Open-source AI products
A SEBI regulation assistant, a zero-knowledge password manager, a passkey library with a preprint, and a local-AI study app for Mac. Each publishes its evaluation results.
Learn more about my workI'm a Technical Product / Program Manager who designs, ships and evaluates AI-native products: retrieval assistants, privacy-first apps and local AI. I help product teams in India do the same.

A SEBI regulation assistant, a zero-knowledge password manager, a passkey library with a preprint, and a local-AI study app for Mac. Each publishes its evaluation results.
Learn more about my workPaid 30-minute consultations on AI product strategy, RAG and agent evaluation, BFSI compliance-by-design and private local AI, plus a four-session mentorship for AI PM career switchers.
Learn more about consultingA practical field guide, answer-first articles and a glossary for product managers building AI products in India.
Learn more in the field guideDemand for AI skills in India has risen sharply, but most AI projects still fail to show a return. Product managers who can specify, measure and ship trustworthy AI close that gap.
Figures are quoted from the linked sources and were last checked on 16 November 2026.
Each card shows dated, measured results. Weak spots are shown in orange, not hidden.
Cited answers over 1,490 SEBI circulars, or an honest abstention.
Proves AI evaluation design · Retrieval (RAG) product design · Trust and compliance by design (India) · Communicating AI quality honestly
Last public activity
A zero-knowledge, offline-first password manager with passkey unlock and on-device AI.
Proves Privacy and security architecture · On-device and local AI · Technical program delivery
Last public activity
Passkey-derived vault key wrapping as an npm library and a research preprint.
Proves Privacy and security architecture · Communicating AI quality honestly
Last public activity
Online lectures into transcripts, slide-linked notes and flashcards, entirely on your Mac.
Proves On-device and local AI · AI evaluation design · AI product strategy and MVP scoping
Last public activity
Search Python code in plain English, then get a one-line explanation of each function.
Proves AI evaluation design · Retrieval (RAG) product design · Communicating AI quality honestly
Last public activity
It is building products where an AI model is the core of the experience, not an add-on. The spec becomes an evaluation set, quality is measured as a rate, every task has a cost, and trust controls are designed in from the first sprint.
Builder's notes from Lecture Lens: four times the LLM judge, not the model, was wrong, why 80% agreement hid a weak judge, and a checklist before a judge gates a release.
Read the article →Builder's notes from Lecture Lens: why screen capture blanked a DRM lecture, the five-phase test that found the cause, and why the fix pauses capture, not bypasses it.
Read the article →Builder's notes from Lecture Lens: a six-layer content guard with hashed blocked terms, a disabled push URL and CI re-checks, plus the limits I document openly.
Read the article →AI-native product management is the practice of building products where an AI model is the core of the experience rather than an add-on. The product manager specifies behaviour with evaluation sets, measures quality as a rate, manages inference cost per task and designs trust controls such as citations, abstention and consent from the start.
AINPM.in is the site of Ian Pinto, a Technical Product / Program Manager in India. It brings together his open-source AI products, a field guide and articles on AI-native product management, a skills matrix with public evidence, and paid consultations.
SEBI Circular RAG is an open-source assistant that answers questions over 1,490 SEBI circulars. It cites every claim, flags superseded circulars, can answer as of a past date and refuses when evidence is missing. A live demo runs on Hugging Face and the code and dataset are public.
India has no single AI Act. Product teams track MeitY's India AI Governance Guidelines, the DPDP Act and Rules (consent managers from 13 November 2026, full compliance by 13 May 2027), IT Rules on labelling AI-generated content, RBI's FREE-AI framework and SEBI's forthcoming AI/ML guidelines.
Start by building a small evaluation set of about 50 real examples for a feature you own, prototype against it with AI coding tools, track cost and latency per task, and learn the regulation that applies to your sector. Publishing a working project with its evaluation results is stronger evidence than a certificate.
No. The content is general information for product managers. Regulatory summaries are for orientation only, and SEBI Circular RAG is an independent research demo that is not endorsed by SEBI. Always verify against primary sources.