←Back/Sales/ChatGPT
IntermediateSales

How to Automate LinkedIn Recruiting with a ChatGPT AI Agent

Use a browser agent to produce a LinkedIn sourcing shortlist from a job description and job-related criteria, while keeping login, profile validation, outreach, and every hiring decision with people.

How to Automate LinkedIn Recruiting with a ChatGPT AI Agent

Source episode · 02:00

How I AI: Automate Recruiting and Build Interactive Personas with Michal Peled of HoneyBook

with Claire Vo

Michal gives ChatGPT Agent a recruiter role, a job description, and explicit sourcing criteria, lets it navigate LinkedIn after manual login, and has the hiring manager validate the linked shortlist.

Read the full episodeWatch on YouTubeListen on SpotifyListen on Apple

Before you start

What you need

  • An approved sourcing process and LinkedIn account
  • A current job description and job-related sourcing rubric
  • Lawful work-location or eligibility requirements
  • ChatGPT Agent access
  • A recruiter or hiring manager who owns review

What you’ll make

A private shortlist with direct profile links, criterion evidence, uncertainty, and no automated outreach or candidate disposition.

Tools used

Step by step

The workflow

Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.

4 steps

Step01

Craft the 'Little Helper' Prompt

Interview the recruiter about the exact sourcing process, then convert it into job-related inclusion criteria, exclusion rules, evidence requirements, and explicit actions the agent may not take.

Example prompt
You are an IT recruiter. 
Log into LinkedIn using my account. If not already logged in, let me take control and log in. Find up to five LinkedIn profiles where the current title and job description match the attached job description. 
Restrictions:
- Candidates must be from Israel or currently working at an Israeli company.
- They must be active in LinkedIn within the last three months.
- The current job role must be close enough to the open role in title and seniority.
- The candidates must either work in their current workspace more than a year, or they can be unemployed, but no more than a year, and have worked in their last workplace for over a year.
Step02

Provide the Job Description

Attach the current job description and instruct the agent to return a small shortlist. Require manual login takeover, direct profile links, evidence for each criterion, and uncertainty instead of unsupported match claims.

Example prompt
Act as a sourcing assistant. After I complete any required login, find up to [count] LinkedIn profiles relevant to the attached role. Use only these job-related criteria: [criteria]. For each person, return the direct profile URL, current role evidence, criterion-by-criterion notes, missing information, and a non-binding fit summary. Do not infer protected traits, message anyone, or change candidate status.
Step03

Unleash the Agent

Run the agent in the approved environment and take control for authentication or any unexpected sensitive action. Stop if the site blocks automation or the task leaves the defined sourcing scope.

Step04

Review and Validate the Results

Have a recruiter open every profile, verify the evidence, remove false or inappropriate matches, check for duplicates, and decide separately whether outreach is warranted. Record feedback to improve the rubric, not to automate the hiring decision.

Send the list to the hiring manager for validation. This helps verify the agent's accuracy and can uncover high-quality candidates that were missed during manual searches.

What good looks like

  • Every listed profile exists and matches the cited public evidence.
  • The rubric excludes protected traits and unjustified demographic proxies.
  • A human recruiter validates the shortlist before it enters the hiring system.
  • The agent does not message candidates, reject them, or make the hiring decision.

Build your next product with ChatPRD

Turn an idea into a PRD, user stories, and a plan.

Try ChatPRD free

After the steps

Runbook notes

How to recover when the loop fails and where human judgment helps.

Recover

If it goes sideways

Agent browsing conflicts with account controls or platform rules
Stop the run, use an approved sourcing method, and confirm the organization’s platform and privacy requirements before continuing.
A score hides missing evidence or subjective assumptions
Require criterion-level evidence and uncertainty, and treat scores only as sorting aids.
Location, tenure, activity, school, name, or photo becomes a proxy for protected traits
Keep only job-related, lawful requirements, remove appearance and identity signals, and audit comparable searches for disparate exclusions.
The agent starts messaging or changing candidate status
Remove messaging and recruiting-system permissions; require a named recruiter to approve any contact or disposition.

Keep building

Related workflows

Create an Automated Workout Tracker with a Simple Claude Voice Note
beginnerPersonalClaude

Create an Automated Workout Tracker with a Simple Claude Voice Note

Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.

Open
How to Rebuild Your Gmail Inbox Inside Claude to Manage Email
advancedOperationsClaude

How to Rebuild Your Gmail Inbox Inside Claude to Manage Email

Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.

Open
Automate Client Proposals and Onboarding with a Claude 'Pipeline Operator'
intermediateSalesClaude

Automate Client Proposals and Onboarding with a Claude 'Pipeline Operator'

Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.

Open

Start shipping
better products.

Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.

Start building freeRequest a demo
Free to start
No credit card
SOC 2 certified
Enterprise ready