DEV Community

Laurent DeSegur profile picture

Laurent DeSegur

Software engineer building open-source AI agent infrastructure. Creator of KarnEvil9 — a deterministic AI agent runtime implementing Google DeepMind's Intelligent AI Delegation framework. Writing abou

Education

CS + EE

Work

Managing Director

How the Multi-Agent Swarm Actually Works

How the Multi-Agent Swarm Actually Works

2
Comments 1
20 min read
Cross-Session Lessons in Carnival9: How an Agent Remembers What Worked

Cross-Session Lessons in Carnival9: How an Agent Remembers What Worked

Comments
26 min read
Two Ends of the Token Budget: Caveman and Tool Search

Two Ends of the Token Budget: Caveman and Tool Search

Comments
23 min read
Five Atomic Skills, Two Approaches: Claude Code and a Paper

Five Atomic Skills, Two Approaches: Claude Code and a Paper

Comments
22 min read
How Claude Code Remembers (And Forgets): The Memory and Persistence Architecture

How Claude Code Remembers (And Forgets): The Memory and Persistence Architecture

Comments
18 min read
Functional Emotions and Production Guardrails: What Interpretability Research Means for Claude Code

Functional Emotions and Production Guardrails: What Interpretability Research Means for Claude Code

Comments
13 min read
Claude Code Is Burning Through Your Quota. Here's What's Actually Happening and How to Fix It.

Claude Code Is Burning Through Your Quota. Here's What's Actually Happening and How to Fix It.

Comments
7 min read
The Upstream Proxy: How Claude Code Intercepts Subprocess HTTP Traffic

The Upstream Proxy: How Claude Code Intercepts Subprocess HTTP Traffic

Comments
21 min read
How Tool Search Defers Tools to Save Tokens

How Tool Search Defers Tools to Save Tokens

1
Comments
21 min read
How Claude Code Extends Itself: Skills, Hooks, Agents, and MCP

How Claude Code Extends Itself: Skills, Hooks, Agents, and MCP

Comments
18 min read
What Happens When Claude Code Calls the API

What Happens When Claude Code Calls the API

Comments
18 min read
94% Exposed, 30% Adopted: Why Engineering Leaders Need to Rethink How They Hire

94% Exposed, 30% Adopted: Why Engineering Leaders Need to Rethink How They Hire

Comments
3 min read
How Claude Code Manages Infinite Conversations in a Finite Context Window

How Claude Code Manages Infinite Conversations in a Finite Context Window

Comments 1
20 min read
How Bash Command Safety Analysis Works in AI Systems

How Bash Command Safety Analysis Works in AI Systems

Comments
5 min read
The Claude Code Leak: What Anthropic Accidentally Revealed About the Future of AI

The Claude Code Leak: What Anthropic Accidentally Revealed About the Future of AI

1
Comments
8 min read
OpenAI Just Shipped a Plugin So Codex Runs Inside Claude Code

OpenAI Just Shipped a Plugin So Codex Runs Inside Claude Code

Comments
3 min read
Inside Claude Code's Architecture: The Agentic Loop That Codes For You

Inside Claude Code's Architecture: The Agentic Loop That Codes For You

2
Comments
6 min read
loading...