docs: tighten See it work example — keep reframe hook, compress details

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-03-18 09:26:52 -07:00
parent ca8737ef78
commit 1a3dac4ab6
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
1 changed files with 20 additions and 56 deletions

View File

@ -61,79 +61,43 @@ Real files get committed to your repo (not a submodule), so `git clone` just wor
``` ```
You: I want to build a daily briefing app for my calendar. You: I want to build a daily briefing app for my calendar.
You: /office-hours You: /office-hours
Claude: What does the pain look like? Specific examples — the last Claude: [asks about the pain — specific examples, not hypotheticals]
time a conflict burned you, the daily friction of switching
accounts, what your assistant has to do manually today.
You: My assistant keeps messing things up... I have multiple Google You: My assistant keeps messing things up... multiple Google calendars,
calendars and events have stale info, wrong locations. Logistics stale info, wrong locations. The prep docs were AI slop...
AND prep for actual events. The prep docs were AI slop...
Claude: I'm going to push back on the framing, because I think you've Claude: I'm going to push back on the framing. You said "daily briefing
outgrown it. You said "daily briefing app for multi-Google- app." But what you actually described is a personal chief of
Calendar management." But what you actually described is a staff AI.
personal chief of staff AI — one that: [extracts 5 capabilities you didn't realize you were describing]
1. Watches your calendar across all accounts [challenges 4 premises — you agree, disagree, or adjust]
2. Generates real prep work — the intellectual work
3. Manages your CRM — who are you meeting, what's the history
4. Prioritizes your time — flags when prep needs to start early
5. Trades money for leverage — finds ways to delegate or automate
The calendar is the entry point, but the product is an AI that
makes a busy CEO a 2000x CEO the way Claude Code makes them a
2000x developer.
[presents 4 premises for validation → you agree/disagree]
[generates 3 implementation approaches with effort estimates] [generates 3 implementation approaches with effort estimates]
RECOMMENDATION: Ship the narrowest wedge tomorrow, learn from
APPROACH A: Daily Briefing First (Narrowest Wedge) real usage. The full vision is a 3-month project — start with
Effort: M (human: ~3 weeks / CC: ~2 days) the daily briefing that actually works.
Risk: Low — you use it tomorrow [writes design doc → feeds into downstream skills automatically]
APPROACH B: CRM-First (Relationship Graph)
Effort: L (human: ~6 weeks / CC: ~4 days)
APPROACH C: Event Intelligence Engine (Full Vision)
Effort: XL (human: ~3 months / CC: ~1.5 weeks)
RECOMMENDATION: Choose A because it ships tomorrow and you
learn from real usage. CRM data layer comes in the second
week naturally.
[writes design doc to ~/.gstack/projects/ — feeds into
/plan-ceo-review and /plan-eng-review automatically]
You: /plan-ceo-review You: /plan-ceo-review
[reads the design doc, runs 10-section mega review] [reads the design doc, challenges scope, runs 10-section review]
You: /plan-eng-review You: /plan-eng-review
Claude: ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌─────────┐ [ASCII diagrams for data flow, state machines, error paths]
│ Calendar│───▶│ Detect │───▶│ Generate │───▶│ Deliver │ [test matrix, failure modes, security concerns]
│ (sync) │ │ (stale) │ │ (prep) │ │ (email) │
└─────────┘ └──────────┘ └──────────┘ └─────────┘
[ASCII diagrams for every data flow, state machine, error path]
[14-case test matrix, 6 failure modes mapped, 3 security concerns]
You: Approve plan. Exit plan mode. You: Approve plan. Exit plan mode.
[Claude writes 2,400 lines across 11 files — models, services, [writes 2,400 lines across 11 files. ~8 minutes.]
controllers, views, migrations, and tests. ~8 minutes.]
You: /review You: /review
Claude: [AUTO-FIXED] Orphan S3 cleanup on failed upload [AUTO-FIXED] 2 issues. [ASK] Race condition → you approve fix.
[AUTO-FIXED] Missing index on listings.status
[ASK] Race condition on hero image selection → You: yes
3 issues — 2 auto-fixed, 1 fixed.
You: /qa https://staging.myapp.com You: /qa https://staging.myapp.com
Claude: [opens real browser, logs in, clicks through flows] [opens real browser, clicks through flows, finds and fixes a bug]
[finds bug: preview doesn't clear on second upload — fixes it]
Regression test generated.
You: /ship You: /ship
Claude: Tests: 42 → 51 (+9 new) Tests: 42 → 51 (+9 new). PR: github.com/you/app/pull/42
Coverage: 14/14 code paths (100%)
PR: github.com/you/app/pull/42
``` ```
You said "daily briefing app." The agent said "you're describing a personal chief of staff AI" — because it listened to your actual pain, not your feature request. Then it challenged your premises, generated three implementation approaches, recommended the narrowest wedge, wrote a design doc, and that doc fed into every downstream skill automatically. Eight commands. That is not a copilot. That is a team. You said "daily briefing app." The agent said "you're building a chief of staff AI" — because it listened to your pain, not your feature request. Then it challenged your premises, generated three approaches, recommended the narrowest wedge, and wrote a design doc that fed into every downstream skill. Eight commands. That is not a copilot. That is a team.
## The team ## The team