evaluations

Optimize Skill Endpoint

Optimize a skill using evaluation data. Fetches model responses and human corrections for the given skill, runs LLM-based optimization to improve the prompt and JSON schema, and saves a new skill version with the same name.

post/v1/evaluations/optimize

Request

  • Base URL: https://api.vlm.run (the document declares no server; this is the origin it was published from)
  • URL: https://api.vlm.run/v1/evaluations/optimize
  • Auth: HTTP bearer

Request body

skill_idstring required

Skill ID (UUID) to optimize

skill_idsstring[] nullable

Additional skill IDs whose executions should be included in the evaluation data.

data_fromstring nullable

ISO date filter start

data_tostring nullable

ISO date filter end

infer_correctionsboolean

Use LLM to produce corrected JSON from notes-only feedback.

n_samplesinteger

Number of response/correction pairs to randomly sample for the LLM optimization.

Response

Successful Response

skill_idstring required

ID of the newly created optimized skill

namestring required

Skill name (same as the original)

versionstring required

Auto-generated version for the new skill

original_skill_idstring required

ID of the original skill that was optimized

total_pairsinteger required

Number of response/correction pairs available

sampled_pairsinteger required

Number of pairs actually sent to the LLM

created_atstring date-time required

Creation timestamp of the new skill

Changes

No recorded changes to this operation across all 2 revisions of this API.