Overview › 1Models

Models

1 optimization in 3 sub-categories.

a.Benchmarking workloads

Analyze workloads and test models across each

Nothing lives here yet.

See also

1.b.i

Match the model and its effort to each call site and query class

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).

Models › Finding specialists
Better qualityLower cost

Tier 3 · tuning · changes model, prompt · any agent · 19 sources, 6 measured
2.a.iii

Choose how the agent acts: typed tools, code execution, or shell, matched to the model and task

Decide the action interface deliberately, by model and by task, and provision what it needs.

Tools › Refactoring
Lower costMixed quality

Tier 3 · tuning · changes tool surface, model · tool use agents · 22 sources, 10 measured

b.Finding specialists

i.

Match the model and its effort to each call site and query class

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).

Better qualityLower cost

Tier 3 · tuning · changes model, prompt · any agent · 19 sources, 6 measured

c.Using cheaper models

Cheaper models with verifiable outputs

Nothing lives here yet.

See also

6.a.i

Oracle-worker multi-model

Let a cheap model do the work and call an expensive one only when a trigger fires: a cascade escalates when the cheap answer looks unreliable or fails a check, a router picks the model before the call, and an advisor tool lets a cheap agent consult a stronger model mid-task.

Topologies › Escalating
Better governanceMixed qualityMixed costMixed performance

Tier 4 · restructuring · changes model · any agent · 6 sources, 5 measured