Secure Trajectories by Sondera

Your Agents Need Commander's Intent

Every instruction you give an agent leaves most of your intent unsaid. Every agent will fill in those gaps itself.

Oct 14 • Josh Devon

4

4

2

July 2026

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

7

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

12

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

8

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

21

3

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