Following are my personal thoughts on tech, AI, startups and adoption of AI in Health-Care. You could read more about me here
User asks an AI data analysis tool: "Pull all patient communication encounters from last month."
The AI confidently writes a SQL query, hits the encounters table directly, and returns 1,247 records. AI confidently answers that. Three days later, you discover the actual number should have been 3,891, because the real path is patients → patient_queue → queue_encounters → encounters. The AI missed two-thirds of your data.
Every care team we talk to has the same complaint: patients happily text, leave voicemails, and fill out surveys, but those signals rarely make it into the plan of care.
Electronic records were never built to absorb that ambient context, and the people who could act on it are already drowning in portal messages and follow-up calls. Yet the value is obvious, timely symptom reporting keeps people out of the ED, surfaces social needs, and lets providers adjust therapy before a flare turns into a crisis.
What we need is a stack that captures self-reported data, triages it with large language models, and still gives clinicians the last word. The winning pattern blends thoughtful UX, observability, and a human-in-the-loop workflow.
Your patient has 247 pages of medical records spanning 8 years. Two ER visits, three specialists, ongoing knee osteoarthritis, recent ACL reconstruction. How do you create a coherent summary that preserves critical information while making it digestible for both clinicians and AI systems?
The answer isn't just summarization, it's recursive summarization. And the secret isn't just what you summarize, but what you choose to preserve at each level of abstraction.
Like many of you, I recently made the full switch from Cursor to Claude Code. This transition marked more than just a tool change – it fundamentally transformed how I think about development environments.
For years, I lived in VSCode (recently Cursor), relying heavily on mouse navigation and minimal keyboard shortcuts. I resisted the pull of Neovim and keyboard-centric workflows. But after embracing Claude Code, I discovered something profound: the terminal is the new IDE. You can run it everywhere with a consistent workflow – be it a Linux box, your Mac, or a VPS. That's all you need.
AI has compressed time in my life. This time compression has unlocked a lot, but perhaps not in the ways you'd expect.
Nothing you don't already know, right?
Healthcare is littered with brittle decision-trees. Pre-op instructions, chronic-care check-ins, discharge follow-ups—each new edge-case multiplies the branches. Most workflows we have are cron-based, running at specific times and are very hard to personalize around patient needs.
We're inspired by the ideas from this Cognitive Architecture paper and an insightful Langchain Blog by Harrison Chase.
At RevelAI Health, we're exploring how to create closed-loop, safe agents in healthcare — systems that can reason and execute on patient needs in a secure and reliable way. The key is understanding how these agentic systems should think, the flow of execution in response to patient intent, and ensuring safety through structured, observable loops.
When deploying a healthcare product, HIPAA compliance is crucial. No matter how innovative your solution is, without convincing the CIO or security team, you won't get deployed. I view security and HIPAA posture as essential features of any healthcare product.
I recently listened to Pieter Levels on the Lex Friedman Podcast, and it was eye-opening. Pieter has built numerous successful micro-SaaS businesses by running his applications on single server, avoiding cloud infrastructure complexity, and focusing on what truly matters: product-market fit.
My desk setup as of writing this post. I've been working from home for the past 1 year and have been slowly evolving my setup to be more ergonomic and efficient.
Also, I want to use this blog to track changes for my setup over time and share with fellow devs / team-mates.
