Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for job seekers

Job Search Funnel Review Agent

One clear, data-backed change to the search plan for next week

Job Search Funnel Review Agent: what goes in, what the agent does and what you get

What it does

A job search can feel stuck, but you cannot fix what you cannot see. This agent reads your pipeline log and works out how many applications turned into replies, screens, interviews and offers. It compares those rates by role level, source and resume version. It then tests simple explanations, such as aiming too senior or relying on one job board, against the data and checks whether each one holds up. If the data is too thin, it says so and does not guess. It ends by recommending one change for next week. Edge case: most replies came through referrals, so the agent compares referral and board results separately before drawing a conclusion.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Weekly review time 2 USES A TOOL Read the pipeline log 3 DOES Compute conversion at each stage 4 DOES Split rates by role level, source and resume version 5 DOES List possible explanations from the splits 6 CHECKS THE RESULT Does each group have enough entries to support aconclusion? If not: merge groups or widen the date range, thenrecompute. Back to step 3. 7 DOES Test each explanation against the numbers 8 CHECKS THE RESULT Does one explanation account for the weakest stage? If not: discard it and test the next explanation, ormark the result unclear. Back to step 5. 9 DOES Recommend one change for next week 10 YOU APPROVE Job seeker approves the new plan 11 RESULT One-page funnel summary and next week's change
Read the steps as a list
  1. Weekly review time
  2. Read the pipeline log
  3. Compute conversion at each stage
  4. Split rates by role level, source and resume version
  5. List possible explanations from the splits
  6. Does each group have enough entries to support a conclusion?If not: merge groups or widen the date range, then recompute. Back to step 3.
  7. Test each explanation against the numbers
  8. Does one explanation account for the weakest stage?If not: discard it and test the next explanation, or mark the result unclear. Back to step 5.
  9. Recommend one change for next week
  10. Job seeker approves the new planThe agent waits here for your OK.
  11. One-page funnel summary and next week's change

How it decides

A cause is accepted only if the data shows a clear gap between groups and each group has at least ten entries. Otherwise the result is marked unclear.

  • Compute each stage rate from the entries that reached the previous stage
  • Require ten or more entries per group before comparing
  • Recommend only one change at a time
  • Say unclear rather than invent a cause

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Minimum entries per comparison (default: 10)
  • Splits to run (default: level, source, resume version)
  • Review day (default: Sunday)
  • Funnel stages to track

What keeps you in control

It always asks you first

  • Job seeker approves the plan change

Hard limits

  • Never invents numbers for missing stages
  • Never changes the log

It stops when

  • Done: one change is chosen and approved
  • Stop: fewer than 20 logged applications, so the agent asks for more data

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensA seeker logged 46 applications with 4 replies. Splits showed 3 of 4 replies came from referrals and only 1 from 38 board applications. The first test blamed seniority, but groups were too small, so the agent merged them and rechecked. Source was the stronger signal. It recommended five referral requests next week, which the seeker approved.

More agents for job seekers