All templates
FeaturedAI#LinkedIn#Recruitment#AI#HR#LLM#Slack

LinkedIn AI Candidate Search & Ranker

Search LinkedIn for candidates via the API, rank each profile with GPT-4o against your job description, and post a shortlist to Slack.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#LinkedIn#Recruitment#AI#HR#LLM#Slack

Click a node to select it — same as the Heym editor; the panel shows its settings.

7 nodes · Free & source-available

LinkedIn AI Candidate Search & Ranker

Automate the first pass of your recruitment funnel. Provide a job description, pull matching candidate profiles from the LinkedIn People Search API, let an LLM score each one 1–10 against your ICP, and get a ranked shortlist in Slack — all without opening LinkedIn manually.

What this workflow does

  1. JobDescription — enter the role title, must-have skills, and seniority level
  2. SearchLinkedIn — POST to the LinkedIn People Search API with extracted keywords
  3. IterateCandidates — Loop over each returned profile
  4. RankCandidate — LLM scores the profile 1–10 against the job description and writes a one-line rationale
  5. CandidateScore — Set node normalises the score and contact URL
  6. TopCandidates — Output captures the full ranked list when the loop finishes
  7. NotifyHR — Slack posts the top 5 shortlisted candidates to your hiring channel

Use cases

  • Inbound sourcing: rank applicants from a parsed ATS export
  • Outbound sourcing: search LinkedIn for passive candidates matching a niche role
  • Bulk re-ranking when a job description changes

Setup

  1. Get a LinkedIn API access token (via the LinkedIn Developer Portal) and add it as Authorization: Bearer YOUR_TOKEN in the SearchLinkedIn HTTP node.
  2. Connect an OpenAI-compatible credential in the RankCandidate LLM node.
  3. Add a Slack credential and set your hiring channel in the NotifyHR node.
  4. Edit the JobDescription textInput with a real role spec before the first run.

Notes

  • LinkedIn API rate limits apply — add a Wait node between iterations for large searches.
  • Swap the LinkedIn HTTP node for an Apollo.io or Hunter.io endpoint to enrich without a LinkedIn developer account.
  • The LLM score is advisory; always review the rationale before outreach.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym