ThoughtsAugust 12, 2026·7 min read
Dreams, Reflections, and Inceptions
Dreams sound mystical. In practice, they are a way to label agent traces, reflect across sessions, and turn repeated behavior into something the next run can use.
Read more →
bdougie
Co-FounderBrian previously founded Open Sauced, where he worked on increasing knowledge and adoption within open source communities. His current focus is AI infrastructure and agent systems — building observational memory pipelines using Kafka, Flink, and DuckDB to help agents get better every run.
briandouglas.me ↗14 articles← All posts
ThoughtsJuly 28, 2026·10 min read
Make Something Agents Want
London's bridges are failing under load nobody modeled. Haussmann rebuilt Paris for traffic that hadn't arrived yet. Agent infrastructure faces the same choice: skills, shared team sessions, and reflections are how you build for the traffic that is coming.
Read more →CompanyMarch 31, 2026·4 min read
Introducing Paper Compute Co: Infrastructure for Running AI Agents in Production
We built Paper Compute to close the Agent Gap — the inability to prove what an agent did, audit its actions, or replay its decisions. Here's what we built and why.
Read more →ProductMarch 25, 2026·5 min read
Turn Your Agent Sessions Into Skills
I hit the same Confluent Cloud bugs across two projects. The second time, I extracted a skill from my tapes sessions instead of debugging from scratch. Now every agent I run knows the fix.
Read more →ProductMarch 17, 2026·8 min read
Logs Are the Self-Healing Feedback Loop
Agents don't need to remember everything. They need to observe what went wrong. Structured logs become telemetry, telemetry becomes signals, and signals become the context for the next run.
Read more →ThoughtsMarch 16, 2026·6 min read
Sandboxes Are for Experiments. Agents Need a Computer.
Once agents got good enough to clone repos, install dependencies, modify files, and execute code they just wrote, the natural question became: where does this actually run? Sandboxes were designed for short-lived, contained execution. Agents aren't snippets.
Read more →ThoughtsMarch 9, 2026·6 min read
Agent Played Pokémon for 1,000 Turns. It Never Left the Bedroom
An AI agent played Pokémon Red for 1,000 turns without leaving the bedroom. The failure wasn't the model. It was the absence of telemetry.
Read more →ProductMarch 4, 2026·6 min read
Agents Need Black Box Recorders
Every commercial aircraft carries a flight recorder. Agent systems don't. The gap between an agent that works and an agent you can trust in production is telemetry.
Read more →ThoughtsMarch 3, 2026·5 min read
Stop Optimizing the Model. Start Securing the Runtime.
Optimizing for model performance while ignoring execution infrastructure is like choosing the fastest race car without checking whether the track has guardrails. The real engineering challenge isn't squeezing more capability out of LLMs—it's figuring out how to actually run them safely.
Read more →ThoughtsFebruary 23, 2026·4 min read
If You Can't See What Your Agent Did, Who's Going Trust It?
Agents are now consequential enough to warrant national-level oversight. Compliance doesn't require weaker AI—it requires observable AI. The observable era is the one that scales.
Read more →CompanyFebruary 19, 2026·9 min read
The Missing Primitive in Agent Infrastructure
Visibility is the easiest piece. The hard part is analyzing and understanding what you're observing. The next phase of agent infrastructure won't be defined by visibility—it will be defined by durability.
Read more →ThoughtsFebruary 17, 2026·5 min read
The True Cost of Claude Code
If you're paying $100/month but consuming multiples of that in value, you have to start wondering when that's going to catch up to you. The AI coding tool market is following a familiar playbook.
Read more →ProductFebruary 16, 2026·5 min read
Continuous AI: How We Keep Our tapes.dev Docs Current
Documentation that writes itself sounds like a gimmick. For tapes.dev, it's an operational reality. Here's how we wired continuous AI into our workflow to keep docs accurate as the codebase evolves.
Read more →CompanyDecember 19, 2025·2 min read
The Missing Harness
Why AI Needs Distributed Systems Infrastructure
Read more →