What the Best Engineers Built for Their Coding Agents
Notas do episódio
What happens when coding agents see your entire system: code, services, infrastructure and live traffic, all connected? Most agents are blind to everything outside the repo. Adyen Staff Engineer Mat Jones explains what changed once theirs weren't, and why he calls it somewhat scary.
In this video, we cover:
- Running five or six coding agents in parallel with git worktrees and Atrium, an internal tool that lets agents coordinate and share memory
- Architect: nine connected graphs in Neo4j covering services, code, DNS, data stores and infrastructure
- Ingesting 7 million trace spans a second with Kafka and Apache Flink, and what collapsed on the first try
- Sentinel: anti-pattern monitoring, with agents that raise the fix as a merge request
- MCP vs APIs vs CLI tools, and how to deal with tool bloat
This episode is for software engineers and platform teams who want coding agents to reason about real systems, not just the repo in front of them. You'll leave with a concrete place to start and an honest view of the risks.
00:00:00 - Intro
00:00:42 - Running Five Coding Agents in Parallel
00:01:35 - Atrium: How Agents Avoid Stepping on Each Other
00:06:57 - Why Graphs Save Coding Agents Tokens
00:12:25 - What Is Architect? Nine Graphs in One Database
00:16:54 - What Broke at 7 Million Spans a Second
00:20:37 - The Timeline From Proof of Concept to Production
00:27:59 - Tracing Code Changes to Critical Payment Flows
00:30:26 - How to Start: Build Scrappy, Then Earn Buy-In
00:35:07 - Making a Codebase Agent Friendly With Skills and Hooks
00:42:07 - Why You Should Start With a Service Graph
00:44:46 - The Downside of Everyone Seeing Everything
00:48:34 - Sentinel: Agents That Find and Fix Anti-Patterns
00:53:01 - Are We Going Too Fast With AI?
01:01:55 - Two Engineers, Four Months: Why Big Bets Got Cheaper
01:07:11 - MCP vs CLI Tools and the Tool Bloat Problem
Guest: Mat Jones, Staff Engineer at Adyen
https://www.linkedin.com/in/mathewwjones