Open in Markdown reader

Lab 3 — Operations Intelligence Sprint

Time: 35 minutes
Team: groups of three or four

Mac / Linux / Windows

Submission: prepare the deliverables below using the public-safe packet and review workflow. One PR per lab; private review is equally available. Never publish grades or personal information.

Use browser-based Sheets/Docs or the supplied files on any OS; desktop Office is not required. Keep the original CSV unchanged and check UTF-8, separators, date/number locale and leading-zero IDs when importing into Sheets, Excel or LibreOffice. Browser GitHub/Discord or their exports avoid desktop-client requirements.

See the platform guide and included local lab track.

Scenario

Leadership wants to know which synthetic inquiries should receive an event-order update this week, what is blocking follow-up, and which product issues need engineering attention.

Mission

Turn five supplied source files into a reviewable one-page recommendation without altering raw data or inventing decisions. This is an introductory export-based workflow, not a test of live connectors.

Sources

• inquiries.csv: duplicates and inconsistent fields
• budget.csv: spreadsheet export with a planted formula error; formula_text records the formula to inspect, and reported_total records its reported result
• discord-thread.md: fabricated operations messages
• github-issues.json: synthetic issue export
• source-register.md: three conflicting classroom source excerpts, not live web pages

Recompute budget totals independently; do not assume an imported CSV recalculates reported_total. Preserve the original exports. Optional connected-app practice requires an isolated instructor-approved workspace and is assessed separately from this core sprint.

Roles

• Data steward: preserve raw data, document transformations, verify formulas.
• Research/doc lead: identify authoritative sources and draft the memo.
• Workflow lead: extract decisions, actions, owners, and unresolved questions from chat/issues.
• Verifier: challenges every claim and checks the final recommendation.

Deliverables

1. Preserved raw file and cleaned working view.
2. A short source/citation log.
3. A one-page decision memo: priority segments, blocking issues, recommended actions, assumptions.
4. An automation boundary: what AI can draft/triage and what still requires review/approval.

Success rubric

The memo must make it easy for a manager to trace every number and decision to a source. “The AI said” is never a source.

Stretch

Sketch a safe recurring workflow: input location, validation, human approval, output destination, audit record, and failure route.