get-convex/convex-evals

1

add-model Add a new AI model to the eval runner, update the manual eval workflow, push changes, and trigger baseline eval runs.…

get-convex/convex-evals

5

2

analyze-ablation Analyze guideline ablation experiment results to determine which guideline sections are essential, marginal, or dispe…

get-convex/convex-evals

5

3

validate-guidelines Empirically verify guideline changes by running before/after eval runs across multiple models and ensuring no regress…

get-convex/convex-evals

5

4

add-eval Design, implement, validate, and calibrate a new eval for the convex-evals suite. Use when the user wants to add a ne…

get-convex/convex-evals

4

5

analyze-eval Investigate a single failing eval from the convex-evals system. Use when the user shares a visualizer URL pointing to…

get-convex/convex-evals

4

6

analyze-run Analyze all failures in a convex-evals run, spawning parallel sub-agents to investigate each failure and producing a …

get-convex/convex-evals

4