Lab 3 — Operations Intelligence Sprint
START HERE · YOUR LAB FILES
Open these resources
Each card opens the supplied file. Keep these alongside the lab; open the same paths in your downloaded course folder when using your AI.
- 1inquiries.csvSupplied evidence · read this source
fixtures/inquiries.csv - 2source-register.mdSupplied evidence · read this source
fixtures/source-register.md
Underlined filenames throughout the steps are clickable. A file you create yourself links to saving instructions, not a nonexistent download.
On this page
SESSION 03 / 35-minute practice lab / within a 2-hour session
Turn messy business exports into a recommendation someone else can audit.
A preserved source, cleaned view, source log, decision memo and automation boundary.
Before you start · recall, then check
What made a code reference trustworthy last session? How would you apply that same rule to a spreadsheet number or chat summary?
Use about two minutes of the existing arrival/discussion time. Try in your own words, then check the source with a partner or coach. This is ungraded practice, not a new submission.
Need a hand? A supported route
Trace one inquiry through the raw file, working view and memo before processing the rest. Split roles, but have a different person check each total. Export-based practice is enough; live connectors are optional.
Time: 35 minutes
Team: groups of three or four
Quick start
First action: Preserve the five supplied sources before cleaning or summarizing.
Finish with: Raw/working data, source log, decision memo and an automation boundary.
Step-by-step help for Session 03 — smaller steps, checkpoints and troubleshooting. Saving and asking for help.
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_textrecords the formula to inspect, andreported_totalrecords 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
- Preserved raw file and cleaned working view.
- A short source/citation log.
- A one-page decision memo: priority segments, blocking issues, recommended actions, assumptions.
- 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.
Product Studio homework — Make a business decision
Create a small synthetic dataset, checked CSV/spreadsheet analysis, source log and one-page decision memo for your product. Draft a concise mock team update; no live Google/Discord posting required.
Budget two to three hours, including evidence and review preparation; ask for coaching or scope adjustment if blocked. Record progress using the milestone template in your own product repository, not the practice packet. See the complete project roadmap, GitHub workflow and small-model guide. The practice lab above remains separate from your individual product.
Leave with a next step
Use the existing closing/debrief time: explain one claim you verified, one limit and your next action. Reuse the lab’s artifacts; this adds no separate worksheet or graded test.
Practice evidence uses the lab submission workflow. Product Studio work belongs in your own product repository. These are different destinations.
Product Studio roadmap · Sharing and review guide
Opening the next session does not mark this one complete. Progress tracking is optional and does not award a credential.