PAparsewise
Agents

Get an agent

Return a single agent by ID, including its dimensions and current extraction status. Returns 404 if the agent does not exist on this project.

get/projects/{project_id}/agents/{agent_id}/

Request

  • Base URL
    https://api.parsewise.ai/api/v1
  • Auth
    API key in header X-API-Key

Path parameters

agent_idstring uuid required
project_idstring uuid required

Response

idstring uuid required

Stable identifier for the agent (UUID).

project_idstring uuid required

Identifier of the project this agent belongs to.

template_idstring uuid nullable required

Identifier of the agent template this agent was created from, or null if the agent was created from scratch.

created_atstring date-time required

Timestamp when the agent was created.

extraction_status'Pending' | 'Processed' | 'No Result' required
requires_attentionboolean required

True if any of this agent's resolved values need attention (for example, unresolved inconsistencies between source documents).

improvement_tip_summarystring nullable required

Summary of the selected active improvement suggestion, or null when none is available.

supplying_agent_namesstring[] required
namestring

Human-readable name shown for the agent (e.g. "Contract value").

extraction_instructionsstring

Natural-language instructions describing what the agent should extract from each document.

value_type'string' | 'number' | 'list'
  • string - string
  • number - number
  • list - list
unitstring

Optional unit for numeric values (e.g. USD, %, kg). Used to normalise extracted values into a consistent unit and for display.

examplesstring

Free-form examples of expected values, used to steer the agent towards the right kind of answer.

inconsistency_instructionsstring

Custom instructions for inconsistency checking. If empty, default instructions will be used.

resolution_instructionsstring

Custom instructions for entity resolution. If empty, default instructions will be used.

enable_complex_calculations_in_resolutionboolean

Enable advanced computational analysis for complex resolution tasks involving calculations or data transformations.

web_search_instructionsstring

Web search task for each cell; required when enable_web_search is true.

enable_web_searchboolean

Enable web search to supplement extraction results with data from the web.

value_if_not_foundstring

Value shown when no extraction is found. If empty, 'n/a' is used.

inconsistency_summarystring nullable

AI-generated summary of why extracted values disagree across documents. Populated when inconsistencies are detected; null otherwise.

agent_type'extraction' | 'derived'
  • extraction - Extraction
  • derived - Derived
derived_promptstring

LLM prompt for derived agents. May contain @Name references to agents and documents.

is_evaluationboolean

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.