engineer. builder. systems+ai.
I work full-stack on onchain products at Polygon, focused on shipping systems that improve speed and confidence through testing, reliability, and clear docs. Outside work, I build practical AI tools, agent workflows, and small products that force real feedback.
If you're building practical agent systems, onchain products, or useful dev tools, email me or say hello on X.
Last updated: 2026-06-29
The active surface area: production work, public tools, and operator systems.
Polygon's native liquid staking product for staking, unstaking, migration, and DeFi-ready sPOL positions.
Add more transport modes and explore notification workflows.
Keep dogfooding the operator surfaces and tighten what is genuinely useful versus just interesting once.
A few receipts before the text starts doing too much work.
agent-first public data tools
A family of terminal tools for public data: transport, companies, rail, fuel, and Parliament. Built for humans, predictable enough for agents.
$ tfl status Central: Good Service District: Minor Delays $ parliament search bills "energy" --take 3 Great British Energy Bill 5172 Committee
proof: five published CLIs · npm packages · landing pages · reusable agent skills
operator tooling
Local-first web dashboard for Hermes Agent. Runtime health, sessions, cron, skills, memory, files, and usage in one place.
proof: real local agent state, not fake dashboard filler
full-stack AI product
Roast and glaze photo app with image uploads, auth, credits, and share-friendly output loops.
proof: upload → generate → credits/payment → share loop
Current focus across production work, public tooling, and the writing that turns the lessons into something reusable.
At work: stepping into Polygon's Open Money Stack while keeping the bar high on reliability, testing, docs, and observability.
Outside work: building agent-first CLI tools and operator surfaces that are useful to humans and predictable enough for agents.
Writing: restarting the habit with notes about agent systems, engineering judgement, onchain product work, and what actually held up.
07 May 2026 · 6 min read
AI has made code generation cheap, and everyone is all in, but nobody is thinking about how the review cycle should change.
27 Apr 2026 · 6 min read
Vibe coding is one way to use AI. Treating every AI-assisted workflow as the same thing is lazy.
17 Apr 2026 · 3 min read
Agents can turn a day into a week of code output. That still doesn't mean the work was the right bet.
Shipped a personal-site pass with richer engagement analytics and trimmed copy around the /log flow.
Reworked a private poker tracker into a focused notes and hand-review tool instead of a noisy results dashboard.
Rescoped a legacy backend modernisation into reviewable chunks with production-backed tests, pnpm, and Node 24.
Merged a FairSide feedback widget and verified real submissions so product decisions can use actual user signal.
Moved Shan OS generated outputs to Discord-first routing so plans, digests, and prompts land where they are actually used.