Signal Thinking
Subscribe
Sign in
Home
Notes
Archive
About
Latest
Top
Discussions
The 22 Failure Modes Are Not 22 Problems. They Are Five.
I published a catalog of twenty-two ways LLM agents fail. Then a commenter said the thing that turns a list into a model: a dependency graph over the…
Jul 31
•
Robert Evans
The Failure Catalog: 22 Ways Every Agent Fails, and the Prompts That Guard Against Them
Every agent you build fails in the same ways.
Jul 30
•
Robert Evans
June 2026
The Penalty for Being Good
How the US government is accidentally handing China the AI race, and why the most principled company in AI is paying the price
Jun 22
•
Robert Evans
1
1
May 2026
My AI Team Debated My Ideas at 5am While I Slept
A tour of the personal intelligence system I built to capture, research, and evaluate ideas overnight
May 25
•
Robert Evans
1
Forty-five minutes on a spec. Thirty minutes to build.
Visionaire Specication System - Claude Code Plugin
May 2
•
Robert Evans
April 2026
The MCP Trojan Horse
How Frontier Models Are Running the Google and Facebook Playbook on Enterprise Data
Apr 3
•
Robert Evans
February 2026
Your AI Code Reviewer Fails on Rule 12
Here's Why
Feb 28
•
Robert Evans
Agentic Engineering: The Learning Layer
Measuring What Matters for Self-Improving AI Teams
Feb 19
•
Robert Evans
Agentic Engineering: Orchestration Design
Building Orchestration Systems That Actually Work
Feb 18
•
Robert Evans
Agentic Engineering: Skill Design
Building Institutional Knowledge Your Agents Actually Use
Feb 16
•
Robert Evans
Agentic Engineering: Agent Design
Specialization Over Intelligence
Feb 13
•
Robert Evans
Agentic Engineering
Building AI Teams That Write Senior-Level Code
Feb 12
•
Robert Evans
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
