CS 319 · Meeting 10 of 10 · capstone
Everything from nine meetings, applied to one real organization — and audited like you mean it.
Agenda · 100 min
Case study · part 10 of 10 · the arc
| Metric | Week 0 | Week 12 |
|---|---|---|
| Time buckets (team avg) | 61% type · 24% review · 8% decide | 18% type · 31% review · 38% decide |
| Loops in production | 0 | 9 enabled · 3 paused/retired |
| Dependency Fridays (Rasa) | 90 min manual | 15 min review-only |
| Specs written per feature | 0 (tickets only) | 6 documents, council-produced |
| Escalations that changed outcomes | n/a | 1 gate + 1 useful checkpoint / day |
| The line that matters | The team didn't shrink. The team's decisions per hour tripled. | |
Their three paused loops are on the slide on purpose. A fleet that never retires anything isn't being audited.
Live exercise · 15 minutes
| Loop | Runs | Last landed | Queue @ gate | Dashboard |
|---|---|---|---|---|
| L1 triage | 220 | 3 days ago | 2 drafts | green |
| L2 changelog | 140 | 21 days ago | 45 drafts | green |
| L3 refund-docs | 61 | yesterday | 14 waiting | green |
| L4 seo | 96 | 6 days ago | prs_unmerged=7 | green |
| L5 design | 38 | mixed | 7 hand-rejected | green |
Assign each loop a verdict. For L2: the CLI bug skipped every multi-line draft and logged ok 140 times — which observability rule (M7) would have caught it in one day instead of three weeks?
The final exam is a poster on the wall
1 Landed, not produced — merged not opened, posted not drafted, paid not shipped
2 Skip ≠ success — different log lines, or dead loops stay green
3 Kill rule — two weeks unlanded → kill / defer / ship. No prompt tuning
4 Gate discipline — queue jam: kill/defer/ship, never another producer
5 Verifier at every handoff — boundaries are API boundaries
6 One shared artifact layer — or the org forgets between turns
7 Every agent has an owner + a sandbox — a role label is not a sandbox
The deliverable · teams of 2 · four weeks
Pick a real organization — student club, family business, your workplace, or Kirana extended. Produce:
Presentation · 7 minutes + 5 Q
25 Spec rigor — binary criteria, refusal conditions, real boundaries
25 Verifier rigor — layer order, maker-checker separation, calibration
20 Honesty of the audit — dead things named dead, theater named theater
15 Graph judgment — gut check applied honestly (a "keep it a loop" verdict can score full marks)
15 Communication — the one-breath explanation test, live
Bonus 5: a documented kill. Retiring a loop is a rite of passage, not a failure.
Field trip · the industry is building this, now
github.com/yc-software/qm — 14.3k stars, MIT. A "multiplayer agent harness for work": every employee gets a scoped agent (memory, files, permissions, sandbox); teams share rooms; admins set one security posture (strict → auto → dangerous; scopes only tighten).
Map it to this course: crons/watches/webhooks = ch 7 triggers · skills shared by grant = ch 16 SOP graduation with governance · per-scope sandbox = tool allowlists made real · Postgres memory = hot/warm/cold state.
The detail worth a whole lecture: its AGENTS.md orders coding agents to "never self-review in the authoring context — dispatch an independent reviewer that did not watch you write the change." Maker-checker (M5) as merge policy, reviewer node (M9) in the repo's own constitution.
What it doesn't solve: your verifiers, your landed-outcome accounting. The harness is the substrate; this course was the rest.
Where it goes
The stack keeps climbing
prompt → context → harness → loop → graph. The next rung will also be a naming event. Use the word-versus-shift filter (M9) on it.
Edges between companies
A2A: agents delegating across vendors and orgs — the Linux-Foundation-governed protocol. Cross-system edges are coming to your fleet.
The question that stays
"What is the work you will keep doing when most of the rest is automated?" — ch 18's final question. Answer it with evidence, and revisit yearly.
The course in one breath
Agents write the code; the foreman writes the spec, the verifier, and the loop — and audits what lands.
CS 319 · end
The loop is yours. When the work forces a graph, you will know.
Textbook
pangmandorin.kamil.web.id
EN · ID, 19 chapters, free
Keep sharp
Appendix A (prompt library) · B (reference architectures) · C (glossary)
Your final artifact
Not a grade. A fleet you audited, a napkin you can defend, and a runbook a stranger can follow at 3am.
Decks are forkable static HTML — teach this course yourself. That's rather the point.