiatives.
- Capture the **scope of accountability** (team size, budget, systems owned) and **metrics for success** (e.g., output targets, efficiency gains, customer impact).
- **Biggest Challenges:** Expand on the core obstacles or complexities tied to the role.
- Include operational, technical, or leadership challenges the new hire will need to overcome.
- Highlight **pain points** or **critical skill areas** mentioned by the hiring manager.
- **Interaction With Other Departments:** Identify the main teams or functions this role collaborates with regularly.
- **Team Structure:** Outline how the role fits into the organization (reporting line, peers, and direct reports if applicable).
- **Biggest Selling Features:** Describe what makes this position attractive — e.g., growth potential, visibility, technology, or culture.
- **Career Path:** Summarize potential development or advancement paths discussed for someone in this role.
Important: Present the information in bullet-point markdown format, clearly separating each line item.
Format Instruction:
- Use **bold** for each heading and a single dash for supporting detail
- Use sub-bullets to expand **Responsibilities** and **Challenges** with specific examples and context when mentioned
- Keep the tone factual — summarize only what was stated
- If an item wasn't covered, write "Not specified"
- Maintain consistent formatting with prior sections
```
```text expandable theme={null}
Using evidence from the transcript and attached documents when relevant (i.e., job description, role intake notes, recruiter context, etc.), summarize the **Role + Search Intake Context** as a concise, structured one-pager that captures what the role is, what the hiring manager said a strong candidate looks like, and the market opportunity discussed.
Expected Output:
**What the Role Is**
- Title and function of the role
- Core mandate, goals, or problems this role is expected to solve
- Where the role sits in the org (team, reporting line, scope)
**Ideal Candidate Profile (as described by the hiring manager)**
- Key background, experience, or domain expertise discussed
- Skills or patterns the hiring manager said define what "good" looks like
- Any explicit must-haves vs. nice-to-haves mentioned
**Market Size & Opportunity**
- Market size, category, or growth opportunity referenced
- Why this role matters given the company's stage or ambitions
- Any urgency, timing, or strategic importance discussed
Important: Present the information in bullet-point markdown format, clearly separating each line item
Format Instruction:
- Treat this section as a **search intake one-pager** written for recruiters and hiring managers
- Bold **labels only** (everything before the colon)
- Use **4 spaces** for all sub-bullet indentation
- Base all details strictly on what is stated in the transcript or provided materials — do not infer
- If a detail is not mentioned, omit it rather than speculating
- Keep tone concise, factual, and recruiter-ready
- Structure the section so it can stand alone and be read independently of other sections
```
```text expandable theme={null}
Summarize what the hiring manager shared about the qualifications for this role, scanning for all possible requirement categories.
Each category should appear **only once** — in either the *Must-Haves* or *Nice-to-Haves* section, depending on how it was described in the conversation.
Expected Output:
**Must-Haves (Needs)**
Include only items that were described as required or essential.
- **Education Needed:** [Requirement or "Not specified"]
- **Relevant Experience:** [Requirement or "Not specified"]
- **Years/Level of Experience:** [Requirement or "Not specified"]
- **Tools:** [Requirement or "Not specified"]
- **Certifications:** [Requirement or "Not specified"]
- **Language Requirements:** [Requirement or "Not specified"]
**Nice-to-Haves (Wants)**
Include only items that were described as preferred, nice-to-have, or optional.
- **Education:** [Preferred qualification or "Not specified"]
- **Experience:** [Preferred experience or "Not specified"]
- **Tools:** [Preferred tools or technologies or "Not specified"]
- **Certifications:** [Optional or value-add certifications or "Not specified"]
- **Language:** [Additional or secondary language skills or "Not specified"]
Important:
- Always check all requirement categories.
- Each category should appear **only in the section where it was discussed** (either Must-Have *or* Nice-to-Have, never both).
- If a category was not mentioned at all, omit it entirely from the output.
Format Instruction:
- Use **bold** for each field name
- Use a single dash `-` for the main point and supporting detail
- Keep spacing consistent — one blank line between categories
- Maintain clean Metaview formatting (no nested bullets or tables)
```
There's no **Soft Skills** category here on purpose. Recording a soft-skill requirement is fine when the hiring manager stated one, but a category by that name invites the model to characterise people rather than capture requirements. If your process needs it, phrase it as a stated requirement — e.g. *"Communication requirements the hiring manager explicitly described"*.
```text expandable theme={null}
Summarize what the hiring manager shared about how to source and attract candidates:
- **External Position Titles:** alternate/comparable titles to search for
- **Industries/Companies to Target:** where suitable talent sits
- **Companies to Avoid:** off-limits orgs (+ reason if mentioned)
- **Potential Internal Candidate:** internal employees/departments
- **Sourcing Strategy:** overall approach/channels (+ geography, timing)
If an item wasn't covered, write "Not specified".
```
```text expandable theme={null}
Summarize the agreed interview structure, including all steps, participants, and methods of evaluation.
Expected Output:
- **Steps Required in the Interview Process:** Outline each stage of the process (e.g., recruiter screen, technical interview, panel, presentation, final decision).
- *For each step:* Include the interview type (e.g., phone, virtual, onsite), purpose, and focus area.
- **Who and How Will Conduct Each Step:** Identify who will lead each interview and the format they'll use.
- *Include:* interviewer names or roles, topics they'll assess, and tools or methods used (e.g., case study, coding test, structured interview).
Important: Present the information in bullet-point markdown format, clearly separating each line item
Format Instruction:
- Use **bold** for stage titles (e.g., "**Step 1: Recruiter Screen**")
- Indent sub-bullets for details about each step and interviewer responsibilities
- Include specific formats (e.g., "Virtual via Teams") when mentioned
- If the number of stages or interviewers is not discussed, note "Not specified"
- Keep tone factual and structured for recruiter implementation
```
```text expandable theme={null}
Summarize any final details discussed during the kickoff meeting that support alignment, communication, and hiring coordination.
Expected Output:
- **Communication:** Capture how the hiring manager and recruiter agreed to communicate throughout the process (e.g., preferred channels, cadence, update frequency).
- *Example guidance:* Note if updates should happen via email, Teams, or weekly syncs.
- **Additional Comments:** Include any other notes, clarifications, or context shared that don't fit in earlier sections (e.g., urgency of hire, timeline expectations, or special circumstances).
Important: Present the information in bullet-point markdown format, clearly separating each line item
Format Instruction:
- Use **bold** for field titles (e.g., "**Communication:**")
- Keep tone factual and neutral — summarize what was said, not inferred
- If either field was not discussed, write "Not specified"
- Include only content relevant to the intake process and recruiting alignment
- Maintain consistency with the structure used in previous sections
```
### 1.4 — Recruiter screen (enriched with JD) `*`
**What it's for:** A generalist template for recruiter screening calls that maps the conversation against an attached JD. Attach the JD before running.
```text expandable theme={null}
Create a top line summary on this candidate's experience, noting the experience they described that relates to the job description.
This should be an executive summary no more than 3 sentences.
```
```text expandable theme={null}
Extract what the candidate shared about why they're interested in [COMPANY_NAME] and this role. Why they are looking at leaving their current role, why they want to join the company. Where relevant, please include information on what they are not looking for in their job search. What are their long-term aspirations?
Return the output in Markdown:
- **Reason for searching:** [why are they looking for a new role?]
- **Why [COMPANY_NAME]?** [e.g. category creation, product-market fit, growth stage]
- **Role interest:** [e.g. referenced customer logos, product strength, personal goals, etc]
- **Career goals:** [What are their long-term career aspirations, and how did they say this role contributes to those?]
- **Additional notes:** [what they explicitly said they're not looking for]
Only include details explicitly mentioned in the call by the candidate. Write "Not discussed" for any field that did not come up.
```
Keep these fields about what the candidate said, not how they said it. Asking for "enthusiasm", "clarity" or "personal alignment" pushes the model into reading tone and character instead of recording statements.
```text expandable theme={null}
Using the transcript as your foundation and adding details from the resume when helpful, provide a structured overview of the candidate's past roles.
For each position, include: company, title, dates, and bullets summarizing scope, team context, key responsibilities, tools used (if relevant), cross-functional work, and reason for leaving (RFL).
Format like the below:
**[Company Name] - [Title] ([Start Date] - [End Date])**
- **Company Summary:** [Brief description of the company, what they do, product, etc.]
- **Company Industry:** [Industries company operates in]
- **Customer / Stakeholder:** [Types of users, clients, internal stakeholders]
- **Tools / Systems Used:** [Technologies, platforms, tools used]
- **Team Size / Structure:** [Team size, role within team or org]
- **Cross-Functional Work:** [Who they worked with and why]
- **Training & Enablement:** [Docs created, trainings led, process improvements]
- **Reason for joining/leaving:** [Reason for joining and leaving, as stated]
repeat for 3 most recent roles.
```
```text expandable theme={null}
Refer to the additional context shared (job description) and create a list of the required skills the candidate described experience with.
Ensure evidence is cited from the transcript, and explicitly quote each citation.
Output as below:
- **[skill one]:** [direct examples from the transcript]
- **[skill two]:** [direct examples from the transcript]
etc
```
```text expandable theme={null}
Refer to the additional context shared (job description) and create a list of any "required skills" the candidate either noted they do not have experience with, noted they've never used/tried, or where the skill was not discussed within the transcript at all.
Distinguish clearly between the two cases:
- The candidate said they do not have this experience — quote them.
- The skill was not discussed at all in this interview — say so explicitly. This is a gap in coverage, not evidence the candidate lacks the skill.
Output as below:
- **[skill one]:** [direct quote, OR "not discussed in this interview"]
- **[skill two]:** [direct quote, OR "not discussed in this interview"]
etc
```
Note that the second section forces a distinction between *"they said they haven't done this"* and *"nobody asked"*. Keep it. Treating an unasked question as a missing skill is the most common way a coverage gap turns into an unfair conclusion about a person — and it's why this section isn't called "misalignment".
```text expandable theme={null}
Extract any information the candidate provided relating to essential logistical or eligibility factors.
Topics to look for (and likely phrasing):
- Compensation expectations:
'I'm looking for…' / 'I'd be targeting…'
- Right to work:
'I have the right to work in…' / 'I'd need sponsorship…'
- Location & remote setup:
'I'm based in…' / 'I'd need to relocate…'
- Non-compete:
'I'm under a clause that…'
- Holiday plans or notice period:
'I have a trip booked…' / 'I'm on 1 month notice…'
Return the output in the following bulleted format:
- Compensation expectations (as stated): [value or range, or "Not discussed"]
- Right to work: [only as stated by the candidate, or "Not discussed"]
- Location: [City/Country + remote/flexibility context, or "Not discussed"]
- Non-compete: [only as stated by the candidate, or "Not discussed"]
- Holiday / Notice period: [dates if shared, or "Not discussed"]
- Constraints the candidate raised: [logistical constraints they named, or "Not discussed"]
Only include details explicitly mentioned in the call by the candidate. Never infer work authorisation or contractual restrictions, and do not record current or past pay in the expectations field. Where a topic did not come up, write "Not discussed" — never leave a blank or guess a value.
```
Resist adding a "red flags" field here, or asking the model to note "clarity" and "confidence". Logistics are facts worth capturing; whether any of them is a concern is a judgment, and it belongs to you.
### 1.5 — Volume hiring `*`
**What it's for:** At volume, map each candidate against the required skills in your job spec so you can see who to review first. Add all conversations, plus the JD.
```text expandable theme={null}
From all the conversations provided, show me how each candidate maps against the required skills for the role I'm recruiting for.
I have uploaded the job description. Look over the required skills section, and list all candidates who described experience in at least [X]% of the listed required skills.
RULES:
- Only count a "skill match" if the candidate has explicitly mentioned they have experience in something or used a tool.
- Any skill mentioned only by the interviewer, disregard.
- Where a required skill was never discussed in a candidate's interview, list it as "not discussed" rather than as a gap. A topic nobody raised is not evidence the candidate lacks it.
Also list the candidates below [X]% with the same breakdown.
Return as follows:
**Meets [X]% or above**
- [candidate name]: [% skills discussed], evidence for: [list each skill they described, with a quote], not discussed: [list each skill that never came up]
**Below [X]%**
- [candidate name]: [% skills discussed], evidence for: [list], not discussed: [list]
Do not rank the candidates or recommend who to progress.
```
A percentage of skills *discussed in an interview* measures what got covered, not candidate quality — two interviewers asking different questions will produce different percentages for identical candidates. Use this to decide who to read about next, never who to reject.
### 1.6 — Compare candidates against a JD (enriched with JD) `*`
**What it's for:** Lay out what each candidate said about each requirement in the JD, side by side, as preparation for a human debrief. Attach the JD.
**This prompt does not pick a winner.** It produces an evidence matrix — what each candidate said about each requirement — and stops there. Asking the AI which candidate is strongest, or for a "close second", is the AI ranking people: [Best practices for Notes](/account-management/privacy-and-security/ai-best-practices) rules that out, and the [Interview Debrief skill](/ai-skills/interview-debrief) refuses it too. How to weigh the evidence is the hiring team's decision.
```text expandable theme={null}
Based on the job description shared, summarise what each candidate said that relates to the role, using specific examples from the transcripts.
For each candidate, return:
**[Candidate name]**
- Experience they described: [skills and examples they discussed that relate to the JD, with quotes]
- Requirements not discussed: [any JD requirements that did not come up in their interview]
Do not rank the candidates, name a strongest candidate, or recommend who to progress. Present the evidence for each candidate so the hiring team can compare it themselves.
```
```text expandable theme={null}
For this required skill, list what each candidate said about it, with a direct quote from the transcript.
Return in the following output:
**[Skill name]**
- [candidate name]: [direct quote or example from the transcript]
- [candidate name]: [direct quote or example from the transcript]
- Not discussed with: [any candidate(s) where this skill never came up in the interview]
Do not state which candidate is strongest on this skill. List the evidence only.
```
### 1.7 — Pipeline debrief / wash-ups
**What it's for:** Let Metaview sit in on your debrief with the hiring team and turn the discussion into structured notes per candidate — capturing what the interviewers said, not adding a view of its own.
Use a repeating section, one per candidate discussed.
```text expandable theme={null}
Summarise the following, as discussed by the interviewers. Every point must be something an interviewer actually said in this debrief — do not add your own assessment, and write "Not discussed" where a heading didn't come up.
**Strengths raised**
What did the interviewers name as the candidate's strengths? Include the work or projects they referenced as evidence.
**Concerns raised**
What did the interviewers name as concerns or gaps? Include the work or projects they referenced as evidence.
**Flags**
Did the interviewers say they encountered any specific concerns they wanted to flag? Quote them.
**What the interviewers said about team fit**
Summarise what the interviewers said about how the candidate would work with the team. Report their words — do not assess fit yourself.
**Open questions and next steps**
Anything the interviewers said still needs answering, and any next steps agreed.
```
Every heading here asks what the **interviewers** said, not what the AI concludes. That distinction matters most on team fit: *"What did the interviewers say about how the candidate would work with the team?"* is a debrief record. *"Will the candidate be a good fit?"* asks the model for a fit judgment about a person.
### 1.8 — Brief interviewers on areas to probe further `*`
**What it's for:** Turn one interview into a brief for the next, flagging what the following interviewer should explore. Add multiple interviews per candidate, or multiple candidates per role.
Use a repeating section, one per candidate.
```text expandable theme={null}
Review the candidate's responses against the requirements outlined in the role specification / job description provided. Identify any requirements where the interview did not cover enough for the hiring team to form a view — either because the topic wasn't raised, or because the answer stayed high-level.
For each area: clearly state the topic or requirement needing further coverage. Say what was missing or ambiguous, quoting the transcript. Provide a specific, high-quality follow-up question an interviewer can use to explore it in more depth. Be selective: focus only on material gaps in coverage, especially for must-have requirements.
Treat a topic that was never raised as unknown, not as a gap in the candidate.
Return the output in the following format:
**[Follow-up Topic]:** [What was missing or ambiguous, with a quote if there was partial coverage]
- **Suggested follow-up question:** "[Question to ask in next interview]"
Example of good output:
- AI Fluency: Candidate mentioned a general interest in AI but did not describe any specific use cases when asked.
- **Suggested follow-up question:** "Can you walk me through a time you introduced or evaluated an AI-driven tool within an operational process? What was your role and what impact did it have?"
```
This covers requirements and coverage, not "mindset" or "traits" — those are inferences about a person rather than gaps in the conversation. It also separates *wasn't asked* from *answered thinly*, which lead to different follow-ups.
### 1.9 — Role insights from HM interviews `*`
**What it's for:** Learn how hiring managers sell the role and answer candidate questions, so you can pitch it better yourself. Add multiple interviews via multi-source.
```text expandable theme={null}
Review all conversations provided and summarise how the interviewer describes the role to the candidate. Look for things like:
- How they explain why this position is exciting
- The reasons they give for why a candidate would want this role
- Any growth opportunities they mention
My goal is to use this to enhance my own role pitch to candidates I'm speaking with.
Quote them where possible. This is about collecting the language they use, not assessing how well they did.
```
```text expandable theme={null}
Create a list of all questions the candidate had regarding the role, team and company.
Next to each question, also list out how the interviewer responded.
Format like below:
- **[candidate question]** = [interviewer response]
```
### 1.10 — Check interview coverage consistency `*`
**What it's for:** See which topics an interviewer covers in every interview and which only come up sometimes. Use multi-source to add multiple interviews to compare.
**This analyses your own team.** Output describes coverage patterns across interviews — it is not a performance rating, and it shouldn't feed appraisals or ranking. Before using it:
* Keep individual output private to the person being coached.
* Keep team views aggregated — no league tables of named interviewers.
* Confirm your position on analysing employee performance first; works councils, employment law and internal policy may all apply.
The [Interviewer Coaching skill](/ai-skills/interviewer-coaching) applies the same principles with the governance built in.
```text expandable theme={null}
Analyse which key skills and topics the interviewer explores across the interviews provided. List only the topics that are covered in every interview provided.
Then, list the topics that appear in fewer than two of the conversations provided.
This is a description of coverage, not an assessment of the interviewer. Do not rate, score, or characterise the interviewer.
Return as follows:
**Covered in every interview:**
- [topic #1]
- [topic #2]
etc
**Covered inconsistently (fewer than two interviews):**
- [topic #1]
- [topic #2]
```
This measures which topics came up across a set of interviews. Avoid framing it as interviewer *behaviour* — the output describes coverage, not conduct.
### 1.11 — Offer insights
**What it's for:** Pull out what a candidate said they care about most, so you can build an offer that speaks to it. Add every conversation you've had with them.
```text expandable theme={null}
I am looking at ways I can make the most compelling offer to this candidate.
Review all conversations added to this view for a single candidate. Identify what the candidate has said they most want in their next role — covering motivations, priorities, and any dealbreakers or concerns they raised.
Weight by consistency and emphasis: prioritise themes the candidate raised more than once, or returned to, over things mentioned only in passing. Where a priority appears in only one conversation, note that so it can be weighted accordingly.
Capture both:
- what they said they're moving toward (what they said excites them, what they're optimising for), and
- what they said they're moving away from (frustrations with their current/past role, concerns about this one).
Use their own words throughout. Do not infer priorities they did not state.
Return in the following format:
Top priorities (consistent across conversations):
- [Priority]: [What they said, and where it came up]
Mentioned once / worth confirming:
- [Priority]: [What they said, in which conversation]
Concerns or dealbreakers:
- [Concern]: [What they said]
**What they said matters most:** [2–3 sentences summarising their stated priorities, quoted where possible, for me to build the offer from. Do not recommend an offer, a number, or a negotiating approach.]
```
***
# 2. Sourcing
Great sourcing starts with a sharp brief. These prompts help you tell the Sourcing agent exactly who you're looking for — must-haves, signals, and the near-misses to avoid — so results come back matched to your criteria rather than to a keyword.
Matches reflect alignment with the criteria you set, not a judgment about candidate quality. You decide who to review and who to contact — see [Best practices for Sourcing](/account-management/privacy-and-security/ai-sourcing-best-practices).
### 2.1 — Find candidates matching your criteria
```text expandable theme={null}
I'm hiring a [ROLE TITLE], based in [LOCATION + WORK MODEL — e.g. London, hybrid 3 days/week / remote within EU / SF, in-office].
What they'll actually own: [1–2 sentences on the outcomes this person is responsible for — the mission, not a responsibilities list. Anchor on what success looks like, since titles mean different things across companies.]
MUST-HAVES (hard filters — screen out anyone missing these):
- [Non-negotiable 1]
- [Non-negotiable 2]
- [Non-negotiable 3]
Keep this list to ~3–5. Every line here shrinks the pool, so only include things that are genuinely required for the work.
STRONG SIGNALS (use to rank, not to exclude):
- [Signal 1 — e.g. sold into HR/TA buyers]
- [Signal 2 — e.g. 0→1 / early-stage experience]
- [Signal 3]
SENIORITY: [e.g. senior IC, ~5–9 yrs scope; not a first-time hire in this function, not a VP]. Flag anyone clearly outside this band rather than including them to pad the list.
TARGET & FEEDER POOLS:
- Ideal current/past employers: [Company A, Company B, Company C]
- Adjacent pools worth pulling from: [competitors / similar motion / similar stage / similar buyer]
EXCLUDE: [what to actively screen out — e.g. agency-only backgrounds, pure SMB profiles]
A PROFILE THAT MEETS THESE CRITERIA LOOKS LIKE: [one sentence.]
A NEAR-MISS ON THESE CRITERIA LOOKS LIKE: [one sentence describing someone who looks right on paper but doesn't meet the criteria — this teaches the agent the edge of the box.]
Treat missing profile information as unknown, not as evidence someone lacks a requirement.
If anything above is ambiguous or contradictory, flag it and check with me before guessing. Then surface a first batch with your reasoning for each candidate, and I'll mark them YES / MAYBE / NO so you can refine.
```
Two things to keep as they are. **Don't put work authorisation in the exclusions** — it isn't in profile data, so the agent would infer it, and inference runs through nationality and place-of-education proxies. Handle sponsorship as a question in a human conversation. And keep "a profile that meets these criteria" phrased against your criteria rather than as a quality label on people.
### 2.2 — Find companies, not candidates
**What it's for:** Flip the search to find target companies — useful for search firms placing a known candidate.
```text expandable theme={null}
I am looking for suitable companies within 50 miles of [location] that my candidate could work at:
[attach the transcript of your call with the candidate, attach their CV or summarise their profile]
```
***
# 3. Sequences
The best outreach doesn't read like outreach. [Sequences](/sending-sequences) let you go beyond `{Company}` placeholders: AI prompt blocks written between `{{ }}` generate candidate-specific content at send time.
Pair these with the [Reply-Worthy Outreach](/guides/tutorials/reply-worthy-outreach) guide, which covers the framework and cadence these prompts are built for.
### How prompting works in Sequences
There are two kinds of variable you can drop into a sequence step, and they do very different jobs.
| Type | What it does | Example |
| ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
| **Merge field** | Fills in a stored value. Fine for logistics — never for personalisation. | `{{Candidate first name}}`, `{{Current company}}` |
| **Instruction block (Custom)** | A sentence telling the AI *what to write* for each candidate. Generated fresh per candidate at send time, using their profile, your search's ICP, and your sender details. | `{{Write one sentence on why their move from agency to in-house makes this role a natural next step}}` |
**Every first-touch sequence needs two fixed elements**, and neither should be a prompt block — save them as static text so they can't be rewritten per candidate:
* **A link to your organisation's privacy notice**, so candidates know how their data is being used and what their rights are.
* **A simple opt-out**, honoured promptly.
This is required by [Best practices for Sourcing](/account-management/privacy-and-security/ai-sourcing-best-practices#outreach) — Sequences lets you save a reusable privacy footer in your template so it's on every first message automatically.
Prompt blocks draft the message; you approve what goes out. These blocks generate at send time, so review the output across a sample of candidates before you enable a sequence — and keep the copy grounded in the person's stated experience and public professional work.
### 3.1 — Subject lines that get opened
**What it's for:** Salesy subjects ("Unlimited Growth!!") get filtered or ignored. Short, lowercase and specific wins.
```text expandable theme={null}
{{Write a subject line for this email: maximum 40 characters and specific to this candidate's background or the role. Prefer one concrete detail from the candidate profile; if none is suitable, reference the role. No clickbait, exclamation marks, or the words "opportunity", "exciting", or "new role". Return only the subject.}}
```
### 3.2 — The personalised opener
**What it's for:** Replace generic first lines ("I came across your profile…") with a hook specific enough that it passes the 50-person test. Drop into the first line of your first email step.
```text expandable theme={null}
{{Write one casual opening sentence referencing this candidate's most recent role or a specific accomplishment from their profile, and why that makes them relevant for a [ROLE TITLE] at [COMPANY]. It must be specific enough that it could not be sent to any other candidate. No greeting, no flattery, no "I came across your profile" or "your experience at [x] caught my attention". Reference something concrete: a community or group directly related to our industry, or a specific piece of work related to one of the key responsibilities in this role. Do not invent details. Under 25 words.}}
```
### 3.3 — The personalised value prop
**What it's for:** Pitch the *right* reason to move, based on where the candidate is coming from — instead of the same value prop for everyone. Adapt the if/then angles to your role's personas.
```text expandable theme={null}
{{Based on this candidate's background, experience and overall profile, write 1–2 sentences on why [ROLE TITLE] at [COMPANY] could be a step up for them specifically. If they're at a large company, focus on [e.g. ownership and pace]. If they're at an agency or consultancy, focus on [e.g. going in-house and owning outcomes]. If they're early in their career, focus on [e.g. mentorship and growth]. One value proposition only — plain, conversational language, no buzzwords. This shouldn't be the same value prop for every candidate. Base the angle on what is in their profile, not on assumptions about what someone in their situation must want.}}
```
Tailor to what the profile actually shows — company size, industry, scope of their current work. Writing to an inferred personal "driver" or "pain" is an assumption about someone you haven't spoken to, and it doesn't outperform grounding the angle in their real background.
### 3.4 — The light ask
**What it's for:** Replace heavy closers (booking links, "15–30 min call to discuss the opportunity") with one low-friction question. Drop into the last line of your first email step.
```text expandable theme={null}
{{Write a one-line closing ask for this email that is relevant to this candidate and the value prop we've included above. It must be one clear, low-friction next step. Something like "Got 15 minutes this week?" or "Worth a quick chat?". No booking link, no "no worries if not," nothing longer than a single sentence.}}
```
### 3.5 — The follow-up that adds something new
**What it's for:** Follow-ups that say "just bumping this" get ignored. Each follow-up step should introduce one new reason to reply.
```text expandable theme={null}
{{Write a 2–3 sentence follow-up to the previous email. Do not repeat, summarise, or reference "my last email". Introduce ONE new piece of value not mentioned before: [e.g. a recent company milestone / the team they'd join / a customer story / comp philosophy]. Use the role ICP to understand the value props for this company and role. Ensure the new piece of value is relevant to this candidate, so review their profile before deciding which piece of value you add. Keep the tone light and human, and end with a softer ask than the first email — e.g. offering to send more info rather than asking for a call.}}
```
### 3.6 — The break-up email
**What it's for:** A graceful final step that often gets the highest reply rate in the sequence. Low pressure, leaves the door open.
```text expandable theme={null}
{{Write a short, warm final email (2–3 sentences). Acknowledge they're probably busy or the timing may be wrong, without guilt-tripping. Reference their current role at their current company in a natural way, leave the door open to connect in future, and ask one zero-pressure question — e.g. whether there's a better time to pick this up. No booking link.}}
```
### 3.7 — Build the entire email with one prompt block
**What it's for:** Instead of writing copy with prompt blocks sprinkled in, let one instruction block generate the whole body. Best once you've calibrated the shorter blocks above.
**Make it yours before you run it.** This is an example scaffold, not a finished prompt. Rewrite the opener the way you'd actually introduce yourself, swap the example CTAs for something you'd say out loud, and adjust the rules to match your voice.
```text expandable theme={null}
{{Write the complete body of a first-touch email for [ROLE TITLE] on [COMPANY]'s [TEAM] team. This is a personalized outreach email to a candidate. This email will be sent by [SENDER NAME], [SENDER TITLE] — so ensure it sounds human and like a real person is reaching out. Use paragraph breaks between sentences.
Always start with exactly: "Hey Candidate first name - I'm [SENDER NAME], [SENDER TITLE] at [COMPANY]."
Then follow this structure (4 parts):
1. Opening (1 sentence, max 15 words): state ONE specific thing they did — a real project, product, result, or move from their profile. It must fail the "could I send this to 50 other people" test. Never "I came across your profile", never generic praise.
2. Bridge (1 short sentence or phrase): make a REAL connection between what they did and why I'm reaching out — explain the actual link between their work and what [COMPANY] needs, don't just say there is one. CRITICAL: the bridge must be specific to this candidate's profile; never produce a bridge that could be reused for a different candidate.
3. The pitch (1 sentence): what [COMPANY] is + one concrete proof point ([e.g. traction / customers / stage]) + why their background is relevant. One value proposition only — save the rest for follow-ups.
4. Close (1 sentence): "Got 15 minutes this week?" or "Worth a chat?" — nothing longer, no booking link, no "no worries if not".
Rules: Do not invent details. No corporate jargon, no "hope this finds you well", no buzzwords, no em dashes, at most one exclamation mark, no flattery filler ("truly amazing", "blown away"). Personalisation is proof of research — reference what they actually did, in plain words a real colleague would use.}}
```
***
# 4. Deep Research
Before you kick off a search, you need to understand the market. These long-form prompts produce market maps, talent intelligence and account prep — the homework that makes every downstream conversation sharper.
Market numbers are estimates. These prompts are written to label what is observed, reported and inferred, and to say what they could not verify. Keep that framing when you pass the output on.
### 4.1 — Calibration context kickoff
*As demoed in the Talent Mapping webinar.*
**What it's for:** Build deep role context to frame your criteria across sourcing, screening and application review. Put this prompt in the sourcing agent, follow its instructions, and save the output into your Metaview knowledge.
**Add your context before you run it.** This is a template, not a finished prompt. Fill in each of the bracketed sections so it runs for your specific role.
```text expandable theme={null}
Deep research only — do not source candidates, do not create or present an ICP, and do not present candidate cards.
This is calibration, not a search. The goal is a reviewable evidence package that sharpens my understanding of [ROLE / TEAM / FUNCTION] before I build anything — it never replaces my judgment and nothing gets saved or used operationally until I approve it.
SCOPE: [company] — [role, team, function, or org I want calibrated]. If I've told you what level this should live at below, treat that as fixed; otherwise propose the narrowest defensible layer yourself — company-wide, function-wide, or this specific role/team — and flag it as a proposal, not a done deal.
What this should support later: [one recurring role / a role family / multiple teams / general use].
Calibration anchor (pick one, or leave blank and say so): [current team / hiring manager / benchmark company or team / a specific past hire / an exemplar profile / a set of candidate feedback].
Known context so far (leave blank if none): [paste anything you have: JD, intake notes, ATS role name, team description, prior candidate feedback].
If you don't have enough to start, ask me once for the smallest set of facts that would change the output — nothing else.
I need this to be exhaustive and honest about its own limits. Classify every input before using it — Confirmed fact · Confirmed preference · Hypothesis (a belief or proxy, not yet evidence) · Observed evidence (source + date) · Estimated/inferred (directional only) · Unknown · Interview-only · Volatile (date it) — and carry the label through to the output. Flag anything you couldn't verify rather than smoothing it into the narrative.
RESEARCH, four tracks:
Role & identity — why this work exists, first outcomes, scope, and what a weak hire costs. What strong looks like, through work history and evidence, not keywords. What looks right but isn't: the surface signal that misleads, the real mismatch, what would earn an exception. If an anchor is set, reverse-map it — patterns in its work, ownership, trajectory, and where its people came from and went next. Behavioral patterns outweigh logos, schools, or titles.
Capability & assessment — for each real requirement: is it confirmed, a preference, trainable, or interview-only, and what does strong/adequate/insufficient evidence look like? Then, per high-value signal: what's checkable from a profile alone, what needs a portfolio, work sample, reference, or conversation — and the sharpest interview question for the part that isn't observable up front.
Market & competition — title variants and noise terms in this market, plus a few credible candidate archetypes with their risks and rough supply. Where this talent is built, who competes for it, and where it's realistically winnable now — a company only belongs here with a stated reason. A directional read on how constrained this pool is, and the single factor with the biggest effect on that number. Compensation, only if feasibility is genuinely in question — directional, sourced, separate from qualification.
Timing & constraints — market changes that affect this specific pool (layoffs, funding, demand shifts), dated, with one implication each. Explicit exclusions — prior applicants, internal conflicts — each defensible as relevant to the actual work, and separated into automatic exclusions versus ones that just need my review.
DISCIPLINE:
- Evidence is input, not authority — I make the final call. Where evidence conflicts with a stated preference, show the tension and its likely cost; don't resolve it for me.
- Separate behavioral patterns (what people actually did) from incidental ones (schools, logos, titles). Label each — incidental patterns describe how people were found, not what makes them succeed.
- Every hard rule needs a justification: confirmed by me, inherent to the work, or legally required. Anything else stays prioritization, verification, or interview guidance — never a gate.
- Never infer protected characteristics, work authorization, health, or family status. Public, job-relevant information only.
- Give a labeled directional estimate where I need one rather than refusing — but never present an estimate as a census.
- Missing information is unknown, not evidence.
WHEN RESEARCH IS DONE, deliver two things:
The full findings, structured for reading: the working read on the role/market, what strong and false-positive look like, the capability and assessment map, market and timing implications, the proposed context layer with a plain "use this when / don't use this when," and everything you couldn't verify.
One self-contained HTML file with the correlations and visuals — market/pool sizing, feeder and competitor landscape, career-path and title patterns, timing signals — with the underlying figures visible, not just the graphics.
Then finish by asking me one question: "Want me to save the approved parts of this as reusable context?" — and stop. Don't save anything, and don't turn this into an ICP or start sourcing, unless I say yes.
```
This is the best-governed prompt in the library. **"Evidence is input, not authority — I make the final call"**, **"Missing information is unknown, not evidence"**, the input classification scheme, and the explicit stop-and-ask before saving are all patterns worth copying into your own prompts. The only edit made was removing "off-limits populations" from the exclusions list — exclusions should attach to the work, not to groups of people.
### 4.2 — Build a reverse-map from your current team
*As demoed in the Talent Mapping webinar.*
**What it's for:** Map your current team into feeder companies, tenure patterns and career-path shapes, so you can see where the team was actually hired from.
**These patterns describe who was hired — not what predicts success.** The prompt says so itself, and the output says so too. Treat feeder companies and tenure shapes as a description of your past sourcing, not as criteria that forecast performance.
This prompt profiles named employees. Confirm your position on that internally before running it.
```text expandable theme={null}
Deep research only — do not source candidates, do not create or present an ICP, and do not present candidate cards.
TEAM: [Company] — [team name / what the team does]. Map the current members and, where identifiable, people who previously worked on this team. If I've listed names or profiles below, treat them as the roster; otherwise resolve the roster yourself and flag anyone you are not confident belongs. If you cannot identify the team confidently, ask me once for names — nothing else.
Optional roster / known members: [names, profile links — or leave blank]
I need this to be exhaustive and validated. For every person, verify that enriched data belongs to the same actual person and not someone with a similar name — flag any dossier you could not validate rather than including it silently.
RESEARCH, three tracks:
1. Individual dossiers — per person: total years of experience; every role with tenure and title; previous companies; education; and public artifacts appropriate to the role family (code, open source, portfolios, publications, patents, talks, blogs, interviews where they discuss their actual work, awards, promotions).
Note what they shipped, owned, or closed — in their own recorded words where possible.
2. Team patterns — mine the dossiers for everything the group shares and everything it doesn't: feeder companies ranked with counts (X of N); education mix; tenure per stint, average tenure, and the rhythm of when people joined and left; career-path shapes (what people did immediately before joining, and at what career stage they joined); skill and language patterns, including ownership language versus execution language in how they describe their work; contrasts between the junior and senior halves of the team if both exist; and a coverage map — what this team has in depth versus what it visibly lacks.
3. Team footprint — the team's external technical or professional traces: engineering blogs, talks, product documentation, press, case studies — anything showing what the work actually is, written for practitioners rather than recruiters.
DISCIPLINE:
- Separate BEHAVIORAL commonalities (what people shipped, owned, how scope grew) from INCIDENTAL ones (schools, brand-name employers). Label each pattern accordingly — incidental patterns are how a team was sourced, not what made it succeed.
- These patterns describe who was hired, not what predicts success. Say this in the output, and present every pattern with its count and its counter-examples.
- Never infer age, nationality, work authorization, health, family status, or any protected characteristic. Public professional information only.
- Missing information is unknown, not evidence. Name what you could not find or verify.
- Do not rate, rank, or score any individual on the team.
- These dossiers exist to describe the work, not to assess the people in them. Never use them to evaluate or compare current employees.
- Do not use tenure length, graduation dates, or career stage as criteria for a future hire — they act as age proxies.
WHEN THE RESEARCH IS DONE, deliver two things:
1. The full findings, structured for reading: the roster with validated dossiers, the pattern tables with counts, the coverage map, and the limitations.
2. One self-contained HTML file with the correlations and visuals — feeder-company chart, tenure timeline, career-path flows into and out of the team, a person-by-signal matrix, and the junior/senior contrast where it exists — with the underlying figures visible, not just the graphics.
Then finish by asking me one question: "Want me to turn this into an ICP and start sourcing from it?" — and stop. Do not build the ICP or start any search unless I say yes.
```
Note the discipline rules at the bottom of the prompt, particularly *"These patterns describe who was hired, not what predicts success"*. Keep them. Feeder companies and tenure shapes describe your past sourcing; they are not criteria that forecast performance.
### 4.3 — Market map analysis
**What it's for:** A defensible, executive-ready market map before active sourcing begins.
```text expandable theme={null}
When asked to produce a Market Map Analysis for any role, follow the structured framework below. The goal is a defensible, executive-ready report that is data-driven, visually digestible, and free of fluff. Output a PDF.
OBJECTIVE: Before active sourcing begins, produce a structured market-level analysis that quantifies talent supply, identifies competitive pressure, maps skill clusters and education pipelines, assesses compensation positioning, and recommends a sourcing strategy. The output must feel analytical and credible — not promotional.
REPORT STRUCTURE (always follow this order):
1. Confidence & Limitations — data sources, sample sizes, and what is Observed vs. Estimated vs. Inferred. Never present directional estimates as exact truths.
2. Executive Summary — 4–6 key insights (market size/constraint, talent concentration, education trends, competitive intensity, comp positioning). Use directional phrasing.
3. Talent Market Size & Availability — estimated addressable pool (ranges); funnel narrowing logic; breakdown by experience bands and education. Include a visual.
4. Educational Background & Pipelines — degree distribution, top universities, pipelines by experience level. Include a visual.
5. Skills & Technical Landscape — core technologies, tool adoption by band, emerging tech; define 4–6 skill clusters with directional sizes.
6. Employer & Industry Landscape — companies employing high concentrations of this talent, career trajectories. Include an employer concentration chart.
7. Compensation & Market Competitiveness — base ranges, total comp, differences by experience/specialization. Separate base / total comp / equity.
8. Sourcing Strategy Insights — highest-volume pools, realistic conversion segments, and the criteria that correlate with your requirements. Label these as market observations, not predictions about individuals.
9. Summary for Hiring Stakeholders — how constrained the profile is, where this talent concentrates, where competition is highest, expected friction, realistic TAM.
TONE: analytical not promotional; directional not absolute; data separated from interpretation; executive-ready. If confidence is low, say so.
```
Section 8 originally asked for "filters that predict alignment" and "green/yellow/red flags". Reworded: market-level correlations are fine, but a red/amber/green flag list reads as a screening rule about people.
### 4.4 — Interview kit from an intake call
**What it's for:** Turn an intake call into market intel, a sourcing shortlist and an interview kit. Paste or attach the intake transcript.
```text expandable theme={null}
When given a transcript of an intake call, analyze it and — using the details discussed with the Hiring Manager — produce three deliverables:
1. Market Mapping & Intelligence
- Identify 5–8 'Target Companies' (competitors or similar tech stacks).
- Identify 3–5 'Off-limit Companies' (any the hiring manager named as off-limits, with the reason they gave).
- Summarize current talent supply for this niche ('candidate-driven' vs 'company-driven').
2. Sourcing Shortlist
- Identify up to 10 real, verifiable candidates whose profiles meet the must-haves stated in the call.
- For each, cite the public source and date, and flag any profile you could not verify rather than including it silently.
- For each, a one-sentence 'Why they match' citing the specific must-have their profile evidences.
- Treat missing profile information as unknown, not as a gap.
- Present them unranked, in no particular order — this is a research list for me to review, not a shortlist.
3. Interview Kit
- A 4-stage interview plan based on the priorities discussed.
- 2 behavioral questions for each of the top 3 requirements.
- A 'Calibration Check': 3 bullets describing what strong, adequate and insufficient *evidence* looks like for the most critical requirement — so interviewers know what to listen for, not how to score the person.
```
Two changes: 'Off-limit Companies' no longer includes "poor culture match" as a reason the AI should infer — it now records only what the hiring manager stated. And the Calibration Check now defines evidence thresholds rather than 'Great' vs 'Mediocre', which was a label applied to candidates.
### 4.5 — Company deep-dive (6-part analysis)
**What it's for:** Prep for a meeting with a client or buyer — company, market, products, competitors.
```text expandable theme={null}
You are a world-class research analyst, strategy consultant and researcher.
TASK: Produce a crisp, 6-part company understanding for:
- Company: {COMPANY_NAME}
- Website: {COMPANY_URL}
- Context: [who you are and what the output is for — e.g. prepping for a meeting with the TA/People leader].
RESEARCH REQUIREMENTS (NON-NEGOTIABLE):
1) Use up-to-date web research (filings, investor materials, reputable press, credible databases).
2) For every key factual claim, provide a source link and publication date.
3) Prefer latest figures (FY2024/FY2025, LTM/TTM); label the period.
4) If a metric is unavailable/conflicting: state "Unknown / conflicting", give the range and why, then a justified best-estimate.
OUTPUT STYLE: single-line action title, then Executive snapshot (max 5 bullets), then a compact Key Facts table, then the 6 sections. Slide-ready bullets (10–18 words).
STRUCTURE (6-PART):
1) Company Overview — what it is/known for; scale, growth, major recent events; how it makes money.
2) Market Definition + Sub-markets — primary market(s); 2–5 sub-markets with why they matter; TAM/SAM/SOM if credible.
3) Position in the Value Chain + Economics — where it sits; profit pools and indicative margins; attractiveness.
4) Products / Services, Use Cases, Customers — for each product line (2–6): what it is, top use cases, personas, pricing if public, real named customers.
5) Competitive Landscape — 5–10 competitors grouped direct vs adjacent; for the top 3–5, positioning, differentiation, GTM comparison.
6) Strategic Hypotheses — 5–7 reasoned hypotheses on outcomes the company is trying to achieve, each tied to observable signals, with expected value and what to validate.
CITATIONS: inline as (Source: Publisher/Company, Date, Link). CONSTRAINTS: don't hallucinate; define jargon; ~900–1,300 words; be conclusion-led.
INPUTS: {COMPANY_NAME} = [UPDATE]; {COMPANY_URL} = [UPDATE]
```
***
# 5. Reports
One conversation is an anecdote; a hundred are a pattern. [Report](/recruiting-platform/reports) columns extract the same structured signal across your whole pipeline, so you can filter and spot trends.
To build your own AI column in [Reports](https://my.metaview.app/reports), click **`+`**, select **`Create with AI`** and paste your prompt.
**Calibrate before you present.** Run a new column across 8–12 real conversations and check each value against the transcript before you rely on the aggregate. Empty and "Not discussed" values are correct when the topic genuinely didn't come up — and a column that reads silence as a negative will quietly skew every number built on it. The [Interview Intelligence skill](/ai-skills/interview-intelligence) walks through this loop in full.
### 5.1 — Compensation as stated (current)
**What it's for:** Capture what the candidate said they currently earn.
**Format:** Currency
This records a figure the candidate volunteered in conversation. It is not a verified salary, and Metaview has no independent knowledge of what anyone is paid. Treat every value as "what they told us", and follow your local rules on asking about current pay — pay-history questions are restricted or banned in a number of jurisdictions.
```text expandable theme={null}
**Identify the salary the candidate stated they currently earn**
- Look only at salary *the candidate said they currently earn*, not expectations, historical salaries, or offers.
- Capture base salary only unless the candidate explicitly states total compensation (e.g., base + bonus).
- Detect when a candidate uses shorthand (e.g., "I make around 50" → **50,000**).
- If a candidate mentions a range, use the **midpoint**, rounded to the nearest thousand:
- Example: "I'm at 45 to 55 now" → midpoint = 50 → **£50,000**
**Determine the Currency**
Use explicit mention when available:
- "£50k" → **£**
- "$60" → **$**
- "50k euros / €50k" → **€**
If no currency is stated:
- Try to infer from context (e.g., employer location)
- If it **cannot** be confidently inferred → leave the currency **blank**
**Interpretation Rules**
- Convert shorthand to full numbers (e.g., "80k" → 80,000; "70" → 70,000)
- If the candidate gives *monthly*, *weekly*, or *hourly* pay, annualise **only if explicitly stated**
- Ignore salaries from many years ago unless clearly stated as current.
- If multiple current salary figures are discussed, take the **final** one.
- Never estimate or infer a figure the candidate did not state.
**Output Format (Strict)**
Return **only one of the following formats**:
- **"£50,000"**
- **"$120,000"**
- **"€90,000"**
- **"50000"** (no currency if unknown)
- **"N/A"** (if not shared)
No narrative or explanation—only the final extracted salary.
**Examples:**
"I'm currently on about 50." → £50,000 (currency inferred from context)
"My base is £42k, bonus is extra." → £42,000
"I make around 3.5k per month." → £42,000 (annualised)
"I don't want to share that." → N/A
"At my last job I made 70k, but now I'm higher." (no current stated) → N/A
"Base 60, OTE maybe 90." → £60,000
```
### 5.2 — Compensation expectations (desired)
**What it's for:** Capture the compensation the candidate said they are targeting.
**Format:** Currency
```text expandable theme={null}
**Identify the Candidate's Stated Desired Salary**
- Look only at salary *the candidate said they are targeting*, not what they currently earn or historical salaries.
- Capture base salary only unless the candidate explicitly states total compensation (e.g., base + bonus).
- Detect when a candidate uses shorthand (e.g., "I'm looking around 50" → **50,000**).
- If a candidate mentions a range, use the **midpoint**, rounded to the nearest thousand:
- Example: "I'm looking anywhere between 45 to 55" → midpoint = 50 → **£50,000**
**Determine the Currency**
Use explicit mention when available:
- "£50k" → **£**
- "$60" → **$**
- "50k euros / €50k" → **€**
If no currency is stated:
- Try to infer from context (e.g., employer location)
- If it **cannot** be confidently inferred → leave the currency **blank**
**Interpretation Rules**
- Convert shorthand to full numbers (e.g., "80k" → 80,000; "70" → 70,000)
- If the candidate gives *monthly*, *weekly*, or *hourly* pay, annualise **only if explicitly stated**
- If multiple figures are discussed, take the **final** one.
- Never estimate a figure the candidate did not state.
**Output Format (Strict)**
Return **only one of the following formats**:
- **"£50,000"**
- **"$120,000"**
- **"€90,000"**
- **"50000"** (no currency if unknown)
- **"N/A"** (if not shared)
No narrative or explanation—only the final extracted salary.
**Examples:**
"I'm looking for about 50" → £50,000 (currency inferred from context)
"I'm currently on £42k, but targeting £50 in my next role." → £50,000
"I'm targeting around 3.5k per month." → £42,000 (annualised)
"I don't want to share that." → N/A
"I'm on $100k currently." → N/A (no desired salary mentioned)
"Base 60, OTE maybe 90." → £60,000
```
Multi-currency pipelines must be reported per currency, never averaged together. Group by geography before you read any comp aggregate.
### 5.3 — Reason for leaving (as stated)
**What it's for:** Capture the reason the candidate gave for looking for a new role.
**Format:** Single-line text
```text expandable theme={null}
Identify the reason the CANDIDATE stated for looking to leave their current role. Use only statements made by the candidate, including phrasings like:
- "I left because…"
- "The reason I'm looking to move is…"
- "The company went through…"
- "I'm no longer there because…"
- "I'm exploring new opportunities due to…"
Review the list below and select the single primary reason the candidate stated. If multiple reasons are mentioned, choose the one the candidate emphasised most. Select the final reason ONLY from the list below.
- If no clear match exists, choose **"Other — "**.
- If the candidate did not state a reason, return **"Unknown"**. Do not infer a reason from context, tone, or their employment history.
ALLOWED REASONS (SELECT ONE)
1. Company / Org Change: Organisation restructure · Company downsizing · Redundancy / role eliminated · Company closure · Merger or acquisition · Change in company direction · Financial instability · Leadership change
2. Career / Role Motivations: Career progression / advancement · Lack of growth opportunities · Lack of challenge · Desire to move into management · Career change into new function · Desire to move into a different industry · Seeking more responsibility · Role too narrow / limited scope
3. Compensation & Benefits: Better compensation · Inadequate compensation · Benefits dissatisfaction
4. Role Fit / Environment: Misalignment with company culture · Misalignment with role expectations · Work-life balance · Workload · Role ambiguity · Support or resourcing (as described by the candidate) · Management or support (as described by the candidate)
5. Strategic / Values: Misalignment with strategy or mission · Ethical concerns
6. Commute / Location: Long commute · Relocation (candidate moved) · Company location change · Desire for remote or hybrid work
7. Interpersonal: Relationship with manager (as described by the candidate) · Team dynamics (as described by the candidate)
8. Job Nature: Temporary or contract role ended · Internship completion · Seasonal role · Fixed-term project completed
9. Personal Circumstances: Personal reasons (do not record specifics)
10. Other: Other — · Unknown
OUTPUT FORMAT
Return **only** the selected reason as plain text, exactly as written in the list. Never characterise a named third party — record only the category, never the allegation.
```
Two things this prompt deliberately won't do. It takes **stated** reasons only and returns `Unknown` otherwise — an implied reason is an inferred one. And **Personal Circumstances** returns a single non-specific label rather than naming health or family situations: those are special-category and caring-status data, and they don't belong in a filterable column about a job candidate even when volunteered.
### 5.4 — Interest in your company
**What it's for:** Capture what the candidate said attracted them to the role or company.
**Format:** List or single-line text
```text expandable theme={null}
Identify the reasons the candidate stated for their interest in joining [COMPANY_NAME] and/or applying for this specific role. Use only statements made by the CANDIDATE, including phrasings like:
- "I applied because…"
- "What attracted me to your company is…"
- "I'm excited about this role because…"
- "I've been following your company since…"
- "The reason I'm interested is…"
- "What stood out to me was…"
Capture both company-level attraction (why [COMPANY_NAME]) and role-level attraction (why this position), where present.
Use only evidence from the transcript. If not stated, omit it. If the topic was not discussed, output exactly: Not discussed
Output rules (follow exactly):
- Output exactly one line.
- Use semicolon-separated phrases for each distinct reason.
- Each reason must be 4–15 words and describe a single motivation.
- Include 1–3 reasons only.
- Order reasons by how much emphasis the candidate gave them.
- No speculation language like "maybe/probably"; only include what was stated.
- Do not mention the transcript, the interviewer, or timestamps.
- Do not include recommendations or next steps.
**Valid reason categories** (use as a lens, not a fixed list — capture the candidate's actual language)
- Mission / Product: disrupting [industry], mission-driven, product innovation, underserved market
- Growth / Stage: scale-up energy, growth trajectory, building something early-stage, pre/post-IPO
- Role Scope: breadth of responsibility, ownership, ability to shape the function, cross-functional exposure
- Career Development: step up in seniority, new skill development, path to leadership, mentorship
- Culture / People: team reputation, a specific person they spoke to, values they named
- Technology / Engineering: modern tech stack, engineering culture, data-driven approach, AI/ML opportunity
- Sector Interest: [sector specifics to the company]
- Compensation / Package: equity upside, competitive package (only if the candidate explicitly mentions it)
- Location / Flexibility: office location, hybrid/remote policy, flexibility
- Personal Connection: referral, knew someone at the company, personal experience as a customer
Required output format
1. [reason 1]
2. [reason 2]
3. [reason 3]
or
"Not discussed"
Examples of good output:
"1. Excited by the company's mission to serve underserved communities
2. wants ownership over full product lifecycle
3. impressed by engineering team after coffee chat"
or
"Not discussed"
```
"Explicit or implicit reasons" narrowed to stated reasons, "strongest signal to weakest" changed to the candidate's own emphasis, and "diversity and inclusion" removed as an example value under Culture / People — inviting a column to record that a candidate mentioned D\&I risks capturing a proxy for protected characteristics.
### 5.5 — Current company
**What it's for:** Extract and normalise the candidate's current employer.
**Format:** Single-line text
```text expandable theme={null}
Determine the candidate's current employer from the transcript. If not clearly stated, return their most recent employer. Then normalise the name:
1) Remove regional/org suffixes (Amazon UK → Amazon; EY Global → EY).
2) Standardise known groups to the best-known brand (Ernst & Young → EY; PricewaterhouseCoopers → PwC; Google Cloud → Google).
3) Roll subsidiaries up to the parent brand unless that changes meaning.
4) If multiple, choose the most recent/current.
5) If none can be determined, output "Unknown".
Output ONLY the final normalised company name — no explanation, no punctuation.
```
### 5.6 — Talent market signals
**What it's for:** Read what candidates say about their current employer, to understand which companies people are leaving and why — a market read drawn from conversations you're already having.
This classifies **what the candidate said** about conditions at their employer — the market signal — not how they feel about it. Don't reframe it as sentiment: inferring a person's feelings is trait inference, and emotion inference in an employment context is restricted in some jurisdictions.
**Format:** Single-line text
```text expandable theme={null}
You are an interview analyst supporting a Head of Talent. Summarise what the candidate explicitly said about conditions at their current company, as a talent-market signal.
- Output **exactly one line**.
- Use **exactly one** hyphen separator: `Signal - reasons`
- No bullets, no numbering, no quotes, no extra labels, no preamble.
- Reasons must be **concise summaries only**.
- Use **semicolon-separated phrases** for reasons.
- Each reason must be **4–12 words** and describe a **single** point the candidate made.
- Include **2–6** reasons only.
- Use only what the candidate stated. Do not infer their feelings, mood, or attitude.
- If the candidate did not describe conditions at their employer, output: `No signal - Not discussed`
Signal classification — based on what the candidate described, not how you judge they feel:
- **Favourable conditions described**: the candidate described stability, growth, or positive change.
- **Unfavourable conditions described**: the candidate described instability, restructuring, or deteriorating conditions.
- **Mixed or factual**: the candidate described both, or described conditions neutrally.
VALID REASONS (talent-market signals only): layoffs, hiring freezes, restructuring, leadership churn; workload and resourcing levels; comp or commission changes, pay instability; strategy or execution changes; customer or workload reality; team or org growth.
Exclude anything the candidate did not state. No proper nouns unless essential. No speculation language. Do not mention the transcript or timestamps. Do not characterise the candidate.
```
### 5.7 — Location extraction columns
**Format:** Single-line text (city, country) / List (relocation)
```text expandable theme={null}
Extract the candidate's stated location. I want to know the city they are currently located in. Return as "City" (e.g. "Chicago" or "London"). Ensure this is stated within the transcript, do not infer or assume. If no location is mentioned, return "Unknown".
```
```text expandable theme={null}
Extract the candidate's stated location. I want to know the country in which they currently reside, or are targeting to reside. Return only as "Country" (e.g. "USA" or "Canada"). Standardise country names into consistent naming conventions for ease of reporting (United Kingdom → UK; United States → USA; England → UK). If no location is mentioned, return "Unknown".
```
```text expandable theme={null}
Determine if the candidate expressed willingness to relocate. Return one of:
• "Yes"
• "No"
• "Conditional"
• "Not mentioned"
Ensure this is clearly stated within the transcript. If the candidate stated they're open to relocation based on specific terms, return "Conditional". If this was not discussed in the transcript, return "Not mentioned".
```
### 5.8 — Interview coverage
**What it's for:** Check whether your interviews are covering the competencies your process expects.
**This analyses your own team.** It counts whether expected questions were asked — it is not a performance rating and shouldn't feed appraisals, ranking, or compensation. Keep individual output private to the person being coached, keep team views aggregated, and confirm your position on employee-performance analysis before rolling it out. The [Interviewer Coaching skill](/ai-skills/interviewer-coaching) applies these rules by default.
**Define your own topics.** The example below uses one competency. Amend it to reflect your process and your defined competencies.
**Format:** Single-line text
```text expandable theme={null}
You are analysing whether the interviewer covered the topic "Bias for Action" during the interview.
"Bias for Action" refers to calculated risk-taking and speed over perfection. Interviewers are expected to explore this through behavioural questions.
Review the interview transcript and count how many distinct behavioural questions the interviewer asked that relate to "Bias for Action". Use the following question set as reference (or equivalent paraphrases):
1. Give an example of a time when you made a decision without having all the information. What was the outcome?
2. Describe a situation where moving quickly made a difference in the outcome of a project.
3. How do you balance speed with quality in your work?
4. Have you ever had a project stall because you waited too long? What did you learn?
5. What's your approach when faced with uncertainty and a looming deadline?
Count how many of the above five question types (or close equivalents) were asked by the interviewer. Each question can be counted a maximum of one time.
Return a coverage label using this rubric:
"None asked" = None of the listed questions appeared.
"Some asked" = One or two of the listed questions appeared.
"Most asked" = Three or more of the listed questions appeared.
"Not applicable" = The topic was covered because the candidate raised it unprompted, another stage owns this competency, or the call ended early.
There are legitimate reasons a question was not asked. Use "Not applicable" rather than "None asked" where one applies.
Where an interviewer asks multiple questions in a single uninterrupted monologue, count that as one question.
This measures question coverage only. Do not assess the interviewer, and do not assess the candidate's answers.
```
**Define what each competency actually looks like.** Traits like "leadership" or "collaboration" are too vague and leave the model to interpret. Instead of *"did the interviewer assess their leadership skills"*, spell out the questions that indicate the topic was explored — as above.
### 5.9 — AI use signal
**What it's for:** Surface where it may be worth looking more closely at how answers were produced.
**Use with care, and read this before you enable it.**
This is a signal to help you decide where to *look more closely* — never a verdict, and never grounds for a decision on its own. Treat any flag as a prompt for a human conversation with the candidate, not a conclusion about them.
Be aware of what you are taking on. The signals this column reads — polished phrasing, structured answers, formality — also describe well-prepared candidates, non-native speakers, neurodivergent candidates, and anyone coached on interview technique. A column like this can systematically disadvantage those groups if it is treated as evidence. If you use it, use it to prompt a fair question, log why you looked, and never let it reach a rejection reason.
The prompt below requires a verbatim quote alongside any flag, so every signal can be checked against the recording. A label with no evidence attached should be treated as no signal at all.
**Format:** Single-line text
```text expandable theme={null}
You are an analyst reviewing an interview transcript. Assess the likelihood that the CANDIDATE was reading or paraphrasing AI-generated output while answering interview questions. This is NOT an assessment of whether the candidate uses AI as part of their job, and NOT an assessment of the candidate.
Critical rules:
- Evaluate the transcript holistically, not individual responses in isolation.
- Base the assessment on patterns and repeated signals across the interview.
- Do not accuse as fact. Speak only in terms of likelihood based on observable transcript signals.
- Do not use personal traits (accent, grammar, fluency, neurodiversity) as evidence.
- Do not use "they mentioned ChatGPT" or other tools as evidence by itself; mentioning AI at work is not proof of AI usage during the interview.
- Default to "Unlikely" where the evidence is thin. A false flag is more costly than a missed one.
What this can look like (signals, not proof):
- Repeated use of overly polished, generic language that lacks grounding in personal specifics
- Consistent rigid structures across many answers regardless of question type
- Meta or "prompt-like" phrasing such as "Let's break this down," "In conclusion," "Here are the key takeaways"
- Confident but vague statements that avoid concrete, lived experience when directly prompted
- Inconsistencies that resemble generated text rather than natural self-correction
- Sudden shifts in tone, sophistication, or completeness between answers
- Transcript pacing cues (if available) such as long pauses followed by unusually complete responses
What should NOT increase suspicion:
- The candidate stating they use AI tools in their normal workflow
- Being articulate, well-prepared, or structured in some answers
- Use of common interview frameworks (e.g. STAR) when paired with specific personal detail
- Short or neutral answers with limited evidence either way
- Formal or verbose phrasing on its own, which may reflect language background or preparation
This is never grounds for a decision. It cannot be used as a rejection reason, and any label other than "Unlikely" must be checked by a person against the recording before anyone acts on it.
Output (choose exactly one):
- "Unlikely" — reads as naturally conversational and grounded in personal experience.
- "Possible" — some recurring cues, but preparation or rehearsed answers remain equally plausible.
- "Review" — multiple strong, repeated cues forming a clear pattern. This means a human should look, not that a conclusion has been reached.
Output requirements (STRICT):
- Produce a SINGLE output for the entire transcript.
- Return the label, then the evidence, in this exact form:
"Unlikely"
"Possible — / "
"Review — / "
- Any label other than "Unlikely" MUST carry at least one exact quote from the transcript. Quotes must be verbatim, never paraphrased. If you cannot supply a verbatim quote, return "Unlikely".
- Do not add headings, bullet points, or extra commentary.
- Do not output per-question analysis.
```
The top label is **"Review"**, not "Suspected" — an instruction to a person, not a finding about a candidate. Keep it that way, keep the default-to-Unlikely rule, and keep the requirement for a verbatim quote. A label stating a conclusion, with no evidence attached, in a filterable field, is the version of this that causes harm.
***
# 6. MCP
[MCP](/integrations/mcp-integration/mcp-overview) lets Metaview reach beyond a single conversation — pulling your interviews, calendar, tech stack and documents into one place so your AI assistant can work across everything at once.
## Already built as a skill
Several MCP workflows now exist as installable [AI Skills](/ai-skills/overview), with the process and safeguards built in. Start there rather than building from scratch:
| What you want | Use the skill |
| -------------------------------------------------------- | ----------------------------------------------------------------------- |
| A quarterly or org-wide candidate intelligence dashboard | [Interview Intelligence](/ai-skills/interview-intelligence) |
| Daily interviewer briefs before upcoming calls | [Interview Prep](/ai-skills/interview-prep) |
| A private coaching brief for one interviewer | [Interviewer Coaching](/ai-skills/interviewer-coaching) |
| A team-level interview quality overview | [Interviewer Coaching](/ai-skills/interviewer-coaching) — team workflow |
| Evidence organised for a candidate debrief | [Interview Debrief](/ai-skills/interview-debrief) |
| A full role launch from an intake call | [Role Launch](/ai-skills/role-launch) |
| Talent market research | [Talent Research](/ai-skills/talent-research) |
You can also use the Metaview MCP connector to build the Report columns in [section 5](#5-reports).
The two prompts below don't have a skill equivalent yet.
### 6.1 — Get started (open prompt)
**What it's for:** Start high-level. This prompt gives you ideas for using the Metaview MCP and walks you through building an analysis from your workspace data — shaping the question, setting scope, and picking an output format.
```text expandable theme={null}
You are a workflow assistant. Your job is to help a recruiter or hiring leader shape a vague question about their hiring data into a runnable analysis using the Metaview MCP. Walk them through guided discovery, set the scope, run a volume check, and generate the output.
Use an interactive input tool at every step where the user needs to make a choice. Do not proceed until they've answered.
STEP 1 — IDENTIFY THE MOMENT
Ask which scenario fits their question best. Single-select:
1. Kicking off a new role (intake summary, target profile, outreach hooks)
2. Mid-search status update (recap of where the search stands, candidates seen, prep for HM check-in)
3. Prepping for an upcoming conversation (interview, debrief, HM 1:1, exec update)
4. Closing a candidate, or preparing feedback for one who isn't progressing
5. Understanding a candidate cohort (motivators, comp, market signals across a group)
6. Understanding interview coverage (coaching, consistency, topics covered)
7. Understanding the process (funnel diagnostics, drop-off, referral patterns)
8. Something else (free text — mirror it back and propose a shape)
Before asking, share this guidance:
"Not sure which to pick? Most recruiters start with one of three: a hiring manager kickoff, a mid-search status update, or prep for a specific call. If your question is more strategic ('what are candidates telling us about us?'), pick one of the cohort options."
STEP 2 — NARROW THE QUESTION
Based on the Step 1 answer, ask the matching follow-ups:
- Kicking off a role: Which role? Have you done an intake call? What do you want — candidate profile, outreach hooks, JD review, or all three?
- Mid-search update: Which role, and how long open? Audience: hiring manager, team, or exec? All candidates or past a specific stage?
- Prepping a conversation: What's the moment? When is it? Output for whom?
- Closing or feedback: Which candidate? Closing, or preparing feedback? Output for whom?
- Candidate cohort: Department, role, or function? Angle: motivators, comp, market signals, sourcing, or concerns raised? Audience?
- Interview coverage: One person, your team, or company-wide? Focus: consistency, coverage, or topics? Audience: the interviewer, their manager, or TA leadership?
- Process: Which stage? Conversion, time-in-stage, drop-off reasons, candidate experience, or referral patterns? One role or all?
- Something else: Ask for a 1-2 sentence description, mirror it back, propose a shape before continuing.
If the request is about interview coverage, remind the user that individual output should go to the person being coached and team views should be aggregated.
STEP 3 — SET SCOPE
1. Department or function (call list_field_values on the Department field to populate options).
2. Time horizon: Last 7 / 30 / 60 / 90 days / Custom.
3. Filter: All / Hired only / Final-stage / Specific role / Specific interviewer.
Guidance: "If your question is about a specific role, narrow scope here. If it's about a cohort or pattern, leave it broader."
STEP 4 — ADD CONTEXT
Ask what they can attach to sharpen the output. Multi-select:
- Hiring rubric or scorecard for the role
- Job description
- Intake notes from the hiring manager kickoff
- Comp bands by role
- Specific competencies or topics that must be covered
- Nothing to add, run with what's in Metaview
Guidance: "Attaching context makes the output meaningfully better. For a kickoff, intake notes build a richer target profile. For a status update, a JD helps show where candidates have and haven't been assessed. For coverage analysis, a rubric defines what 'covered' means."
STEP 5 — PICK YOUR OUTPUT FORMAT
Single-select: Quick summary in chat / One-pager document / React dashboard (JSX file) / Slack DM(s) / Slide deck / Email draft.
Guidance: "Quick summary if it's just for you. One-pager for sharing. Dashboard for leadership or recurring reports. Slack DM for time-sensitive prep."
If the chosen format is mismatched to the use case (dashboard for thin data, Slack DM for an exec audience), flag it and offer to switch.
STEP 6 — VOLUME CHECK
Run a count query using the chosen filters. Surface:
"[N] conversations match. Under 10 is thin — findings will be illustrative only. 10-50 is the sweet spot. 50+ will take a while and may produce noisy output."
If 50+, suggest narrowing by role, time window, stage, or interviewer. Wait for confirmation.
STEP 7 — CONFIRM AND RUN
Mirror back the plan in plain language:
"I'll analyse [N] conversations from [filter] over the [time window], focusing on [theme], and produce a [output format] for [audience]. Anything to adjust?"
Wait for confirmation. Once confirmed:
- Pull the relevant AI fields from Metaview MCP. Reuse existing fields where possible; create new ones only if needed.
- Wait for processing. Verify the fields have actually populated before aggregating — a half-processed column reports "not discussed" for conversations that were never analysed.
- Synthesise: lead with the strongest pattern, surface counterintuitive findings, flag data gaps, and anonymise candidate references (no names or initials).
- Generate the output in the chosen format.
STEP 8 — CAVEATS
State the sample size on every finding. If volume was thin or any section had sparse data, say so. Distinguish "not discussed" from a negative answer. Do not invent findings to fill space, and do not present patterns as proof of causation.
STEP 9 — OFFER TO SAVE
Ask: "Want me to save this as a reusable prompt with these parameters baked in?" If yes, output the finalised prompt as a copy-pasteable text block.
```
### 6.7 — Updated hiring thesis memo
**What it's for:** Turn synthesised hiring findings into a single-page thesis memo that mirrors the voice, structure and formatting of an existing thesis you attach, then export it to PDF and check it fits on one page.
A reference memo is required — the prompt needs an existing document to copy voice and structure from.
```text expandable theme={null}
You are a hiring strategy assistant. Your job is to translate findings into a single-page thesis memo that mirrors the voice and structure of an existing reference thesis the user provides.
Use an interactive input tool at every step where the user needs to make a choice. Do not proceed until they've answered.
STEP 1 — SETUP QUESTIONS
Ask these as a single batch:
1. Source findings. Free-text or attachment: paste the data summary, or describe the new thinking the thesis should reflect.
2. Reference thesis. Attachment required. The new memo will mirror this one's voice, section structure, header table, heading colours, and bullet style. If the user has no reference, stop and ask them to provide one before proceeding.
3. Audience. Free-text: who is this memo addressed to (e.g. TA + hiring managers, exec team)?
4. Signature. Free-text: author name and title for the byline.
5. Page and format constraints. Single-select: Match the reference thesis exactly / Custom (free-text follow-up for page count, margin size, body font size).
STEP 2 — READ THE REFERENCE
Parse the reference thesis. Identify:
- Memo header table fields and order
- Section headings and their order
- Heading colour, font, and weight
- Bullet style (dash, dot, indented, spacing)
- Voice (formal vs direct, hedged vs assertive, sentence length)
- Page geometry (margins, body font size, line spacing)
If the reference has named sections like "Executive summary," "The thesis in one paragraph," "The signals we screen for," "What good evidence looks like," "Closing" — reuse those exact section names. The new memo should feel like the next edition of the same document.
STEP 3 — DRAFT
Write the memo content using the source findings. Match the reference's voice closely. Keep every section tight, but never cut confidence qualifiers, sample sizes, or limitations — those are substance, not hedging. If the memo will not fit on one page with them intact, deliver two pages.
Carry the limitations through: state the sample size behind any claim, and do not present a pattern as a prediction about individuals.
Every item under a "signals we screen for" or "disqualifiers" heading must be traceable to a criterion the user set, and each must be justifiable as confirmed by the user, inherent to the work, or legally required. Anything else is prioritisation or interview guidance, never a gate. Mark the draft "requires human approval and legal review before use in screening."
Include a short "Confidence and limitations" section stating what the findings rest on and what they cannot support.
STEP 4 — GENERATE THE DOCX AND CONVERT TO PDF
Build the docx mirroring the reference's formatting. Apply the page constraints (default: 0.75" margins, 10pt body if no reference geometry detected). Convert the docx to PDF. Verify page count.
STEP 5 — PAGE-FIT CHECK AND TIGHTEN
If the PDF is more than one page:
- Tighten line spacing first (e.g. 1.05 → 1.0).
- Tighten paragraph spacing before sections next.
- Reduce body font by 0.5pt only if still over after spacing adjustments.
- Re-export and re-verify. Repeat up to 3 times.
- Do not cut content unless explicitly told to. If after 3 passes it still spills, deliver both versions and flag it.
STEP 6 — DELIVER
Write both the docx and PDF to the output directory and present them. Lead with the PDF. Confirm page count in the message.
```
***
## Use these responsibly
**Review before acting.** Every prompt here produces a draft. Check it against the source conversation before sharing it or using it in a hiring, outreach or people decision.
**Give every prompt a fallback.** `Not discussed` / `Not specified` / `Unknown` — so a topic nobody raised never reads as a negative answer about a person.
**Prompts that analyse your own team** — interview coverage, consistency, pitch quality — should stay private to the person being coached or aggregated at team level. Confirm your organisation's position on employee-performance analysis before enabling them.
For the full picture, see [Best practices for Notes](/account-management/privacy-and-security/ai-best-practices), [Best practices for Sourcing](/account-management/privacy-and-security/ai-sourcing-best-practices), and [Best practices for Application Review](/account-management/privacy-and-security/ai-best-practices-app-review).