Security engineering · AI-assisted development · Agents in our loop

Your agents. Your rules.

AI agents are everywhere in your product and code.
Without rolesboundariesoversight, you're guessing.
Let's inspect.
Hallucination Check
agent-verified output
PASS
PII Detection
sandbox-enforced
CLEAN
Signed Trail
a7f3b2 · jose · 10:42
SIGNED

Coderoom

Code quality matters. Working with agents puts even more pressure on it. A coding workspace built for a different model of agentic engineering.

Open source
Available on GitHub
Human-led
The engineer remains central
Mob programming
Multiple agents, shared review
Control by design
Roadmap includes sandboxing, scoped permissions, and explicit escalation

Latest insights

Short, practical notes on engineering, security, control, automation, and regulatory delivery.

#coderoom#agentic engineering
5 min read
Mob Programming for One

Agents can generate useful material faster than an engineer can absorb it. This post uses mob programming as a model for structuring engineer-writer-reviewer loops that preserve understanding, scrutiny, and engineering …

#DORA#Register of Information
6 min read
Beyond the first submission: three governance failures that will break your DORA RoI in 2026

The 2025 Register of Information submission was a scramble for most organizations. In 2026, the biggest challenge many organizations still face is unresolved governance, driven by unclear ownership, disconnected …

#DORA#Register of Information
6 min read
Why your DORA Register of Information looks complete but fails regulatory validation

The Register of Information often looks complete during internal preparation but fails regulatory validation. This happens because the reporting templates do not enforce the underlying data model. This post explains what …