• SCORE
  • RANK
  • GAP
  • HUMAN

How to score mentor startup pairings with your AI

Connect your mentor and startup data once. Your AI then handles the heavy lifting of calculating match scores based on specific criteria.

Ask AI about this page

Short answer

How can I use AI to score mentor and startup matches?

Your AI analyzes the expertise of your mentors and the specific stage of your startups to produce a compatibility score. You get a ranked list of pairings that fit your program's requirements. This breakdown shows how the scoring works.

The matching outcomes

Where every match lands.

The AI processes your data to produce these specific results.

SCORE

Numerical match quality

The AI uses evaluate_match_quality to assign a specific score to every pair. You see exactly how well a mentor's background aligns with a startup's current needs.

RANK

Prioritized pairing lists

Instead of guessing, you get a sorted list of the best possible matches. This helps you decide which mentors to introduce to which founders first.

GAP

Missing expertise identification

The AI flags where a startup lacks a specific type of mentor. You'll know exactly which expertise areas you still need to recruit for your program.

HUMAN

Final selection review

The AI provides the data, but you make the final call. You use the scores to guide your intuition during the actual introduction process.

The workflow

What your AI does when the data arrives.

The AI acts as a data analyst, comparing two distinct datasets to find the strongest links.

  1. Data ingestion

    Your AI reads the mentor profiles and startup descriptions you provide. It extracts key technical skills, industry experience, and company stages.

    evaluate_match_quality

  2. Compatibility calculation

    The agent compares the mentor's specialized knowledge against the startup's current growth phase. It looks for specific overlaps in expertise.

    evaluate_match_quality

  3. Scoring and ranking

    The AI converts these comparisons into a standardized quality score. It then organizes these scores so the highest-value matches appear at the top.

    evaluate_match_quality

  4. Insight generation

    The AI summarizes why certain matches scored high or low. It highlights the specific reasons for a strong connection or a significant mismatch.

    evaluate_match_quality

Try it

Copy these to start.

Use these prompts to trigger the matching process.

Starting points

These are opening lines. Replace the bracketed text with your actual file names or database links.

Accelerator Mentor Match Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_20phNeormGQUqEuEuOZY51qFatUpfRT4rfvGwoNk/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Accelerator Mentor Match capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "accelerator-mentor-match-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_20phNeormGQUqEuEuOZY51qFatUpfRT4rfvGwoNk/mcp"
    }
  }
}
Copy into chat04

  • Score the matches between the mentors in mentors.csv and the startups in startups.json.

  • Compare the expertise in my Google Sheet of mentors against the startup profiles in this folder.

  • Give me a ranked list of the top 5 mentor matches for the startup listed in this document.

  • Analyze the match quality for the mentor in this contact list against our current seed-stage startups.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Accelerator Mentor Match once, then ask.

Just link the MCP to your client. Your credentials stay encrypted, and you can start asking questions immediately.

Connect Accelerator Mentor Match to your AI

FAQ

How this task behaves

  • 01

    Can the AI automatically send introduction emails to the mentors?

    No. The AI only calculates and provides the match scores. You must handle all communications yourself.

  • 02

    Does the AI change my original mentor or startup data?

    No. The AI only reads your data to perform the evaluation. It cannot edit, delete, or overwrite your files.

  • 03

    How does it decide what a 'good' match is?

    It uses the expertise and stage data provided in your files to run the evaluate_match_quality tool.

  • 04

    Can I use this with any AI client?

    Yes, as long as your client is MCP-compatible, like Claude, Cursor, or Windsurf.

  • 05

    What happens if a startup has no matching mentor expertise?

    The AI will return a low quality score for those pairings, highlighting the gap in your current mentor pool.

  • More questions about Accelerator Mentor Match? The Connector page answers them. See everything the Accelerator Mentor Match Connector can do

Connect Accelerator Mentor Match to Claude, Cursor, ChatGPT & more