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 chief strategy officers

Startup Scouting Agent

Maintain a verified, ranked list of startups for each theme and refresh it monthly

Startup Scouting Agent: what goes in, what the agent does and what you get

What it does

A team needs startups in battery recycling and finds them through conference chatter. This agent takes a theme and searches funding news, product launches and startup databases. It builds a list of candidates and scores each on fit with the theme, stage and traction, such as customers, revenue signals and team strength. It checks for conflicts, for example a competitor of a current partner or a company already in the portfolio, and verifies key facts with a second source. If the list is thin, it widens the search terms and runs again. It rechecks monthly for new entrants and for changes in funding. The lead approves any outreach. Edge case: a startup with one source claiming big customers is marked unverified.

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 Theme set or monthly refresh 2 USES A TOOL Search funding news, launches and databases 3 DOES Build the candidate list 4 DOES Score fit, stage and traction 5 CHECKS THE RESULT Are key facts confirmed by a second source? If not: Search for another source or mark the factunverified. Back to step 3. 6 USES A TOOL Check conflicts with partners, competitors and theportfolio 7 CHECKS THE RESULT Are there at least 10 qualified candidates? If not: Widen the search terms and repeat. Back to step2. 8 DOES Rank and draft one-page summaries 9 YOU APPROVE Lead approves any outreach 10 RESULT Ranked list and monthly change log
Read the steps as a list
  1. Theme set or monthly refresh
  2. Search funding news, launches and databases
  3. Build the candidate list
  4. Score fit, stage and traction
  5. Are key facts confirmed by a second source?If not: Search for another source or mark the fact unverified. Back to step 3.
  6. Check conflicts with partners, competitors and the portfolio
  7. Are there at least 10 qualified candidates?If not: Widen the search terms and repeat. Back to step 2.
  8. Rank and draft one-page summaries
  9. Lead approves any outreachThe agent waits here for your OK.
  10. Ranked list and monthly change log

How it decides

It ranks startups by fit, stage and traction and includes only those with at least 2 sources for key facts.

  • Include only companies with key facts in 2 sources
  • Exclude conflicts flagged by partners or the portfolio
  • Rank by fit first, then traction
  • Treat funding older than 24 months as lower priority

Make it yours

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

  • Theme and criteria (default set per theme)
  • Minimum list size (default 10)
  • Refresh frequency (default monthly)
  • Source requirement (default 2 sources)

What keeps you in control

It always asks you first

  • Lead approves any outreach to a startup

Hard limits

  • Never contact a startup without approval
  • Mark unverified facts clearly
  • Do not share confidential strategy in searches

It stops when

  • Done: Ranked list delivered and refreshed monthly
  • Stop: Theme is unclear, so ask the lead to define it

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 happensFor the theme battery recycling the agent finds 31 startups and keeps 14 after the two-source check. 3 conflict with a partner and are removed. The list drops to 8 candidates, under the 10 needed, so the agent adds the term second-life batteries and reaches 13. The lead approves outreach to 3.

More agents for chief strategy officers