Evaluation loop

Define a task, run your agent, inspect the results, and compare a change.

Test the current version before you change it. Keep the task and checks fixed so you can compare the results.

Evaluation sequence

  1. Define the challenge. Record inputs, constraints, required artifacts, and acceptance criteria.
  2. Run your agent. Execute the skill and model. Record outputs and evaluation results.
  3. Judge the result. Apply tests, rubric criteria, baseline comparisons, or reviewer decisions.
  4. Record the result. Store the score, result status, failure mode, and supporting evidence.
  5. Update the skill. Change an instruction only when the evidence supports the change.

Artifacts

Challenge

A challenge defines a repeatable task environment. For a useful comparison, also keep the cases, evaluator, model settings, and runtime settings fixed.

Run

A run records one skill and model attempt. It contains outputs and evaluation results. It can contain bounded trace metadata when capture is enabled.

Evaluation

An evaluation applies a defined method to a run result. Use deterministic tests when the task permits them.

Evaluation result

An evaluation result records the outcome of a check. It can contain a score, pass state, failure category, and evidence links.

Skill version

A skill version contains reusable agent instructions. Its provenance must identify the evidence that caused the change.

Compare runs

  1. Keep the challenge definition unchanged.
  2. Keep the evaluator unchanged.
  3. Change one agent variable.
  4. Run the candidate.
  5. Compare scores, failures, artifacts, and available bounded trace metadata.
  6. Accept or reject the change.

A score change can hide a regression. Review the result and available execution metadata.

Provider roles

Provider keys

Provider keys let Versalist send supported model calls through a user-managed account. Manage these keys in Integrations.

Custom model endpoints

This capability is planned. The current product does not expose a general endpoint adapter.

Compute adapters

This capability is planned. A catalog entry does not mean that a runtime adapter exists.

  • Challenges explains environment selection and creation.
  • Skill bundles explains skill inspection and reuse.
  • CLI explains local run and comparison records.
Was this page helpful?