Overview › 1 Modelsa. Benchmarking workloads
Benchmarking workloads Analyze workloads and test models across each. Nothing lives here yet.
See also 1.b.i Pick the model per role or call site rather than one model everywhere, and set its reasoning effort and sampling parameters per site; tune each role's prompt to its model (GEPA raised every model tested at lower cost).
2.a.iii Decide the action interface deliberately, by model and by task, and provision what it needs.
Try it for yourself Paste this into Claude Code, or any coding agent, in your agent's repo to check it for these optimizations.
Read these agent optimizations (Models: Benchmarking workloads), each with the signs that it applies:
- 1.b.i Match the model and its effort to each call site and query class: https://mahalsystems.ai/aot/optimizations/model-and-effort-per-call-site.md
- 2.a.iii Choose how the agent acts: typed tools, code execution, or shell, matched to the model and task: https://mahalsystems.ai/aot/optimizations/choose-action-interface.md
Then check whether any of them applies to the agent in this repository. Look for each one's signs under "When it applies" in its code, prompts and tools, and in any traces or eval results you can find. Tell me which apply, strongest first, with what you found for each. Don't change anything yet. Copy prompt 
Mahal Systems