Builds the product, not just the roadmap
The proof-of-concepts that close deals, the personal agent fleet, the apps, this site: built hands-on with Claude Code, then run in production.
Evidence
Every claim on my CV, mapped to the write-up that substantiates it.
Hiring screens ask for demonstrated capability. This page is the map: each claim I make, and the published work behind it. Every number comes from one production system I am accountable for, not a benchmark.
Sells what he builds
Sole DRI and deployed engineer on enterprise deals with household Singapore names: Ha Li Fa and COURTS, two five-figure engagements taken from discovery to signed work order to live production, one person end to end. Underneath them, the volume motion: 20+ proof-of-concepts carried from first prototype to paying deployment, 30+ SME clients closed, and 15+ of those deployments delivered solo.
Ships complete products, fast
Parallax went from empty repo to the App Store in three weeks. Ragnarok, a multi-tenant gym operating system, went from first commit to production in seven, and moved a 441-member gym off its incumbent software.
Runs agents at production scale
230K+ AI interactions a day across 100+ SME deployments, 99.65% task success. Real customers on real WhatsApp lines, not benchmarks.
Evaluates what it ships
Three-layer evaluation: deterministic checks on every wake, calibrated LLM-as-judge at scale, weekly human review as the source of truth.
Owns deployment safety
Model-layer safety is the lab’s job. Deployment-layer safety, pointing a safe model at a real business without getting burned, is mine.
Understands the workflow nobody documented
The hard part of a deployment is rarely the model. It is the approval queue that is slower than the messaging window, and the trust the owner has not extended yet.
Measured after handoff, not at the demo
A deployment counts when the business runs on it without me. Adoption, self-learning in place, and reliability once I am gone.
Treats cost as a product feature
Model tiering, cost attribution per interaction, and the observability to catch a runaway cron before the bill does.
Kills what does not work
Product judgement includes the post-mortem. One product retired in public, and the architecture lesson that came out of it.
If you are screening me and have ninety seconds: the failure museum, then the eval framework. If you would rather read code than prose, start here. Or curl yashgadodia.com/cv.