Update an agent
Replace the agent's configuration (instructions, dimensions, etc.). If the change invalidates already-extracted results (e.g. editing the prompt), the affected extraction results are cleared automatically. Returns the updated agent.
Request
- Base URLhttps://api.parsewise.ai/api/v1
- AuthAPI key in header X-API-Key
Path parameters
Request body
Human-readable name shown for the agent (e.g. "Contract value").
Natural-language instructions describing what the agent should extract from each document.
- string - string
- number - number
- list - list
Optional unit for numeric values (e.g. USD, %, kg). Used to normalise extracted values into a consistent unit and for display.
Free-form examples of expected values, used to steer the agent towards the right kind of answer.
Custom instructions for inconsistency checking. If empty, default instructions will be used.
Custom instructions for entity resolution. If empty, default instructions will be used.
Enable advanced computational analysis for complex resolution tasks involving calculations or data transformations.
Enable web search to supplement extraction results with data from the web.
Web search task for each cell; required when enable_web_search is true.
Value shown when no extraction is found. If empty, 'n/a' is used.
- extraction - extraction
- derived - derived
LLM prompt for derived agents. May contain @Name references to agents and documents.
Marks a derived agent as an evaluation agent: its prompt is treated as an evaluation criterion scored over the referenced agents, its value type is always number, and it is listed on the evaluation page.
Response
Stable identifier for the agent (UUID).
Identifier of the project this agent belongs to.
Identifier of the agent template this agent was created from, or null if the agent was created from scratch.
Timestamp when the agent was created.
True if any of this agent's resolved values need attention (for example, unresolved inconsistencies between source documents).
Summary of the selected active improvement suggestion, or null when none is available.
Human-readable name shown for the agent (e.g. "Contract value").
Natural-language instructions describing what the agent should extract from each document.
- string - string
- number - number
- list - list
Optional unit for numeric values (e.g. USD, %, kg). Used to normalise extracted values into a consistent unit and for display.
Free-form examples of expected values, used to steer the agent towards the right kind of answer.
Custom instructions for inconsistency checking. If empty, default instructions will be used.
Custom instructions for entity resolution. If empty, default instructions will be used.
Enable advanced computational analysis for complex resolution tasks involving calculations or data transformations.
Web search task for each cell; required when enable_web_search is true.
Enable web search to supplement extraction results with data from the web.
Value shown when no extraction is found. If empty, 'n/a' is used.
AI-generated summary of why extracted values disagree across documents. Populated when inconsistencies are detected; null otherwise.
- extraction - Extraction
- derived - Derived
LLM prompt for derived agents. May contain @Name references to agents and documents.
Marks a derived agent as an evaluation agent: its prompt is treated as an evaluation criterion scored over the referenced agents, its value type is always number, and it is listed on the evaluation page.
Changes
No recorded changes to this operation across all 1 revision of this API.