Mental model 🧠
The Orchestration Multiplier
One engineer with 10 agents ships faster than a room full of devs debating variable names and burrito orders.
Quick Insights 🔎
🤯 25% of YC Startups have 95% AI-Generated Code
These are engineers who chose not to code. YC's CEO warns: "If you're not doing it, you might be left behind.
🚀 The rise of "context engineering”
LangChain calls it the most important skill you can develop.
🎯 The Anthropic Claude Code Playbook (50+ Use Case PDF)
Growth Marketing's ad automation scripts. Data Science's visualisation workflows. Legal's 1-hour app builds.
Inside the Every Claude Code demo
I watched an Every demo this week. Two engineers spawning features with voice instructions. Claude Code agents flying in all directions. Terminals stacked like Bloomberg screens.
And yeah my brain broke a little.

Dan Shipper, co-founder of Every, called it “compound engineering.” I haven’t stopped thinking about it since. This isn’t advanced vibe prompting. It’s also not some clever hacks. It’s a new abstraction layer and it’s shipping real code.
Every is one of the first truly AI-native teams, built from the ground up to work with agents. They publish a daily AI newsletter, ship multiple AI products, and run a million-dollar consulting arm. And their engineers? They write almost zero code.
Kieran Klaassen, a senior engineer at Every working on Cora, coined the term “compound engineering” and his Claude Code commands look like witchcraft.
I'm not an expert, but it feels like I watched the rise of Uber-engineers operating at 100x impact.
Just realised how much I still have to learn.
The fairytale 🧚
"AI will replace all engineers. We don't need developers anymore."
You’ve heard it on panels, in tweets, maybe even in your own team’s group chat.
But it’s missing the point entirely. Maybe even I said it one time. But now my thinking has changed.
The reality ✅
What’s actually happening looks a lot more interesting.
We're creating Uber-engineers. They’re getting multiplied by orchestration.
Think about it.
We went from Assembly to C to Python. Each abstraction made developers more powerful, not unemployed. Now we're going from typing code to conducting AI agent orchestras.
The Every team proves it daily. Their team is spinning up features in hours with six agents running at once.
2 engineers working like 15
Multiple Claude terminals open at once
Voice in, features out
Routine work? Fully delegated to agents
This is what compound engineering looks like in an AI native startup.
A new abstraction layer where the best engineers become conductors, not typists.
👉 Read my post on You Can't Prompt Your Way to Production
How Every pioneered compound engineering
The journey was messy.
They started with Cursor and Copilot.
Hit walls. Switched to Windsurf.
Hit more walls. Then Claude Code dropped.
Discovered: Claude Code could act as autonomous team members
Breakthrough: Running multiple instances like a distributed team
Their Compound Engineering Workflow in Action:
Morning: Kieran speaks a feature idea into Claude Code (voice, not typing)
Research Phase: Agent searches web for best practices, analyses codebase
Planning: Creates detailed GitHub issue with implementation steps
Execution: Multiple agents work in parallel, frontend, backend, tests, docs
Review: Human orchestrators check architecture, not syntax
What makes Claude Code different
Claude Code takes over and asks what's next.
Traditional AI Coding (Copilot, ChatGPT):
Lives in your IDE as suggestions
Limited context window
Can't execute commands or see results
You're still the coder
Claude Code:
Claude Code plugs Opus 4, the same model Anthropic’s engineers use directly into your terminal.
Understands your entire codebase
Directly edits files and runs commands
Can manage git, run tests, deploy code autonomously
You become the orchestrator
Claude Code wasn’t built for you. It was built for Anthropic’s engineers to ship faster, then handed to the rest of us like a cheat code.
👉 Here’s a great guide as to how Anthropic team use Claude code for everything from Growth Marketing to Data Science.
The compound engineering playbook
1. Build Prompts That Build Prompts
The Every team created a prompt that generates research documents, which become prompts for implementation.
"This is part of the compounding effect," Kieran explained. "Having an idea that has a lot of outcomes."
One voice command → Research document → GitHub issue → Multiple implementation agents
2. Fix Problems at the "Lowest Value Stage"
Don't let AI implement a flawed plan.
Review the architecture early when changes are cheap.
3. Parallel Agent Execution
The Every team runs multiple terminals. This is something I want to spend more time researching myself.
Terminal 1: Frontend agent building UI
Terminal 2: Backend agent creating APIs
Terminal 3: Test agent writing specs
Terminal 4: Docs agent updating guides
You: Orchestrating and reviewing
What orchestration actually means
This isn’t “prompt engineering” where you feed one big query and pray. This is agent orchestration, where one Claude agent can spawn other agents to handle subtasks.
You can literally split a project into frontend, backend, test, and docs and then have separate agents work on each in parallel, across different terminals. One agent writes UI. Another builds the API. A third writes test specs.
It’s like running a distributed team, except no one sleeps, complains, or stops to eat.
The 100x Engineer Stack
Here’s what the new breed of builders actually use:
Claude Code Max ($200/month)
Access to Opus 4 in your terminal. Your autonomous engineering team, on demand.Multiple terminals
Run agents in parallel, frontend, backend, testing, docs.Voice input (e.g. Whispr Flow)
Speak features into existence. No typing. Just talk.Pre-trained prompt libraries
Build prompts that build systems. This is compounding in action.GitHub automation
Claude files PRs, writes tests, merges code. No junior dev required.
How to install Claude Code:
Install Node.js 18+, then run:
npm install -g @anthropic-ai/claude-code
🎥 Must-watch: The Every demo. It’s the closest thing I’ve seen to real AI orchestration in action.
North star reality check for engineers and marketers
Kent Beck said:
90% of traditional programming is becoming commoditised.
The other 10%? It's now worth 1000x more.
The same shift is coming for everyone whose work used to mean “doing the thing”
Marketers who wrote campaigns by hand
Designers who built every screen from scratch
Analysts who manually pulled reports
PMs who wrangled timelines, not agents
What matters now?
System thinking over syntax
Orchestration over implementation
Taste and architecture over algorithms
Managing AI agents like a tech lead manages humans
The job now is conducting, not doing.
And small teams are starting to work at a fundamentally higher level because of it. Because they’re letting go of the busywork and leveling up to orchestration.
Orchestrators ship symphonies. Everyone else is still stuck tuning the violins.
Figure out which one you want to be.
👉 Read my post on Agentic Vibe Marketing Is Already Here
This week's intel 📚
Some interesting Substacks I read this week
the friend who never logs off by
OpenAI is replacing the entire premise of social networks by becoming the first infinitely responsive, 1:1 social graph that reflects you back to yourself.Successfully coding with AI in large enterprises by
To scale AI inside large engineering teams, you need centralised systems, clean documentation, and intentional workflows otherwise, AI becomes noise instead of leverage.
Got something I should read? Hit reply, I actually read every suggestion.
Until next week, keep building. No fairytales required.
Martin, Chief Ranter at Uncharted
P.S. this week’s track is Paranoid Android by Radiohead