I'm Sekou. Twenty years turning business strategy into distributed systems, from multi-region networks to GPU-ready compute and LLM serving. This is where I think out loud about that work: the trade-offs, the failures, and what actually held up in production.
Sekou M. Doumbouya, infrastructure/cloud architecture leader. Not the basketball player.
01. Writing
Essays on systems design, infrastructure leadership, and AI workloads.
A 41-task graph ran for 41 hours, produced 115 reviews, and merged nothing. Then I pivoted mid-flight to milestones, and the same session shipped five PRs in half the time.
Read article →anvil-serving routes coding-agent work to local models only where measured quality has earned it, verifies local output, and escalates up the tier ladder the moment verification fails.
How wiring two mismatched GPUs into my coding harnesses turned into intent-based routing, and why the measurement, not the transport, became the product.
Two days of autonomous agents shipped a release and moved a billion tokens. Only about five percent was generated work. That five percent is the number that sizes a local box.
02. Proof of Impact
A few case studies, when you want the receipts behind the writing.
Coding harnesses can point at a local model, but most routers decide by static model names, costs, or regexes. That is not enough for agent work. A model can return clean JSON that is still semantically wrong, and a bad plan can poison an entire run without throwing an error.
Read case study →Multiple AI coding agents and the humans supervising them increasingly work the same plan at the same time, but the tools they coordinate through (GitHub Issues, markdown conventions, chat history) store free-form text, claim work by label or a chat message, and enforce nothing when two agents grab the same task. Worse, when an agent reports a task complete, nothing verifies the claim. Status outranks evidence, which is exactly backwards for autonomous or weakly-supervised runners.
Read case study →Individual investors face a fundamental asymmetry: the tools that power institutional decision-making (real-time data, portfolio analytics, macro indicators, technical analysis) are locked behind expensive terminals or scattered across dozens of websites. Meanwhile, AI assistants can reason about financial data but have no access to it.
Read case study →03. Community
Thought leadership, community, and open source.
Interested in AI infrastructure, platform engineering, or just want to connect? I'm always happy to talk shop.
Get in Touch →
