Build the Review Report and Grounded Drafts

What you will complete

A styled report with same-run HTML, Markdown, JSON, and CSV evidence plus draft-only messages.

Make the operating decision

The report header shows run ID, collection time, exact source scope, caps, status, and cost when returned. Reconciliation identifies requested, accepted, returned, normalized, duplicates, exclusions, unknowns, and errors. Empty, partial, failed, and zero-match runs require different labels.

Each review card includes identity confidence, selected signal, event and first-seen dates, evidence excerpt, direct source links, fit rationale, timing hypothesis, alternative explanation, missing information, status, and review state. If no verified business contact or source-thread route exists, state contact route not found.

Drafts mention only the observed event and the learner's approved offer, then ask a low-pressure question. They never invent prior contact, shared connections, customer results, budget, deadlines, or authority. HTML, JSON, CSV, and Markdown derive from one normalized representation and share IDs and states. Escape untrusted text and neutralize spreadsheet formulas.

Worked fictional example: Harborline Safety Training

Northstar's fictional draft notes the dated Hamilton opening and asks whether external onboarding support is still being considered. It does not say the company has a training problem. No contact route is found, so the report provides a research action rather than a guessed email.

Harborline Safety Training, Northstar Distribution, Dockside Logistics, Westbank Storage, all events, excerpts, people, and URLs are fictional fixtures. They do not prove a live source, lead, contact route, or business outcome.

Complete workbook section 7

Use the evidence available for your own bounded job. Write unknown when the evidence is missing, and record the person or action that can resolve it.

1. Build the run and reconciliation header.
2. Render evidence cards and distinct failure states.
3. Create one grounded draft and one research question.
4. Compare IDs, states, and counts across all exports.

Open the course workbook PDF or read the workbook details.

Critical gate before continuing

• Every personalized statement traces to evidence or the business brief.
• No guessed contact appears.
• Exports reconcile with the report.
• No send or publish control exists.

If a gate fails, repair the current section, narrow the scope, leave the route manual, or record a blocked or stop decision. Continuing is not the only successful learner action.

Common failure modes

• Expanding beyond a styled report with same-run html, markdown, json, and csv evidence plus draft-only messages. before the current artifact can be graded.
• Turning a missing value, unavailable source, or blocked integration into a confident conclusion.
• Treating a prompt instruction as proof that the effective tool or permission boundary works.
• Marking a manual, simulated, or untested route as live.

Check your application