Following are my personal thoughts on tech, AI, startups and adoption of AI in Health-Care. You could read more about me here
2026 is the year of customized agent harnesses. Not generic chat. Not another SaaS with an AI button. Thin, opinionated agents wrapped around a specific job.
I just open-sourced Byaan, a local data agent harness I have been using daily for a few months and building all along. Site is at byaan.ai.
I do not think AI will replace every app with one giant productivity blob.
I do think AI changes something more interesting: it makes small, personal software worth building again.
There are places where I still want real software. Finance, healthcare, taxes, legal work, anything with consequences. I do not want a loose chat interface guessing its way through that. I want software with a database, a model of the domain, boring reliability, and a clear relationship with the data.
AI is useful there, but only when it sits on top of a system I trust.
That is why I built Fino, a local-first personal finance app that lets me connect my bank accounts, import the accounts Plaid misses, and then talk to my money from Claude.
Not "chat with a spreadsheet" as a demo. More like: "why did our spending feel weird this month?" and then getting an answer from my actual transactions, local rules, savings goals, recurring subscriptions, and financial memory.
I do not think AI will replace every app with one giant productivity blob.
I do think AI changes something more interesting: it makes small, personal software worth building again.
I have been building a lot with Claude recently. Obviously, you can ship code very quickly now. But how do you plan large features, understand UX, brainstorm different patterns, and then ship across 3 repos in an established codebase without breaking things?
The goal is to put large features in front of customers in weeks, not months. Test your assumptions and iterate on top of real feedback.
Like many of you, this tweet from Andrej Karpathy is what pushed me to actually try this. The whole post is worth reading, but the core idea:
I spent last night configuring Claude Code's security and realized something uncomfortable: for months, I had been running an LLM with unrestricted access to my terminal. It could read my SSH keys, browse my AWS credentials, curl data to any endpoint, and push code to production. I just never thought about it because the tool was helpful and nothing bad had happened yet.
That is exactly the kind of reasoning that gets production databases dropped.
Your AI can write SQL. It just has no idea what the data means.
I have spent the last four years building AI products in healthcare. Our databases have columns like amt_1, stat_cd, eff_dt. A model looking at raw schema has no way to know that amt_1 is patient copay in one table and coinsurance in another. That stat_cd means enrollment status, not statistical code. That eff_dt is the date a policy became active, not when something happened.
This is tribal knowledge. It lives in the heads of the three people who built the database. It is not documented anywhere. And it is the reason text-to-SQL fails in production.
There's a lot of hype around Clawdbot. People claiming it'll make you a billion dollars, automate your business, act as your chief of staff. And yes, it's also a security nightmare.
But there's something real here. Clawdbot (now renamed Moltbot) is pointing toward a fundamentally different relationship with AI. Not a chat window you visit, but a system running on YOUR machine, 24/7, on your infrastructure, with your files. AI in a box.
These are the principles we follow at RevelAI Health. They've shaped how we build and ship. Might be useful for other early to late stage startups too.
I started with Zellij. The learning curve was low, commands were intuitive, and I adopted it quickly. Since I've abandoned IDEs for the terminal, having a solid multiplexer was essential.