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

How to review agent failures and approve proposed fixes with Agent Foundation

Inspect execution evidence in Findings and ask Composer for a reviewed change.

Authorization notice. Agent Foundation is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn operator running agents in Service who needs to find why runs failed and decide what to change.

The problemFailed agent runs are hard to diagnose, and fixes applied without review can make things worse.

The outcomeA recorded diagnosis and a proposed Agent revision that you reviewed and approved before anything was published.

What you need first

  • Docker with Docker Compose for the self-hosted Service stack
  • A model provider API key or an eligible ChatGPT plan
  • Python 3.13 and uv for the Harness library or Harness UI
  • A trusted machine, since Harness UI Full Control runs as your host account

Steps

  1. Start the stack with docker compose -f a13n-service.yaml up -d --wait --pull always.
  2. Open Findings in the Console and review the scanned diagnoses and their status.
  3. Inspect the evidence for one diagnosis and record your judgment.
  4. Send the cited Agent revision and evidence to Composer to request a proposed change.
  5. Review the proposed change and approve or reject it. Nothing is repaired or published automatically.

Prompt for your agent

In the agent-foundation Service Console, open Findings and list the diagnoses with status for <agent-name>. Pick one, summarize its cited evidence, and confirm that no change was published before you review it.

Caveat. Findings depends on existing execution evidence, so it only helps after agents have run through a Service stack that is recording traces.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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