DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run deterministic evals on the collaboration workflow with Agent Me

Run the versioned fixtures and see the pass count for the verified workflow.

Who it is forA maintainer or evaluator who needs repeatable results before trusting changes to the role pipeline.

The problemBehavior of a multi-role AI pipeline can drift without anyone noticing unless it is measured the same way each time.

The outcomeA deterministic report of supported, unsupported, adversarial, and boundary cases for the verified workflow.

What you need first

  • Docker with the Compose plugin, or Python 3.11+, uv 0.11 or 0.12, Node.js 22+, npm, and Git
  • Markdown notes you are allowed to use and want the twin to read
  • Read docs/TRUST.md before loading private knowledge

Steps

  1. make setup
  2. make evaluate
  3. .venv/bin/python scripts/evaluate_collaboration.py --workflow verified --json
  4. Confirm the default evaluator reports COLLABORATION_EVAL 4/4 passed.

Prompt for your agent

In the jzjzzzzzzz/agent-me repository, run the collaboration evaluator with the verified workflow in JSON mode. Return the pass count and any failed case IDs. Verify that rerunning the same command on unchanged code gives the same result.

Caveat. The fixtures are small and fictional, so a passing score shows that the checks run, not that the twin represents a real person well.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page