Case: share a research method with a team

We will create a company-research assistant for a frontline team. Start a project and record its boundaries: research drafts with sources, while people retain responsibility for account-opening decisions.

Try it · Create the project, save its brief, then start a DeepAgents admin conversation.

Upload anonymized notes. Ask the assistant to separate entity confirmation, source checks, and comparable-sample rules. Keep scripts separate with documented inputs and outputs so the method can be maintained.

Try it · Inspect the demonstration rules, workflow steps, and script notes.

Create the research Service with a connection, saved prompt version, and allowed documents. Enable only required scripts and web access. Save a draft before testing it as a user.

Try it · Configure the research Service, leave Publish immediately unselected, and save a draft.

In the project conversation, open Test a Service and select the draft. Replies now use its configuration. Administrator contact is simulated, but other authorized tools may still perform actions.

Try it · Select the demonstration draft, start the test, and enter a fictional company.

Open Tracing to inspect recorded file access and tool actions. It helps check evidence for verification steps, but a missing record does not prove that no action occurred.

Try it · Switch to Tracing, select the demonstration turn, and inspect Execution order.

Exit testing and return to the DeepAgents admin conversation. Review the missed verification and update the shared rule file: even a name-only request must start with background checks.

Try it · Exit test mode, request the rule change, and inspect the file edit.

Restart testing with a fresh question. Verify the entity, year, and standalone reporting scope before research. If Service configuration changes, exit and reopen test mode.

Try it · Restart the demonstration test and inspect the clarification sequence.

After reviewing the test, return to My services, verify the prompt and access scope, and publish. Share the Service link so colleagues can begin their research tasks.

Try it · Review the demonstration configuration and show its published access entry.

A colleague submits the synthetic case. The assistant confirms the entity, then shows sources, comparable-sample scope, and unresolved facts. Its output is a research draft for human review.

Try it · Enter the synthetic case in the Service conversation and inspect the report summary.

The colleague points out that Sample A uses consolidated group accounts. The assistant explains the mismatch, excludes that sample, and revises this report while retaining unresolved items.

Try it · Submit the scope correction and inspect the exclusion and revision notes.

The colleague suggests making entity and reporting-scope checks mandatory. With their confirmation, the Service submits feedback and context. This illustrates the published flow, distinct from simulated contact during testing.

Try it · Confirm the demonstration suggestion and inspect its Inbox entry.

Enable Service records so the admin can review feedback. A person reviews the change, then saves shared rules through DeepAgents or the file editor and retests. Feedback does not rewrite rules automatically.

Try it · Show Service records authorization, then return to the project to revise rules based on review.