> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.middesk.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.middesk.com/_mcp/server. # Review work > Review agent findings, resulting actions, and changes to the Business report After an agent takes action on a Business report, Middesk stores a record of its findings and how each finding was applied or not applied to the report. This record is represented as an `agent_application` in the API. ## Understanding the results Each `agent_application` answers three questions: * **What did the agent find?** `resolutions` contains one entry for each reviewed finding. `original_artifact` preserves what the agent proposed and any supporting sources, while `agent_display_name` identifies the agent that produced it. * **What was done with those findings?** `outcome` records how the finding was handled. `resolved_artifact`, `correction`, and `exclusion` show any adjustments. `actions` lists the actions taken, and `execution_result` shows whether they were applied, partially applied, left the report unchanged, or failed. * **How did the Business report change?** `changes` contains the effects recorded for completed actions, and `report_transitions` summarizes relevant before-and-after report values. At the application level, `review_task_transitions` records corresponding changes to the Business's review tasks. ## Checking screenshot capture status When web evidence screenshot capture is enabled for your agents, the `screenshot_captures` object tells you whether captures have completed for an agent run. | Value | Meaning | Action | | :--------------------------------------------- | :----------------------------------------------------------------------------------------------- | :------------------------------------------------ | | `null` | The run has no screenshot captures. | Continue without waiting for captures. | | `{ "settled_at": null }` | At least one screenshot capture is pending. | Wait for capture to finish. | | `{ "settled_at": "2026-09-09T10:00:00.123Z" }` | All screenshot capture attempts are complete. Failed and unavailable captures count as complete. | Continue with your screenshot-dependent workflow. | Only one state indicates pending work, so check for that state rather than for a timestamp: **`Check for pending screenshot captures`** ```javascript title="Check for pending screenshot captures" const captures = application.screenshot_captures; const screenshotCapturePending = captures !== null && captures.settled_at === null; ``` `screenshot_captures` reflects the status for the result's `run_id`. If another agent run applies findings, its new result may show pending captures even when earlier results are settled. When a screenshot is available, its source includes a `screenshot_id` that you can use to [retrieve the Document](/api-reference/documents/get-a-document). If your workflow requires available screenshots in the [Business PDF](/api-reference/business-verification/businesses/retrieve-a-business-pdf), retrieve the latest PDF when no captures are pending. ## Receiving updates through webhooks Middesk sends a `business.updated` event after an agent finishes acting on its findings and its `agent_application` can be reviewed. If screenshots are still pending, Middesk sends another `business.updated` event after all capture operations finish. Default webhook payloads don't include `agent_applications`. To include these records and their screenshot status, add `agent_applications` and the nested `screenshot_captures` field to a custom event schema. Use the [webhook event schema API](/api-reference/webhooks/create-webhook-event-schema) to configure these fields, then choose which [webhook events](/work-with-agents/webhooks) to subscribe to and when they are sent. ## Agent application fields Select only the fields your integration uses. The following selection shows every available field: **`Agent application fields`** ```graphql title="Agent application fields" { id agent_applications { object id run_id thread_id created_at finalized_at applied_by { id name email } screenshot_captures { settled_at } review_task_transitions { key before after } resolutions { object id artifact_id agent agent_display_name original_artifact resolved_artifact report_record { object id } artifact_field outcome decision_mode proposed_value resolved_value correction { id original_value resolved_value reason created_at } exclusion { id created_at } selected_sources execution_result actions { id type status completed_at } changes { kind report_record { object id namespace } operation before after } report_transitions { key label kind before after before_intent after_intent } } } } ``` Each result contains these top-level fields: | Field | Type | Description | | :------------------------ | :--------------- | :------------------------------------------------------------------------------------------------ | | `object` | string | Always `agent_application`. | | `id` | string | Unique identifier for the result. | | `run_id` | string | Identifier for the run that produced the findings. | | `thread_id` | string or `null` | Identifier for the thread containing the run. | | `created_at` | string | ISO 8601 timestamp when Middesk created the result. | | `finalized_at` | string | ISO 8601 timestamp when Middesk finalized the result. | | `applied_by` | object or `null` | The `id`, `name`, and `email` of the person who applied the findings. | | `screenshot_captures` | object or `null` | Web evidence screenshot capture status for the run. | | `review_task_transitions` | array | Review task changes, including the task `key` and JSON `before` and `after` values. | | `resolutions` | array | Agent findings and the decisions, adjustments, actions, and Business changes resulting from them. | ## Automating how findings are applied Each item in `resolutions` includes `decision_mode`, which shows whether its outcome was chosen manually or automatically. Learn about configuring your [interrupt policy](/work-with-agents/interrupt-policy) to control which findings apply automatically and which pause for human review. > **Get a demo** > > Contact your account manager or [contact sales](https://www.middesk.com/contact-sales) to inquire about access.