Best of the Pod: Claude Code - How Two Engineers Ship Like a Team of 15
🤖 AI Summary
Overview
This episode dives into how Kieran Klaassen and Nitesh Agarwal, two engineers from Every, are revolutionizing software development using AI agents, particularly Anthropic’s Claude Code. They discuss their innovative workflows, the concept of compounding engineering,
and how they leverage AI to amplify productivity, achieving the output of a much larger team. The episode also features a ranking of popular AI coding agents and explores the evolving mental models required for this new era of software engineering.
Notable Quotes
- Coding with AI is more than just the coding part. It should be used for everything.
– Kieran Klaassen, on the expansive potential of AI in engineering.
- What you did first is spent time building a prompt that effectively builds other prompts. That’s really cool.
– Dan Shipper, on the power of compounding engineering.
- You want to catch problems at the lowest value stage.
– Nitesh Agarwal, on the importance of early intervention in AI-driven workflows.
🚀 Compounding Engineering with AI
- Kieran Klaassen introduced the concept of compounding engineering,
where each task completed with AI makes subsequent tasks easier and faster.
- The team uses AI agents not just for coding but for research, workflows, and even project management, creating a seamless and efficient development process.
- By designing prompts that generate other prompts, they’ve streamlined feature development, reducing manual input and accelerating progress.
🤖 Claude Code: A Game-Changer in Agentic Coding
- Claude Code, an agentic coding tool by Anthropic, is central to their workflow. It operates as a command-line interface with access to local files, enabling it to perform tasks like code reviews, debugging, and creating pull requests autonomously.
- Unlike traditional tools like Cursor or Windsurf, Claude Code simplifies the process by focusing on broader engineering support rather than just coding.
- The team demonstrated how Claude Code can autonomously research, plan, and execute tasks, significantly reducing the time and effort required for development.
🛠️ New Mental Models for AI-Driven Development
- The team emphasized the importance of adapting to new workflows and principles in the age of AI.
- Nitesh Agarwal highlighted the need to focus on the earliest stages of problem-solving to prevent errors from compounding later in the process.
- They stressed the value of human oversight, intuition, and taste in reviewing AI-generated outputs to ensure quality and alignment with project goals.
📊 Ranking AI Coding Agents
- Kieran Klaassen shared his tiered ranking of popular AI coding agents:
- S-tier: Claude Code, AMP
- A-tier: Cursor, Friday
- B-tier: Devin, Codex, Charlie (for code reviews)
- C-tier: Windsurf
- D-tier: GitHub Copilot (not yet tested for agentic capabilities)
- He emphasized that different agents excel in specific tasks, such as UI design (Friday) or code reviews (Charlie), and suggested using them in tandem for optimal results.
📋 The Role of Traditional Practices in AI Workflows
- Despite the advancements in AI, the team underscored the continued importance of traditional engineering practices like testing and evaluations (evals).
- They use tests to verify the functionality of AI-generated code and prompts, ensuring reliability and accuracy.
- The team also highlighted the potential of automating tests and evaluations to further enhance efficiency and reduce manual intervention.
AI-generated content may not be accurate or complete and should not be relied upon as a sole source of truth.
📋 Episode Description
If you’re using AI to just write code, you’re missing out.
Two engineers at Every shipped six features, five bug fixes, and three infrastructure updates in one week—and they did it by designing workflows with AI agents, where each task makes the next one easier, faster, and more reliable.
In this episode of AI & I, Dan Shipper interviewed the pair—Kieran Klaassen, general manager of Cora, our inbox management tool, and Cora engineer Nityesh Agarwal—about how they’re compounding their engineering with AI. They walk Dan through their workflow in Anthropic’s agentic coding tool, Claude Code, and the mental models they’ve developed for making AI agents truly useful. Kieran, our resident AI-agent aficionado, also ranked all the AI coding assistants he’s used.
If you found this episode interesting, please like, subscribe, comment, and share!
Want even more?
Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.
To hear more from Dan Shipper:
Subscribe to Every: https://every.to/subscribe
Follow him on X: https://twitter.com/danshipper
Head to ai.studio/build to create your first app.
Pitch is the AI presentation platform that helps professionals collaborate on, create, and deliver winning slide decks — all while staying on brand: https://pitch.com/use-cases/ai-presentation-maker/?utm_medium=paid-influencer&utm_campaign=every
Timestamps:
Episode start: 00:00:00
Introduction: 00:01:16
Why Kieran believes agents are turning a corner: 00:03:18
Why Claude Code stands out from other agents: 00:06:36
What makes agentic coding different from using tools like Cursor: 00:11:58
The Cora team’s workflow to turn tasks into momentum: 00:15:20
How to build a prompt that turns ideas into plans: 00:23:07
The new mental models for this age of software engineering: 00:34:00
Why traditional tests and evals still matter: 00:39:13
Kieran ranks all the AI coding agents he’s used: 00:42:00
Links to resources mentioned in the episode:
Try Cora, our AI email assistant: https://cora.computer/
Kieran Klaassen: @kieranklaassen
Nityesh Agarwal: @nityeshaga
The book that helps Nityesh form mental models to work with AI agents: High Output Management