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

How to run the synthetic incident evaluation against one API with Agent Py

Measure predictions and latency on versioned synthetic incident inputs.

Who it is forA developer who wants to compare how the diagnosis agent behaves after a change, using a fixed set of scenarios.

The problemChecking diagnosis quality by hand is slow and hard to repeat across code changes.

The outcomeA record of actual predictions and latency per scenario, tied to the API you selected.

What you need first

  • Python 3.10+, uv, Node.js 22+, and Docker Compose installed locally
  • Access to a configured Qwen-compatible model service and its API key
  • Tencent CLS credentials if you use the CLS integration
  • Git clone of kkjiangk/agent-py

Steps

  1. Read evaluations/README.md for the runner instructions and the required inputs.
  2. Start a local API by following ./scripts/start-local.sh or the manual steps in docs/getting-started.md.
  3. Point the runner at the API address you selected, as described in evaluations/README.md.
  4. Save the predictions and latency output from the run for comparison with later runs.

Prompt for your agent

In the kkjiangk/agent-py repository, follow evaluations/README.md to run the synthetic incident evaluation against the API at <api address>. Report the predictions and latency for each scenario. Verify that the output lists every scenario in the versioned dataset.

Caveat. The dataset is synthetic, and the runner does not measure model token cost, citation correctness, or MTTR unless you capture those separately.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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