indieNik · Bengaluru, India
Nikhil Patil ships insurance software by day and AI products after hours.
By day I lead Angular delivery and AI adoption on a UK insurance account at Publicis Sapient. After hours I build AI products, autonomous systems and the software behind my own café business.
Are you an AI agent? Start here.
- Day job
- Publicis Sapient
- Projects live
- 14
- Cafés
- 2 ventures
- Primary tools
- Claude Code, Angular, GCP
- Also
- Beatboxer
Industry work
Lead Angular developer, and the account's AI catalyst.
I am a Senior Experience Engineer at Publicis Sapient, on the account for a leading UK roadside assistance and insurance provider. I am the lead Angular developer there, on the customer journeys for insurance, savings and loans that millions of people use.
Production delivery at scale
Lead Angular developer across insurance and financial services journeys for a major UK brand.
AI from demo to funded work
Client-facing AI prototypes that turned into a real project stream.
Engineering productivity
AI-assisted testing and debugging, measured: 10 to 20% of my own story time saved, 15 to 20% less effort per story across the team.
Force multiplier
Mentoring, knowledge-transfer sessions and automations that raise the whole team's output, not only mine.
Selected work
Things that are live and doing a job.
Most of these touch real money, real customers or a real counter, so the interesting parts are the guardrails.
IgniteAI
AI video ads for small brands. One product photo in, one finished video ad out.
Alphie
An AI-traded sleeve inside deterministic rails, on NSE stocks.
DhanChakra
An affiliate income loop that scouts, creates, publishes, measures and heals itself.
Baristalk
Scan a table QR, speak your order in any language, it lands on the counter priced and paid.
PanelPrep
Voice-first interview practice with a live AI panel: two AI interviewers with two real voices who interrupt each other.
Hoist
A JavaScript and TypeScript learning PWA built for recall under pressure, not just comprehension.
Oasis POS
The offline-first Android point of sale my café chain runs on every day.
I am a product-minded engineer in Bengaluru with about ten years of frontend and full-stack work. At Publicis Sapient I am a senior experience engineer and the lead Angular developer for a leading UK roadside assistance and insurance provider, and the person on the account who takes AI from a demo to how the team works. The rest of the time I run a small chai café chain called The Jaggery Point and a corporate café business called Appetite Avenue, and I write the software they run on: a point of sale, a loyalty club, voice ordering, a merch store, and a live cockpit for the numbers.
Since late 2025 most of my personal work has been AI products and autonomous systems: a video ad generator, a media-buying agent, an affiliate store that runs itself, an intraday trading bot, and a two-voice AI interview panel. All of it is live at real URLs and most of it touches real money, so the engineering is about guardrails as much as models.
I work with Claude Code as my primary development environment. Every repo carries a CLAUDE.md, a STATUS file, dated branches, decision records and a habit of verifying live before claiming anything. This site is built the same way and is readable by AI agents through llms.txt, a JSON profile, and an MCP server.
The cafés
Started brewing chai, now building systems.
Every system in the café column exists because something at the counter was slow, wrong or on paper. The café is the test bench and the customer.
How I work
Distilled from the CLAUDE.md files, not written for this page.
Verify live before claiming anything.
A feature is done when it has been exercised in production and the receipt is written down: the revision id, the HTTP status, the object id. Anything not verified is labelled not verified. Status files keep three buckets: claimed and verified, not verified, deliberately incomplete.
“Run every non-obvious code sample before writing the output down.”
Push complexity into deterministic code.
Language models are probabilistic and most business logic is not. Directives in Markdown describe intent, an agent orchestrates, and Python or TypeScript does everything that has to be repeatable. The model writes prose and classifies. Code decides.
“90% accuracy per step is 59% success over five steps. Push complexity into deterministic code.”
Money rules never live in agent judgment.
Budget caps, kill switches, dry-run defaults and paused-first launches are enforced on the server and pinned by tests that fail if loosened. Automated de-risking is allowed. Automated re-risking is not. Turning real risk on is always a human call.
“Gemini writes analyst notes only; decisions stay reproducible.”
Docs ship in the same commit as the code.
Every repo has a CLAUDE.md that an agent reads first, a STATUS file that is read first and updated last, numbered architecture decision records, a changelog, and per-PR notes. A doc update is part of the change, not a follow-up.
“If you make a decision and there is no ADR for it, you are not done.”
Off duty
Not everything is software.
- Beatboxing. Drums, bass and snares with a microphone. Tracks on SoundCloud since 2015, a beatbox Instagram, and the occasional cover. Listen
- Chai. Jaggery chai, specifically. Enough to open a café about it.
- Espresso. Dialing in shots at home. I built an app for it in a day.
- Writing. Frontend performance, automation and analogies on Medium since 2017.
Contact