I turn a messy idea into a product that ships.
I'm Aniket — a technical partner for founders who don't have a tech team, and SaaS teams who need AI done properly. I built an entire AI SaaS product solo — front end, back end, infrastructure, every AI feature — and spent 15 years shipping production software for teams across Europe. If you have the idea, the customers and the business knowledge, I bring the team.
Two ways to work with me.
You have the idea, the customers and the business knowledge — not the engineers. I work as a fractional CTO: architecture, build, and ship the whole product, AI included.
You already have a product and a team. You need OpenAI or Claude built into it properly — chat, document processing, structured extraction, RAG, agents — without breaking what's already shipping.
An AI business-strategy platform, built solo.
Vizologi helps founders and analysts reason about business models with AI. I designed and built the whole product — front end, back end, infrastructure, and every AI feature in it.
Three AI features, one engineer, running in production.
Each of these is a distinct pattern I designed, built and keep running against real usage — with the cost control, queuing and failure handling that separate a feature that ships from one that stalls in a notebook.
Ask in plain language
A question about companies or markets pulls the right records from the database and answers with generated charts and cited sources.
Autopilot pipeline
One short prompt fans out through a sequenced, queued pipeline to produce a full business model canvas, SWOT and PEST analysis.
Instant company breakdown
From just a company name and URL, generate a structured business-model overview in seconds — bounded to stay useful, not generic.
Under the hood — Node.js + MongoDB Atlas · asynchronous job queues for the multi-step pipelines · source-grounded retrieval · and model/token-cost tuning worked out against real production limits (smaller models that finish structured output where larger ones truncate). Currently extending retrieval from keyword to vector/hybrid search.
Real-time product configurators, in the browser.
Interactive 3D for physical products — customise a product and watch it update live. Built with Three.js on the front end and Blender Python scripting to generate the geometry. Few AI engineers ship this; I've shipped three.
- 01 Ice-pop configurator Three.js · Blender
- 02 Chocolate configurator Three.js · Blender
- 03 Shoe-outsole configurator Three.js · Blender
drag to rotate · three.js
What I actually do.
Next.js front ends, Node.js backends, Postgres/MongoDB, Stripe billing, multilingual systems — the whole product, when there's no team to hand it to.
OpenAI and Claude wired into an existing product — chat, RAG, structured extraction, agents, workflow automation — built to run in production, not a notebook.
n8n workflows, Odoo, and the legacy systems a business already runs on — wired together instead of ripped out and replaced.
Interactive configurators with Three.js and Blender — real-time geometry in the browser, generated from parametric models.
A technical partner for founders who don't have — or don't need — a full engineering team.
I take a business problem and own it end to end: architecture, build, integrations, and the AI layered on top. Not a spec handed to a team — the whole thing, shipped, by one person who's done every layer before.
Based in Goa, India, I've run production software for teams across Europe for over a decade — SaaS products, AI integrations, automation, payments, multilingual systems, and the legacy code most people won't touch. I care about the boring parts — the queue that doesn't drop jobs, the cost that stays predictable, the deploy that comes back up.