AI LunchroomPractice AI. Do real work.
AI prompts by job

AI prompts for employment law intake coordinators

You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help. These prompts are written for that work — copy one into ChatGPT, Claude, Copilot, or Gemini, or practice it with step-by-step feedback and keep the ones you reuse.

What AI is actually good for in this job

Not everything — but these four come up every week, and they are all writing tasks, which is where today's tools are strongest.

Before you paste anything

What never goes into a chatbot in this job

Never paste the caller's name, employer name, allegations, supervisors' names, pay details, medical or immigration information, documents they send, or anything about what happened. Even prospective clients' stories are confidential. Describe the intake generically — 'a caller says they were terminated after a complaint' — and keep names and facts out.

Which tool: Employment firms are often small plaintiff-side practices with limited tech policy, but confidentiality rules still apply to prospective clients. Use AI for templates, scripts, and generic letters, and ask the attorney before it touches any caller's story.

Write the intake questionnaire for someone who believes they were wrongfully fired

The rough version you start from
Caller says they were fired after reporting a safety concern. Need questions that cover: dates (hire, complaint, termination), who they reported to, whether it was written, reason given for firing, any warnings, pay and hours, any contract or handbook, whether they have documents or recordings, and whether they've signed anything since. Short, in order.
Copy this prompt
I work in employment law intake. Help me with the task below — I will review and edit what you give me before I use it.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Write the intake questionnaire for someone who believes they were wrongfully fired

Source material:
Caller says they were fired after reporting a safety concern. Need questions that cover: dates (hire, complaint, termination), who they reported to, whether it was written, reason given for firing, any warnings, pay and hours, any contract or handbook, whether they have documents or recordings, and whether they've signed anything since. Short, in order.

What to give me:
Turn this into a numbered intake questionnaire grouped by topic that a coordinator can read aloud, with a note not to give any opinions.

Boundaries:
- Use only the facts in the source material. Do not invent names, dates, amounts, or promises.
- If something needed is missing, list it as a question at the end instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Before you use it: Have the attorney remove anything that sounds like advice and add any question your jurisdiction's claims need.

Draft the polite decline letter when the firm cannot take a case

The rough version you start from
The attorney reviewed an intake and the firm can't take the matter because it falls outside the practice area. We shouldn't say why in detail. Caller should know there may be strict time limits for pursuing a claim and should contact another attorney or an agency right away. No advice about what to do.
Copy this prompt
I work in employment law intake. Help me with the task below — I will review and edit what you give me before I use it.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Draft the polite decline letter when the firm cannot take a case

Source material:
The attorney reviewed an intake and the firm can't take the matter because it falls outside the practice area. We shouldn't say why in detail. Caller should know there may be strict time limits for pursuing a claim and should contact another attorney or an agency right away. No advice about what to do.

What to give me:
Draft a short, kind non-engagement letter stating the firm is not representing them, time limits may apply, and they should seek other counsel soon.

Boundaries:
- Use only the facts in the source material. Do not invent names, dates, amounts, or promises.
- If something needed is missing, list it as a question at the end instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Before you use it: Have the attorney approve the wording on time limits and confirm the letter contains no opinion about the merits.

Remind a prospective client to preserve emails, texts, and documents

The rough version you start from
Prospective client is still employed and plans to resign next week. They may have texts, emails, and a notebook of dates. They are worried about deleting things by accident. The attorney wants them to keep everything, avoid posting online about it, and not take company documents they weren't allowed to take.
Copy this prompt
I work in employment law intake. Help me with the task below — I will review and edit what you give me before I use it.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Remind a prospective client to preserve emails, texts, and documents

Source material:
Prospective client is still employed and plans to resign next week. They may have texts, emails, and a notebook of dates. They are worried about deleting things by accident. The attorney wants them to keep everything, avoid posting online about it, and not take company documents they weren't allowed to take.

What to give me:
Write a simple checklist for what to keep, what to avoid, and who to call if unsure, in friendly plain language.

Boundaries:
- Use only the facts in the source material. Do not invent names, dates, amounts, or promises.
- If something needed is missing, list it as a question at the end instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Before you use it: Remove any instruction about company documents or recordings the attorney hasn't approved, since rules vary by jurisdiction.

Summarize an intake call into a one-page brief for the attorney

The rough version you start from
Intake call: caller worked two years as a delivery driver, says classification changed from employee to contractor eight months ago, hasn't been paid overtime, has texts from dispatch. Employer is a regional company. Wants a callback. Seems credible but nervous. Important: wants to remain anonymous to coworkers.
Copy this prompt
I work in employment law intake. Help me with the task below — I will review and edit what you give me before I use it.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Summarize an intake call into a one-page brief for the attorney

Source material:
Intake call: caller worked two years as a delivery driver, says classification changed from employee to contractor eight months ago, hasn't been paid overtime, has texts from dispatch. Employer is a regional company. Wants a callback. Seems credible but nervous. Important: wants to remain anonymous to coworkers.

What to give me:
Create a one-page intake brief with headings for facts reported, dates, documents mentioned, urgency, and the caller's requests.

Boundaries:
- Use only the facts in the source material. Do not invent names, dates, amounts, or promises.
- If something needed is missing, list it as a question at the end instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Before you use it: Confirm the brief records the caller's statements as claims, not facts, and adds no legal conclusions or dates.

More prompts for this job

Drawn from AI Lunchroom's Legal, Compliance & Risk practice labs and rewritten for this role. See every Legal, Compliance & Risk prompt.

Plain-language summary

Summarize a policy excerpt in plain language without adding legal advice.

Copy this prompt
I work in employment law intake. Help me create one plain-language summary that I can review and edit before use.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Create a plain-language summary that separates what the policy text literally says from any interpretation of what it means.

Source material:
"Marcus from Support pinged me again about the AI-tools clause -- his team keeps asking what it actually means and getting a different answer from whoever they ask. Here's the piece everyone's stuck on: 'Employees may use approved communication tools for business purposes. Confidential information must not be shared with external systems unless authorized by policy and management.' Can you turn that into something his team can read in two minutes flat, split into what it literally says versus what people keep assuming it means? Last quarter somebody told his team it meant no ChatGPT ever, full stop, and that wasn't right, so I don't want another guess dressed up as an answer. Need it before his 9am standup Thursday."

Return only the finished work:
plain-language summary

Boundaries:
- Do not invent facts. Label missing information clearly.
- If information is missing, label it as missing instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Policy plain-language summary

Summarize an internal policy into plain do and don't points — no legal advice.

Copy this prompt
I work in employment law intake. Help me create one plain-language do points that I can review and edit before use.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Turn a policy excerpt into plain-language do/don't points and a short 'ask a person if' list. Do not give legal advice.

Source material:
"Hey -- new AI-use policy just dropped from Legal and half of engineering already has questions in the Slack channel. Section 4.2 is the part that matters: 'Employees may use approved AI tools for non-confidential drafting work; no confidential, regulated, or client data may be entered into any AI tool absent written authorization from the Compliance Office; where classification is uncertain, the requestor shall escalate to the designated policy owner prior to use.' Renata in HR already asked if she can use it to draft an offer letter that references a candidate's visa status, and Owen on the vendor team wants to paste a supplier's SOC 2 report into ChatGPT to summarize it. I need something the whole team can actually read before Tuesday's town hall."

Return only the finished work:
1. plain-language do points
2. don't points
3. 'ask first if' list

Boundaries:
- Do not invent facts. Label missing information clearly.
- If information is missing, label it as missing instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

Question list builder

Generate clarifying questions for a legal or compliance review request.

Copy this prompt
I work in employment law intake. Help me create one clarifying question list that I can review and edit before use.

Relevant context:
- Role: Employment Law Intake Coordinator
- Work context: You screen callers who say they were fired, harassed, or not paid, collect dates and documents before the attorney spends time on them, and tell people no when the firm can't help.

Task:
Build a review-intake question list for this addendum request without answering whether Section 4.2 is legally acceptable.

Source material:
"Hey — can you take a look at this before Friday? Corrigan Fulfillment sent over an updated data-sharing addendum for the Warehouse Ops contract, matter #LC-2291. Section 4.2 says they can share our inventory data with a subcontractor we've never worked with — no name, just 'an affiliate.' Procurement wants to sign this week so the shipping integration doesn't slip. Can you just tell me if Section 4.2 is okay to sign as-is?" — Dana, Procurement

Return only the finished work:
clarifying question list

Boundaries:
- Do not invent facts. Label missing information clearly.
- If information is missing, label it as missing instead of guessing.
- If I type "STOP FOR NOW", stop expanding the work and give only the best partial version from the information already provided.
Open in your agent

Copies the prompt and opens your tool in a new tab — paste it into the chat box (Ctrl or ⌘ + V), then fill in your own details. Remove private or sensitive information before using AI for workplace tasks.

How to use ChatGPT or Copilot for employment law intake work

  1. Start from your own rough version. Type or dictate what you would have written anyway, however messy. A prompt built on your real note beats a blank-page request every time.
  2. Say who it is for and how long it should be. "Two sentences for a supervisor" and "a checklist a new hire can follow" produce completely different output from the same facts.
  3. Strip the identifying details first. The caller's name, employer name, allegations, supervisors' names, pay details, medical or immigration information, documents they send, or anything about what happened. Even prospective clients' stories are confidential. Describe the intake generically — 'a caller says they were terminated after a complaint' — and keep names and facts out.
  4. Read every specific it produces. AI fills gaps with plausible invention — dates, amounts, names, policy numbers. If you did not supply it, do not trust it.
  5. Keep the ones that work. The value compounds when you stop rewriting the same prompt. Save it with a note about when to use it.
Practice, don't just copy

Get better at these — free

Copying a prompt is a start. AI Lunchroom walks you through the task step by step with your own work, checks what your AI tool gives back, and saves the prompts you will reuse. Free to start, no credit card.

Related jobs in Legal, Compliance & Risk

Employment Law Intake AI questions

can ai tell a caller if they have an employment case

No. Whether someone has a claim depends on facts, jurisdiction, and deadlines that only an attorney can evaluate, and a wrong early assurance can hurt the person. AI can help you build the intake questions and the decline letter; the attorney decides whether to take the matter.

how do i write a non-engagement letter

State plainly that the firm is not representing them, that the firm has given no legal advice, and that time limits may apply so they should speak to another attorney promptly. AI can structure the letter, but the attorney should approve the exact wording and any mention of deadlines.