Secure Trajectories by Sondera

Safe Was a Policy Decision All Along

OpenAI's models breached a company to cheat on a test. The scary part isn't that they broke a rule. It's that they didn't.

Jul 22 • Josh Devon

6

1

3

June 2026

Know Your Golem: Characterizing AI Agents

A framework for characterizing, monitoring, and controlling AI.

Jun 22 • Matt Maisel

6

1

Your Agent Doesn't Care What It Costs

Token burn has become a security and resiliency risk, and the only way to control the bill is to govern what the agent does.

Jun 10 • Josh Devon

8

2

LLMs-as-Judges Miss Bad Behavior

Context rot affects the watchers too. As an agent's run grows, the LLM monitoring it misses buried dangerous actions up to 30 times more often.

Jun 2 • Josh Devon

8

2

May 2026

The Agent PB&J Problem

The lethal trifecta is not just a story about prompt injection. It is a story about literal execution.

May 26 • Josh Devon

11

1

4

O brave new world, that has such people and AIs in't.

How do we control AI behavior, not just monitor it?

May 1 • Matt Maisel

7

1

1

April 2026

How to Stop Claude Code from Leaking Sensitive Data

Moving from “prompt and pray” to hard rules that control what agents actually do.

Apr 23 • Josh Devon

10

6

2

March 2026

Hooking Coding Agents with the Cedar Policy Language

A reference monitor built on the trajectory event model.

Mar 5 • Matt Maisel

20

2

7

Claude Code's Plan Mode Isn't Read-Only, But You Can Fix It

Making "read-only" a rule instead of a suggestion.

Mar 2 • John Brock

6

2

February 2026

We Told OpenClaw to rm -rf and It Failed Successfully

Policy as code guardrails for AI agents

Feb 4 • Josh Devon

18

2

6

January 2026

Gas Town Needs a Citadel

Why Industrialized Agent Orchestration Requires Industrialized Control

Jan 21 • Josh Devon

4

6

3

Supervising Ralph: Why Every Wiggum Loop Needs a Principal Skinner

From Naive Persistence to Reliability

Jan 13 • Josh Devon

8

1

4