Hi, I'm André
I'm a solo developer building systems in Rust. Most of my time goes into AgenticOS, a personal agent-infrastructure platform: persistent multi-layer memory for coding agents, MCP servers, hook-based lifecycle automation, and multi-agent orchestration. The rest is split between web work, analytics pipelines, and 3D/VFX tooling (Houdini, Blender).
Here I write about building and measuring agent systems - what actually works, what silently breaks, and how to tell the difference.
Recent posts
-
81% of my agent's telemetry was a copy of something I already had
My agent logged every tool call verbatim, and two thirds of the biggest rows were the harness echoing back a file that was already in git. Measuring it split one population into two with opposite economics, and produced an option nobody had drafted.
-
Prompt injection is worse when your agent has a memory
Most injection defense assumes the attack ends with the session. A memory system removes that assumption: one poisoned line promoted into durable memory resurfaces later as trusted context. So the defense has to be infrastructure, not vigilance.
-
An agent that remembers everything is a secret leak with a good memory
An encrypted vault protects the secrets I chose to protect. The dangerous ones are the keys pasted into a debugging session, and a memory system that writes every event to disk turns each one into a liability that grows every day the system runs.
-
Testing a data pipeline against the spreadsheets it replaced
Replacing a reporting workbook means first proving you match it. Then the diffs start pointing the other way, and you find out the report you were treating as the specification does not reconcile against the warehouse it came from.
-
Letting an agent write to my production CMS
Handing an agent write access to a live CMS is not a drafting problem, it is a blast-radius problem. The work that made it safe happened before the agent existed: collapsing eighteen write paths into one seam that a test can enforce.