docs: move demo up, make it dramatically more impressive

Show the actual architecture diagram, auto-fixed issues, 100% coverage,
regression test generation. Punch line: "That is not a copilot. That is
a team."

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-17 13:59:10 -07:00
parent 98cfed3001
commit 4522cd2927
+58 -39
View File
@@ -24,6 +24,64 @@ Fork it. Improve it. Make it yours. Don't player hate, appreciate.
---
## See it work
```
You: I want to add photo upload for sellers.
/plan-ceo-review
Claude: "Photo upload" is not the feature. The real job is helping
sellers create listings that actually sell.
What if we auto-identify the product from the photo, pull
specs and pricing comps from the web, draft the title and
description, and suggest the best hero image?
That's a 10-star listing experience. "Upload a photo" is
a 3-star one. Which are we building?
/plan-eng-review
Claude: ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌─────────┐
│ Upload │───▶│ Classify │───▶│ Enrich │───▶│ Draft │
│ (sync) │ │ (async) │ │ (async) │ │ (async) │
└─────────┘ └──────────┘ └──────────┘ └─────────┘
│ │ │ │
▼ ▼ ▼ ▼
S3 + DB Vision API WebSearch + LLM gen +
persist + fallback price APIs user edit
Failure modes: 6 mapped. Test matrix: 14 cases.
Missing: what if classify returns low-confidence?
[implement the plan]
/review
Claude: [AUTO-FIXED] Orphan S3 cleanup on failed upload
[AUTO-FIXED] Missing index on listings.status
[ASK] Race condition: two tabs can overwrite hero image
selection. Add SELECT FOR UPDATE? → You: yes
Pre-Landing Review: 3 issues — 2 auto-fixed, 1 fixed.
/ship
Claude: Tests: 42 → 51 (+9 new)
Coverage: 14/14 code paths tested (100%)
PR: github.com/you/app/pull/42
/qa https://staging.myapp.com
Claude: Upload → classify → enrich → draft: end to end ✓
Mobile upload: ✓ | Slow connection: ✓ | Bad image: ✓
Regression test generated: test/qa-regression-001.test.ts
```
One feature. Six commands. CEO taste → architecture → review → ship → QA. The agent found a race condition I would have missed, auto-fixed two issues I didn't even think about, wrote 9 tests, and generated a regression test from QA. That is not a copilot. That is a team.
---
## The team
| Skill | Your specialist | What they do |
@@ -60,45 +118,6 @@ Fork it. Improve it. Make it yours. Don't player hate, appreciate.
---
## Demo
```
You: I want to add seller photo upload to the listing app.
You: /plan-ceo-review
Claude: "Photo upload" is not the feature. The real job is helping sellers
create listings that actually sell. Here's the 10-star version:
auto-identify the product, pull specs and comps from the web,
draft the title and description, suggest the best hero image...
You: /plan-eng-review
Claude: [Architecture diagram, state machine for upload → classify → enrich
→ draft pipeline, async job boundaries, failure modes, test matrix]
You: [implement the plan]
You: /review
Claude: Race condition: two tabs can overwrite cover-photo selection.
Trust boundary: web data into draft generation = prompt injection.
[AUTO-FIXED] 2 issues. 1 needs your input.
You: /ship
Claude: Tests: 42 → 47 (+5 new). PR: github.com/you/app/pull/42
You: /qa https://staging.myapp.com
Claude: All 3 affected routes working. Upload + enrichment flow passes
end to end. Regression test generated.
```
Six commands. Plan → architecture → review → ship → QA. Done.
---
## My journey and why this exists
I have a full time busy job as CEO of Y Combinator. And I am coding a lot. Like, a lot a lot. I was stranded in Austin due to weather and I was coding. My mom was in the hospital and not too lucid for most of it, and I was coding by her bedside too. She's ok now.