Revise an agent prompt from a natural-language change
Take the prompt as it stands in the editor plus a change the user described in their own words, and return the full revised prompt with a one-sentence summary of what changed. The prompt is not stored — the caller decides whether to keep the revision.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
A natural-language change to make to an existing agent prompt.
A saved agent's prompt: literal text with references between the runs.
The same convention every other stored prompt in the product uses
(EnrichmentPromptTemplate for columns, template segments for
sequences): identity-keyed segments, so renaming what a reference points
at never rewrites the prompt. Structurally parallel to the enrichment
template rather than importing it — an agent prompt references INPUTS,
an enrichment prompt references COLUMNS, and the import hierarchy keeps
the two domains apart.
1 - 400020Revise in the light of what people said was wrong with this agent's real results. The complaints are read server-side from stored feedback, so the client cannot put words in their mouths.
Response
Successful Response
The revised prompt and a one-line account of what changed.
The declared inputs after the edit — a revision may mint one.
A saved agent's prompt: literal text with references between the runs.
The same convention every other stored prompt in the product uses
(EnrichmentPromptTemplate for columns, template segments for
sequences): identity-keyed segments, so renaming what a reference points
at never rewrites the prompt. Structurally parallel to the enrichment
template rather than importing it — an agent prompt references INPUTS,
an enrichment prompt references COLUMNS, and the import hierarchy keeps
the two domains apart.