From 1a3dac4ab67c426a60b0292dcbef764978869f84 Mon Sep 17 00:00:00 2001 From: Garry Tan Date: Wed, 18 Mar 2026 09:26:52 -0700 Subject: [PATCH] =?UTF-8?q?docs:=20tighten=20See=20it=20work=20example=20?= =?UTF-8?q?=E2=80=94=20keep=20reframe=20hook,=20compress=20details?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-Authored-By: Claude Opus 4.6 (1M context) --- README.md | 76 +++++++++++++++---------------------------------------- 1 file changed, 20 insertions(+), 56 deletions(-) diff --git a/README.md b/README.md index b1d0eb0f..45bf1f32 100644 --- a/README.md +++ b/README.md @@ -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: /office-hours -Claude: What does the pain look like? Specific examples — the last - time a conflict burned you, the daily friction of switching - accounts, what your assistant has to do manually today. +Claude: [asks about the pain — specific examples, not hypotheticals] -You: My assistant keeps messing things up... I have multiple Google - calendars and events have stale info, wrong locations. Logistics - AND prep for actual events. The prep docs were AI slop... +You: My assistant keeps messing things up... multiple Google calendars, + stale info, wrong locations. The prep docs were AI slop... -Claude: I'm going to push back on the framing, because I think you've - outgrown it. You said "daily briefing app for multi-Google- - Calendar management." But what you actually described is a - personal chief of staff AI — one that: - 1. Watches your calendar across all accounts - 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] +Claude: I'm going to push back on the framing. You said "daily briefing + app." But what you actually described is a personal chief of + staff AI. + [extracts 5 capabilities you didn't realize you were describing] + [challenges 4 premises — you agree, disagree, or adjust] [generates 3 implementation approaches with effort estimates] - - APPROACH A: Daily Briefing First (Narrowest Wedge) - Effort: M (human: ~3 weeks / CC: ~2 days) - Risk: Low — you use it tomorrow - 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] + RECOMMENDATION: Ship the narrowest wedge tomorrow, learn from + real usage. The full vision is a 3-month project — start with + the daily briefing that actually works. + [writes design doc → feeds into downstream skills automatically] 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 -Claude: ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌─────────┐ - │ Calendar│───▶│ Detect │───▶│ Generate │───▶│ Deliver │ - │ (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] + [ASCII diagrams for data flow, state machines, error paths] + [test matrix, failure modes, security concerns] You: Approve plan. Exit plan mode. - [Claude writes 2,400 lines across 11 files — models, services, - controllers, views, migrations, and tests. ~8 minutes.] + [writes 2,400 lines across 11 files. ~8 minutes.] You: /review -Claude: [AUTO-FIXED] Orphan S3 cleanup on failed upload - [AUTO-FIXED] Missing index on listings.status - [ASK] Race condition on hero image selection → You: yes - 3 issues — 2 auto-fixed, 1 fixed. + [AUTO-FIXED] 2 issues. [ASK] Race condition → you approve fix. You: /qa https://staging.myapp.com -Claude: [opens real browser, logs in, clicks through flows] - [finds bug: preview doesn't clear on second upload — fixes it] - Regression test generated. + [opens real browser, clicks through flows, finds and fixes a bug] You: /ship -Claude: Tests: 42 → 51 (+9 new) - Coverage: 14/14 code paths (100%) - PR: github.com/you/app/pull/42 + Tests: 42 → 51 (+9 new). 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