product engineer. i live at the intersection of customers, engineering, and product — which is a fancy way of saying i care about what gets built and why, not just how. based in bangkok.
i want to be a founder one day. but that's not something you announce — it's something you earn. so for now: i talk to users, i ship things, i get shit done. ai handles the heavy lifting on the engineering side. my job is figuring out what's actually worth building. this is where i document the work.
Writing
view all writing →Experience
- >worked with enterprise clients — Kraken, Lisk, Reya, and others — to scope and launch their chains on Gelato RaaS
- >guided teams through stack decisions: OP vs Arb Orbit, DA layer, sequencing, settlement tradeoffs
- >collected requirements, coordinated with internal devs to get chains live, stayed involved post-launch
- >set up integration partners, launched Blockscout instances, submitted PRs to the superchain registry
- >supported 30+ protocols on devrel — MoonPay, Infinex, MakerDAO, Beefy, and others — wrote docs when official ones didn't exist
- >moved into the backend team for the last year — shipped code on Web3 Functions, Relay, VRF, Gasless, and AA
- >worked directly with the CTO: added prometheus metrics, shipped new features including Tenderly simulation for ERC-4337 transactions
- >led the TRON gasless integration using JIT energy rental — cut transaction costs by 60%
- >also built an elizaOS AI agent — presented it live at ETH Dubai 2025. open source · watch the demo
- >first real exposure to production DeFi
- >built automation bots for strategy rebalancing and smart contract operations
- >learned fast what happens when onchain automation breaks in a live system
- >built the ops dashboard for monitoring contract state, tracking transactions, and managing protocol deployments
- >got a practical education in how yield strategies actually execute across chains, and how to instrument systems so you know when something is wrong before users do
Builds
Basic prompts were producing vague, generic outputs. Built PromptBetter to sit in front of Claude Code and rewrite prompts for clarity and technical depth before anything runs. Using it daily and improving it — better rewrite quality, tighter approval flow.
I built Saphan because daily conversations in Thailand became hard when language got in the way. Most translation tools I tried felt robotic in real human conversation. I am improving real-time voice quality, reducing latency, and making turn-taking feel more natural during long conversations.
Gemstone dealers and diamond traders run their entire trading desk on memory, Excel, and WhatsApp — no real-time margin, no inventory visibility, no audit trail. Grew up in this industry and knew exactly how broken it was. Built Krsyn to fix it: real-time margin, live inventory, memo exposure, and full audit trace in one system. Live at krsyn.com. Already talking to customers across colored stones, diamonds, consignment, and direct sales. In the feedback phase — iterating fast on what I'm hearing.
Built to explore x402 micropayments and verifiable randomness. Wanted to see if per-request payment for randomness made sense for autonomous agents — no subscriptions, no pre-funding, no API keys. Experiment is done. Not actively developing.
Now
- Demoing the jewelry trade ERP to first clients
- Iterating on PromptBetter based on daily use
- Publishing build logs as things ship
Reading
the pragmatic programmer
david thomas & andrew hunt
changed how i think about software craft
working in public
nadia eghbal
how open source actually works and why maintainers burn out
poor charlie's almanack
charlie munger
mental models worth spending time with
the design of everyday things
don norman
still shapes how i think about interfaces and feedback loops