Build an Account Research Briefing Agent
Build an agent that turns company documents and dated announcements into a cited account brief. Separate verified facts from sales hypotheses and let the user inspect evidence before exporting the briefing.
What you are building
The core problem, expected build, and operating context for this challenge.
An account executive preparing for a first customer meeting.
Build an agent that turns company documents and dated announcements into a cited account brief. Separate verified facts from sales hypotheses and let the user inspect evidence before exporting the briefing.
Company profile
Dated company documents
User research questions
Retrieve relevant document sections.
Resolve dates and conflicting facts.
Draft the company summary and evidence-backed meeting questions.
Export a briefing with citations and explicitly labeled hypotheses.
A research workspace with a source viewer, editable briefing, citations, and document export.
Create a cited briefing about the planned expansion, identify Person A as current director, and label the automation opportunity as a hypothesis.
A working local application with the specified review interface.
Source code, dependency lockfile, and setup commands.
A recorded end-to-end demo using the supplied starter data.
Example outputs, action logs, and automated tests.
These fictional records are a small development fixture, not a production dataset. Implement the mock services described in the brief.
```json { "company": "Example Support Ltd", "as_of": "2026-09-19", "documents": [ { "id": "D1", "date": "2026-08-01", "text": "The company operates two support centers and plans a third." }, { "id": "D2", "date": "2026-09-01", "text": "Person B becomes operations director on October 1. Person A remains director until then." } ], "questions": [ "What is changing in operations?", "Who currently leads operations?" ] } ```
Use the fictional company bundle. Do not send outreach or infer personal characteristics. Choose an available model that supports your implementation. Record its identifier and version.
Review the complete application, not only the starter-case answers.
The expansion claim cites D1.
The director claim respects the effective date in D2.
The proposed sales opportunity is not stated as a customer commitment. Add one normal case, one incomplete-input case, and one failure-recovery case.
Participation guide
Use the fictional company bundle. Do not send outreach or infer personal characteristics.
How work is evaluated
Review workflow completion, interface usability, evidence quality, and safe failure handling. No agent execution has been verified.
A working local application with the specified review interface. Source code, dependency lockfile, and setup commands. A recorded end-to-end demo using the supplied starter data. Example outputs, action logs, and automated tests.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Retrieve relevant document sections.
Resolve dates and conflicting facts.
Draft the company summary and evidence-backed meeting questions.
Export a briefing with citations and explicitly labeled hypotheses.
Reference links and supporting material
Supplied fictional starter records: Company profile, Dated company documents, User research questions. The overview includes the complete JSON bundle. Implement local mock services and extend the sample coverage.
Challenge setup
Configuration summary for this challenge.
Challenge input
Input details are not configured.
LlamaIndex
Data framework for LLM applications
Evaluated output
No output checks are configured.
- No evaluation checks are configured.
- 1 public reference case
- 1 configured tool
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- LlamaIndex ยท Optional
Evaluation contract
- No evaluation checks are configured.
Reference cases
- 1 public reference case
Workflow tasks
No workflow tasks are configured.
Recipe freeze marker
No recipe freeze time is recorded.