Original: Dan Shipper (Every) · 30/01/2026
Summary
What happens to software engineering when 100 percent of your code is written by agents? While we’re on our Think Week offsite this week, we’re resurfacing Cora general manager Kieran Klaassen**’s work on the theme of compound engineering. In this final piece, Kieran teams up with ***[Dan Shipper](https://every.tKey Insights
“What happens to software engineering when 100 percent of your code is written by agents?” — Introducing the concept of compound engineering where AI agents write all the code.
“In compound engineering, you expect each feature to make the next feature easier to build.” — Explaining the core principle of compound engineering that differentiates it from traditional engineering.
“Roughly 80 percent of compound engineering is in the plan and review parts.” — Highlighting the importance of planning and review in the compound engineering process.
Topics
Full Article
Published: 2026-01-30
Source: https://every.to/source-code/compound-engineering-how-every-codes-with-agents-af3a1bae-cf9b-458e-8048-c6b4ba860e62
.png)
While we’re on our Think Week offsite this week, we’re resurfacing Cora general manager Kieran Klaassen**’s work on the theme of compound engineering. In this final piece, Kieran teams up with Dan Shipper to describe how compound engineering allows Every’s lean team to provide multiple software products to thousands of users. They propose a four-step loop (plan, work, review, compound) for software teams writing code with AI so you can create the same development magic. Read on for the complete framework, and learn why planning dominates 80 percent of the process.—Kate Lee
What happens to software engineering when 100 percent of your code is written by agents? This is a question we’ve had to confront head-on at Every as AI coding has become so powerful. Nobody is writing code manually. It feels weird to be typing code into your computer or staring at a blinking cursor in a code editor.
So much of engineering until now assumed that coding is hard and engineers are scarce. Removing those bottlenecks makes traditional engineering practices—like manually writing tests, or laboriously typing human readable code with lots of documentation—feel slow and outdated. In order to deal with these new powers and changing constraints, we’ve created a new style of engineering at Every that we call compound engineering.
In traditional engineering, you expect each feature to make the next feature harder to build—more code means more edge cases, more interdependencies, and more issues that are hard to anticipate. By contrast, in compound engineering, you expect each feature to make the next feature easier to build. This is because compound engineering creates a learning loop for your agents and members of your team, so that each bug, failed test, or a-ha problem-solving insight gets documented and used by future agents. The complexity of your codebase still grows, but now so does the AI’s knowledge of it, which makes future development work faster.
And it works. We run five software products in-house (and are incubating a few more), each of which is primarily built and run by a single person. These products are used by thousands of people every day for important work—they’re not just nice demos.
This shift has huge implications for how software is built at every company, and how ambitious and productive every developer can be: Today, if your AI is used right, a single developer can do the work of five developers a few years ago, based on our experience at Every. They just need a good system to harness its power.
The rest of this piece will give you a high-level sense of how we practice compound engineering inside of Every. By the time you’re done, you should be able to start doing the basics yourself—and you’ll be primed to go much deeper.
Compound engineering loop
A compound engineer orchestrates agents running in parallel, who plan, write, and evaluate code. This process happens in a loop that looks like this:- Plan: Agents read issues, research approaches, and synthesize information into detailed implementation plans.
- Work: Agents write code and create tests according to those plans.
- Review: The engineer reviews the output itself and the lessons learned from the output.
- Compound: The engineer feeds the results back into the system, where they make the next loop better by helping the whole system learn from successes and failures. This is where the magic happens.
Key Takeaways
Notable Quotes
What happens to software engineering when 100 percent of your code is written by agents?Context: Introducing the concept of compound engineering where AI agents write all the code.
In compound engineering, you expect each feature to make the next feature easier to build.Context: Explaining the core principle of compound engineering that differentiates it from traditional engineering.
Roughly 80 percent of compound engineering is in the plan and review parts.Context: Highlighting the importance of planning and review in the compound engineering process.
Related Topics
- [[topics/claude-code]]
- [[topics/agent-native-architecture]]
- [[topics/ai-agents]]
Related Articles
Compound Engineering: The Definitive Guide
Dan Shipper (Every) · explanation · 87% similar
Compound Engineering Camp: Every Step, From Scratch
Dan Shipper (Every) · tutorial · 85% similar
My AI Had Already Fixed the Code Before I Saw It
Dan Shipper (Every) · explanation · 85% similar