Blog / Thoughts¶

Recursive Summarization Unlocks Effective LLM Integration in Healthcare

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.

How Claude Code Made Me Fall in Love with the Terminal

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 Gave Engineers 20 Hours Back Per Week. Why Aren't We Shipping Faster?

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?

Can we reverse the curse of rigid journeys & workflows with LLMs?

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.

Cognitive Architecture Patterns in Health Care for LLMs

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.

Is Your Security Posture Holding Your Healthcare Startup Back?

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.

Does Your Startup Really Need Complex Cloud Infrastructure?

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 in 2024

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.

How LLMs Revolutionized My Productivity

In the ever-evolving landscape of LLMs, I've observed two distinct camps: the doomsayers who predict a dystopian future and the overly optimistic who claim AI has completely transformed their lives overnight. As for me? I find myself somewhere in the middle – cautiously optimistic about the technology's potential while actively seeking ways to harness it for practical, everyday use.

From Concept to Production with Observability in LLM Applications

Understanding observability in AI applications, particularly in Large Language Models (LLMs), is crucial. It's all about tracking how your model performs over time, which is especially challenging with text generation outputs. Unlike categorical outputs, text generation can vary widely, making it essential to monitor the behavior and performance of your model closely.