Versalist guides
5 public guides
2 tracks

Guides for verified agent changes

Define the task, keep the evaluation contract stable, inspect the evidence, and record the release decision. Each guide supports part of the closed agent-improvement loop.

Evaluation systems
Agent Evaluation

Start here when a score cannot show whether an agent change is safe.

Change discipline
Prompt and Policy Changes

Use this track before you publish a new instruction, dataset, or policy revision.

Evaluation systems
3 guides

Evaluation systems guides

Define tasks, run agents, grade results, inspect failures, and control changes.

Best for

Teams that need reproducible evidence before an agent change reaches production.

Suggested entry
Agent Evaluation

Start here when a score cannot show whether an agent change is safe.

Start with this guide
Change discipline
2 guides

Change discipline guides

Treat prompts, data, and policy instructions as versioned agent components.

Best for

Teams that improve agents and need proof against regressions.

Suggested entry
Prompt and Policy Changes

Use this track before you publish a new instruction, dataset, or policy revision.

Start with this guide
More guides

Keep going