How to build a Team OS in Claude Code with Hannah Stulberg, PM @ DoorDash

136 snips

Apr 7, 2026

Hannah Stulberg, a DoorDash product manager and former Google APM who created the 'Claude Code for Everything' series, shares her Team OS approach. She explains a shared repo that scales PM context, the lean root CLAUDE.md and nested indexes, and how to structure docs, agents, and metrics so everyone self-servers. Practical tips on plan mode, verification phases, and saving prompts round out the conversation.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ADVICE

Standardize Summaries With Shared Skills

Standardize outputs with skills/commands: create shared customer call templates and skills so all summaries follow the same structure for easy cross-customer synthesis.
Designers, analysts, and account leads fill the same fields so Claude can reliably aggregate hundreds of summaries.

ADVICE

Separate Metrics Queries And Schemas

Split analytics into metrics, queries, and schemas by product area so Claude loads only the needed tier.
Store metric definitions, SQL queries, and table schemas separately and link them in the product folder to empower PMs and engineers to self-serve analysis.

ADVICE

Require Repo Updates Before Shipping

Gate launches on repo updates: require metrics, queries, schemas, and playbooks to be checked into the repo before shipping a feature.
This enshrines shared context so engineers, on-call, and PMs can validate features without a data scientist.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Today’s episode

The way PM teams are trending, one PM is going to support 20 people.

Not just engineers. Designers. Analysts. Strategy partners. GTM. Sales. Support.

You cannot answer everyone’s questions about everything. You cannot be in every Slack thread. You cannot be the bottleneck for context that already exists somewhere in a Google Doc no one can find.

But you can give them a high-context, well-organized repo.

Hannah Stulberg is a PM at DoorDash and a former Google PM. She has spent over 1,500 hours in Claude Code.

She wrote the viral Claude Code for Everything series. Her setup is not a personal productivity system. She has structured her entire team’s context into a shared repo that everyone queries.

Her strategy partner - completely non-technical - puts up pull requests every day. Her engineers query metric definitions without asking the analyst. Her designers pull product context without waiting on a PM.

If you are building a team that runs on AI, this is the episode to watch.

----

Check out the conversation on Apple, Spotify, and YouTube.

Brought to you by:

* Bolt: Ship AI-powered products 10x faster

* Jira Product Discovery: Plan with purpose, ship with confidence

* Kameleoon: Leading AI experimentation platform

* Amplitude: The market-leader in product analytics

* Product Faculty: Get $550 off their #1 AI PM Certification with my link

----

If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.

I’m putting on a free webinar on Behavioral and AI PM interviews. Join me.

----

1. Build a Team OS, not a personal OS - A shared repo where every function checks in work. Engineers, designers, and analysts self-serve without asking the PM.

2. Root CLAUDE.md is everything - Doc index, team roster with Slack IDs, channel map. Keep under one page or you burn context every session.

3. Nested indexes save 97% of context - Every folder gets a navigation CLAUDE.md. A customer query used only 3% of the context window.

4. Three token tiers - Always-loaded root (~500 tokens), folder indexes on navigation (200-500), content files on demand (1,000-10,000+).

5. Split analytics by product area - Metrics, queries, schemas separated. Progressive loading prevents waste.

6. Gate launches on repo updates - Feature not shipped until metrics, queries, schemas, and playbooks are checked in.

7. Verified playbooks kill hallucinations - Analyst-audited methodology. Claude follows verified steps instead of inventing its own.

8. Plan mode makes 10x docs - Shift+Tab twice. Five phases: load context, ask questions, build plan, push thinking, review agents.

9. Split long docs across parallel agents - Each writes to a temp file. Orchestrating agent compiles. Prevents context overflow.

10. The flywheel compounds daily - Automate one task, free time, improve the repo. After 1,500 hours still iterating every day.

----

Where to find Hannah Stulberg

* LinkedIn

* In the Weeds Substack