Seven Featured Editions from the Vault

Hover or tap any spine in the arc to pull the volume forward, inspect its core thesis, and load its interactive chapter spread into the dual-page reader below.

What it is

One app for the whole family, with your parents at the centre. Know they’re okay, reach them in a tap, book anything they need, send money safely, gift with dignity. From any city in the world, with their consent at the core.

Reassurance, never surveillance. Everything shared is chosen by them, visible to them, paused in one tap.

Why I’m building it

It starts with the 11pm phone call. “Sab theek hai.” Everything is fine, and you hang up in Gurgaon, or Bengaluru, or Toronto, not quite believing it, because last month “everything is fine” turned out to include a slip near the bathroom door that nobody mentioned until the bruise had faded.

We are a generation that moved for work and stayed for life. Our parents stayed where our childhoods are. Between those two facts sits a daily worry nobody has built for: the ordinary physics of an ageing home. A wet bathroom floor. A staircase with a railing on one side. A jar that won’t open, so it gets put back.

The care is enormous. The tools are jugaad.

In the US and Japan, ageing at home is a whole category, grab bars designed like bathroom fittings rather than hospital hardware, kitchen tools built for stiffer hands. In India that aisle mostly doesn’t exist. Parwah is the aisle, plus the app that makes distance stop mattering.

Six worries, six answers

• “All is well”, daily check-in. One morning tap and the whole family breathes easy. If it’s missed, the circle knows it’s time to call, no more guessing from a thousand kilometres away.
• Know they’re okay. With their consent, the moments that matter, reached the temple, made it home, phone charged. An SOS button alerts the whole family with one press.
• Do it for them. The cab to their door, the gas refill, the plumber, the train ticket, the groceries. Booked from your phone in minutes; they get a confirmation in big, friendly type.
• Money, minus the worry. Send money in seconds, pay bills from anywhere, set a monthly allowance, and a scam shield that warns before an unknown payee gets a single paisa.
• Gifts that say parwah. Daily-living essentials chosen with dignity, bathroom safety, comfort for the knees, clever tools for stiff jar lids, delivered like family would, with a card in your words.
• Parwah AI. A voice helper in Hindi and English that does the task for them, or walks them through it step by patient step, and a real human on WhatsApp when they’d rather ask a person.

Consent is the product, not a setting

The obvious version of this app is a tracker, and the obvious version is the one families refuse. So the design constraint came first: parents are the users here, never the subject.

• Their data is theirs. Every share is chosen by them, visible to them, revocable in one tap. No ads, no data selling.
• Built senior-first. Big type, voice-first, three actions per screen. If Papa needs a manual, I’ve failed.
• A human within reach. A real person on WhatsApp, for them and for you.
• Zero miracle claims. Safety, comfort and connection for daily living. The products are not medicines and don’t diagnose anything, doctors do the doctoring, and that line is on the box, not in the footnotes.

The website is live.

Visit the working website to explore Parwah and see how it brings family care into one place.

Live in India

Parwah is a working website, and I am continuing to improve it. The name says the rest: parwah means care. Our parents spent decades showing theirs.

What it is

A global natural-disaster outlook: real-time monitoring, AI-assisted forecasting and evidence-based insights on one screen. A live map of active events, authority-sourced official warnings, hazard-by-hazard forecasts for the next 30 days, and per-region views across 195 countries.

It grades its own forecasts

Anything can produce a forecast. The interesting engineering is the machinery that makes one checkable, so the Forecast Verification Center sits on the same screen as the forecasts it is judging.

• The forecast is frozen before the window opens. Each one carries a target date and a verification window, and is graded against what actually happened.
• Five factors, stated up front. Timing, geography, mechanism, severity and official data, not a single confidence number that hides which part was wrong.
• Final grading requires meaningful impacts that match the frozen forecast, so a vague prediction cannot be retrofitted into a hit.
• The record is published, including when it is bad. A pending forecast says PENDING on the front page rather than quietly disappearing.

Eight hazards, one feed

• Live event map. Leaflet over Esri world imagery, markers coloured by alert level, refreshed every 60 seconds from a serverless events API.
• Extreme heat, flood, storm, earthquake, volcano, wildfire, landslide and drought, each filterable, each with its own 30-day outlook.
• Official warnings kept separate from forecasts. Authority-sourced alerts are labelled by agency and validity, so the reader can tell a government warning from a model.
• Alerts you can set for any country, state or city, plus historical events and location comparison.

It is not a replacement for a warning

Stated on the product, not in a policy page: forecasts support awareness and preparedness; they do not replace official government warnings. Generative tools make producing a confident claim fast and producing a false one exactly as fast, so the useful part is the bit that declines, and the disclaimer lives where the forecast lives.

What it is

Hey Yaara is an AI voice companion built specifically for elderly users. It listens, it responds in a warm conversational tone, and it does not demand the user learn anything new. No app navigation, no menus, no notifications competing for attention. You open it, you speak, you're heard.

It runs as a Progressive Web App, installable on any phone or tablet, no app store, no download friction. The interface is deliberately spare: one button to start talking, one to stop. Everything else is voice.

Why I built it

India has roughly 140 million people over 60. A huge share of them live alone, or with family members who are out of the house most of the day. The loneliness problem is well documented; the technology gap is too. Most "senior-friendly" apps still assume you know how to navigate a smartphone.

I wanted to see what a tool would look like if it started from voice first, not screen first. Something my own family members could use without me having to teach them.

What's broken without it

• Loneliness without a conversational outlet. Family calls are precious but rationed. A voice companion is always available, never tired, never busy.
• App fatigue and interface anxiety. Buttons, menus, gestures, notifications, all of it is friction. Voice removes the entire learning curve.
• The "I don't want to be a burden" problem. Many elderly users hesitate to ask family for help with small things. A neutral AI removes that emotional cost.
• Cognitive engagement. Light conversational stimulation has measurable benefits on cognitive sharpness in later years.

The roadmap in my head

Multilingual support is the most obvious next move, Hindi-first, then regional. Voice cloning so a user's children can record a "voice they recognise". Family hand-off, moments where the AI says "let me get your daughter on the line for this one".

And a hardware companion, a dedicated, always-listening, single-purpose device that doesn't require holding a phone.

What it is

MusicGenAI is an AI-powered music generation app. You give it a prompt, a mood, a genre, a theme, and it composes a full track with vocals, generated lyrics, and verified output. The whole pipeline runs end-to-end on a stack I built: React/TypeScript frontend on Vite, Supabase for storage and auth, and a Python microservice handling the vocal synthesis.

It's not a wrapper around someone else's model. It's a real composition tool with its own orchestration layer.

Why I built it

The first wave of AI music tools (Suno, Udio, others) showed what's possible, but they're all closed boxes, you get an output and you don't see the seams. I wanted to understand the pipeline by building one myself: prompt parsing, melody generation, lyric generation, lyric verification (a step most tools skip), vocal synthesis, and final mixing.

Beyond curiosity, this was a real PM exercise too, for any AI music product to be a sustainable business, you need control over the failure modes. You can't operate at scale if you don't know why a track came out wrong. Building the pipeline taught me where the failure modes actually live.

What's broken without it

• Existing tools are black boxes. When the lyrics drift or the vocal sounds off, you can't debug it. MusicGenAI exposes the stages so you can fix them.
• Lyric hallucination. Most generators will happily produce nonsense. The verification step catches and rewrites bad lines before the vocal layer runs.
• Indie creators want control, not magic. Songwriters who use AI as a co-writer need to nudge each stage, pick the melody first, then iterate on lyrics, then choose a vocal. The pipeline supports that.
• Cost transparency. Running your own stack means you know what every track costs to generate.

How it's built

• Frontend, Vite + React + TypeScript + shadcn/ui + Tailwind. Fast, type-safe, no friction.
• Auth & storage, Supabase, with row-level security so users only see their own generations.
• Vocal pipeline, Python microservice (Dockerised, runs separately) that handles the heavier audio synthesis steps.
• Lyric verification, A standalone TypeScript step that round-trips lyrics through a validation pass before they hit the vocal layer.
• Deployment, Vercel for the frontend with auto-deploy on push; Python service runs on its own infrastructure.

What it is

AI TeleSuite is a real-time AI sales co-pilot. It transcribes a sales call as it happens, scores the pitch against quality criteria, and surfaces conversion suggestions live to the operator. Think of it as a quiet voice in the seller's ear, trained on what good looks like.

This is the consumer-facing companion to a product I built at Times Internet, same philosophy, smaller surface area, designed for individual sellers and tiny teams rather than enterprise sales floors.

Why I built it

At ET, the original telesuite was for our high-volume assisted-sales channel, dozens of agents, structured scripts, mature ops layer. It worked beautifully and made the difference in scaling Assisted Sales from ₹15L to ₹80L MRR.

But the same problem exists everywhere outside enterprise sales floors: a freelancer running calls all day, a founder doing demos, a small startup with three SDRs. They have no coaching layer. Every call is solo, every mistake invisible, every win unrepeatable. AI TeleSuite is what happens when you take the enterprise version and strip it down to one user.

What's broken without it

• Solo sellers have no quality feedback loop. Big sales orgs have call review meetings; freelancers have a hopeful inbox.
• Pitch consistency is invisible. Without recording and scoring, you don't know whether your fifth call of the day is as sharp as your first.
• Wins are unrepeatable. If you don't know which sentences moved the needle, you can't double down on them.
• Coaching at scale is expensive. A senior sales coach costs $200/hour. AI can do the first 80% for almost nothing.

The roadmap in my head

The next step is integrations, pull objection responses from your CRM, post-call summaries to your pipeline, and a coaching dashboard that surfaces patterns across a seller's last 50 calls. The vision is a quiet, persistent improvement engine that runs in the background while you sell.

What it is

LifeEngine is an AI-powered wellness planner. You tell it your goals, fitness, sleep, nutrition, stress, focus, and it builds a daily plan around them, adjusting as you log progress. It's behind a login because the version of wellness advice that actually works is personal, and personal data needs to live behind auth.

It's my own take on a personal health engine, a brand-agnostic, personalised wellness companion that works for anyone, not tied to any one publisher's product.

Why I built it

I shipped Times Health+ subscriptions at Times Internet, paid wellness content for Indian users. The product works, but it has the same problem every content product has: the content is one-size-fits-all, even when the user's goals aren't.

LifeEngine is my answer to that, a personalisation layer that takes the same wellness library and routes the right pieces to the right user on the right day. I built it as a side experiment to see whether the personalisation actually does the work I expected it to.

What's broken without it

• Generic wellness content underperforms. A "drink more water" tip means nothing if the user is actually struggling with sleep.
• No accountability loop. Most wellness apps tell you what to do but never check if you did it. The engine builds in light daily check-ins.
• Subscription churn for content products. If the content doesn't feel made for you, you'll leave. Personalisation is a retention play, not a fancy feature.
• The expert in your pocket. The promise of AI wellness has always been "your own nutritionist + trainer + therapist". This is one honest attempt at the planner layer of that.

What I learned

Building the engine end-to-end forced me to confront a question I'd been ducking at work: where does AI personalisation actually create value in a content subscription, and where does it just look like value? The answer turned out to be more nuanced than the PRD I'd have written before, and that's exactly why I keep building these on the side.

What it is

The Third Eye is a personal AI operating system. One assistant, four personas, JARVIS, FRIDAY, E.D.I.T.H., ULTRON, sharing the same toolset: tasks, notes, knowledge-base RAG, web search, weather, news, stock quotes, multi-agent parallel reasoning, translation, location-aware suggestions, calendar, reminders, voice control.

The agents disagree about tone; they agree about answers. You pick the personality, you get the same capabilities underneath.

Why I built it

Every productivity tool I tried at work, Notion, ChatGPT, custom GPTs, solved one slice but never the whole loop: capture → memory → recall → action → review. So I built the loop. It runs on my own infrastructure, learns my context, and never asks me to copy-paste between tabs.

The Iron Man personas weren't a gimmick, they were a forcing function. If JARVIS, FRIDAY, EDITH and ULTRON all had to share the same backend, I had to design the backend right.

What's broken without it

• Tool sprawl with no memory. ChatGPT forgets, Notion doesn't reason, calendar apps don't notice patterns. Third Eye stitches them.
• One-time consent. Mic, location, camera, notifications, granted once via a single dialog, never asked again unless reset.
• Voice that actually works. Wake word on agent name OR "hey/hi", Web Speech STT with interim text, TTS matched to the active agent's persona.
• Multi-agent reasoning. ULTRON mode kicks off N parallel sub-agents on distinct angles of a hard question and synthesises, for strategy / pros-cons / "should I do X".

How it's built

A Next.js 14 App Router app on Vercel, Google sign-in via NextAuth (JWT), all data server-scoped through one authenticated API route, and a 7-provider LLM cascade behind every generation. The assistant is a real tool-calling agent, not a chat box.

• Agent tool-loop. /api/chat streams a Gemini function-calling loop with ~25 tools, tasks, notes, goals, knowledge search, web/news/weather/stocks, calendar, email, reminders, multi-agent reasoning, and a Studio asset generator. Sensitive actions (send email, etc.) are confirm-then-act; created items get a short-lived Undo.
• Personas that actually change behaviour. JARVIS / FRIDAY / E.D.I.T.H. / ULTRON each inject their persona into the system prompt and drive a matching TTS voice, same tools underneath, different character on top.
• RLS-safe data layer. The browser never talks to Supabase directly; every read/write goes through a session-authenticated server route using the service role scoped to the user's email, with Row-Level-Security enforced by a tracked migration. A "Cloud synced / Local only" badge surfaces the persistence state.
• Real RAG memory (Cortex). Uploaded docs and past exchanges are embedded into Supabase pgvector; the assistant does semantic recall + document search with citations, falling back to keyword search when embeddings aren't configured.
• Mode-aware runtime. A Personal / Professional / Enterprise switcher re-frames the assistant's priorities and scopes Tasks, Notes, Goals, Knowledge and Finance to the active mode, plus a Studio of per-mode generators (landing pages, HTML mailers, lifecycle plans, creative).
• Ambient capture + vision. Live Capture uses the Web Speech API to transcribe continuously, auto-extracts tasks into the tracker (with a Wake Lock so the mic survives), and Gemini multimodal analyzes a shared screen or webcam frame (E.D.I.T.H.-style). Gmail/Chat scraping turns inbox activity into tasks on a schedule.
• Agent safety layer. A global kill switch plus an append-only, exportable audit log of every action the agent takes, surfaced on a dedicated Activity page and a dashboard widget.
• Cinematic front-end. A Three.js arc-reactor hero and GSAP scroll-reveals (both reduced-motion-aware and paused on hidden tabs), a command-center dashboard where every feature is a live widget, and an installable PWA.

The roadmap in my head

Wake-word via Porcupine for true always-on, a native desktop capture bridge for background/screen-off listening (the one thing a browser can't do), dedicated audio/music generation, deeper permission tiers for the agent, and predictive routines ("you usually do X now"). Vision, wake-word-on-name and Gmail/Calendar tools are already live.

What it is

Mailer Architect turns a one-line brief into a fully designed, send-ready HTML email, copy, layout, hero, subject line, quality score. It's universal: it reads the context and writes the right kind of mailer for a company or D2C brand, a product, a school or college, an office team, an event invite, a task or submission reminder, a nonprofit appeal, anything a mailer could exist for. A six-tier LLM cascade handles failover: OpenAI → Anthropic → Gemini → xAI → Groq → Cerebras. When one provider exhausts quota, the next takes over inside the same request.

Why I built it

Every organisation sends email, not just marketing teams. Schools send notices, offices send updates, event hosts send invites, and everyone chases deadlines with reminders. Each one costs time at a blank page, and the cost of not sending is bigger than the cost of a mediocre first draft. I wanted one tool that gives a competent, on-tone first draft in under a minute for any context, and lets a human edit instead of starting from scratch.

What's broken without it

• One template for everything. Most generators only know "sales email." Architect detects the context, commerce, school, college, office, event, reminder, nonprofit, and adapts tone, structure and call-to-action to match.
• LLM single-point-of-failure. One provider's billing limit hits and your send dies. The cascade routes around it without anyone noticing.
• Blank-page cost. Three genuinely different-angle variants land in seconds, each quality-scored, so a human edits instead of writing from zero.
• Always answers. A deterministic engine ships fully designed HTML even with no API keys, the demo never returns an error.

The roadmap in my head

Saved brand kits (palette + logo) per sender, a performance dashboard, an AI-generated mailer calendar built from past sends, and automated scheduling. (In flight.)

What it is

A long-form D2C marketing landing page with an all-in-one AI agent embedded right at the top. The agent starts narrating the page aloud the moment you land (selectable British voices, with play/pause and mute), holds a two-way voice conversation when you tap Talk, answers typed questions in chat, and runs a "help me choose" recommendation flow, all four sharing the same page context, so every answer is grounded in what the page is actually selling.

Why I built it

D2C landing pages are monologues, thousands of words of persuasion with no way for the visitor to ask the one question actually blocking the purchase. The best-converting sales channel is still a human who explains, listens, answers and recommends. I wanted the page itself to behave like that salesperson, without making the visitor read a word if they'd rather just listen and talk.

What's broken without it

• Reading is friction. Most visitors skim 20% of a long-form LP. Auto-narration delivers the full pitch hands-free, the way a podcast does.
• Questions go unanswered. Objections, "will this work for me?", "how is it different?", normally send visitors to Google and they don't come back. Voice and chat answer them in the moment, on the page.
• One-size pitch. "Help me choose" turns a static offer into a guided recommendation tied to what the visitor actually needs.
• Four vendors, one widget. A narrator, a voice agent, a chatbot and a recommender are normally four separate tools with four contexts. Here one agent shares state, content and controls.

The roadmap in my head

Conversion attribution per interaction (do narration listeners or talkers buy more?), scroll-aware narration that follows the section you're reading, multilingual voices for other markets, and piping conversation transcripts into a lifecycle/retention dashboard as objection-mining data for the next campaign.

What it is

JobHunt is a free, live job-search tool. You sign in with Google, type a role and (optionally) a location, and it pulls current openings from free, keyless public job boards, Remotive, RemoteOK, Arbeitnow and The Muse, matches them to your query, de-duplicates, and hands back each with a direct link to apply. No spreadsheet, no workflow to import, no API key: just type and search.

Why I built it

Job hunting means checking board after board, copy-pasting listings, and losing track of what you've already seen. I wanted a single box where you describe the role once and the tool does the scanning for you, pulling live, real postings from several boards at once and showing them cleanly so you can go straight to applying.

Under the hood

• Gated by Google sign-in. Access runs through Supabase auth, so the tool is tied to a real Google account, light protection against abuse.
• Free public job APIs. A Vercel serverless function queries several free, keyless job boards (Remotive, RemoteOK, Arbeitnow, The Muse) in parallel at request time, no paid key, no per-minute rate limit to hit.
• Matched to your role. Results are title-matched to what you searched, de-duplicated across boards, and each carries a company, location, source and a direct apply link.
• Genuinely free. No API key anywhere, visitors never need one and there is nothing to install or run out of.
• Results you can act on. Every opening opens straight to the original posting in a new tab, so you go from search to apply in one click.

What matters most

Every listing comes straight from a real job board's own API, nothing is invented, and always links back to the original posting to confirm before applying. Because it's public, it's gated behind sign-in, so it stays honest, free and abuse-resistant.

The roadmap in my head

Saved searches and email alerts for new matches, more boards and region filters, salary and seniority signals, a "tailor my application" handoff that drafts a role-specific resume and cover letter, and a lightweight tracker so you can mark what you've applied to, all while keeping the one-box, sign-in-and-search simplicity.