Agents Are Databases in Disguise
AI agents face the same challenges as databases and workflow engines. Here's why treating agent memory like a proper data system unlocks reliability.
LLMs Databases Durable Execution
Read more →
Blog
Technical insights on machine learning, MLOps, AI engineering, and software development. Sharing practical experiences and deep dives into the latest trends in tech.
Browse by Series
The Death of Syntax: Why Code is Becoming the New Assembly
We are witnessing a phase transition in software engineering. Code is becoming a transient artifact, bytecode generated by AI compilers. The future belongs to Architects of Intent, not writers of loops.
Claude Code Cursor Windsurf
Read more →
Ambient AI: Building Torale from Complexity to Simplicity
The evolution from overengineered web scrapers to grounded search APIs, and what it takes to make information truly ambient. A technical journey through V1's failure, Gemini's unlock, and shipping a production monitoring platform.
Torale Gemini Claude Code
Read more →
Why Your ML Infrastructure Choices Create (or Kill) Momentum
How early architectural decisions create a flywheel effect that accelerates rather than hinders your path to production. Discover the Nimble Flywheel framework for scaling ML from prototype to production.
Infrastructure Production
Read more →
Modern ML Cookiecutter Template
From dependency hell to device confusion - I built a modality-aware cookiecutter template that gets you from idea to training in minutes, not hours. Here's why modern ML projects need modern tooling.
uv Polars LitServe
Read more →
30 Days of Claude Code: How I Became More Productive and Worse at Programming
A month-long experiment with Claude Code that replaced Instagram reels with AI-powered coding sessions. How I shipped more projects than ever before while paradoxically becoming worse at programming from scratch.
Claude Code GitHub AI Tools
Read more →
Stop Training and Praying
Master efficient ML development with the Pre-Flight, In-Flight, Post-Flight framework. Learn how to catch bugs before expensive training runs, monitor training in real-time, and evaluate models beyond vanity metrics. Stop wasting millions on failed ML experiments.
GPU Training Model Evaluation Data Quality
Read more →
What If AI Agents Could Fix MLOps Forever? A Thought Experiment
A wild 2 AM thought experiment: What if AI agents could orchestrate your entire MLOps stack through MCP? From data drift to deployment, explore the future of autonomous ML operations.
MCP ClearML MLflow
Read more →
A Builders's Guide to the Agent2Agent (A2A) Protocol: The Universal Language for AI Collaboration
Master the Agent2Agent (A2A) Protocol! Learn how Google's open standard enables secure AI agent communication, discover vs MCP differences, explore authentication, monetization, and orchestration. Complete Python examples included.
A2A Protocol MCP OAuth
Read more →
The Great Rewiring: A Product Builder's Guide to the Converging Tech Shifts Defining the Next Decade
Explore six pivotal technological shifts - Autonomous Economy, Radical Abstraction, Modularity & Composability, Ecosystem Dynamics, Ambient Intelligence, and Next-Gen UX - that are converging to reshape our digital future. A strategic framework for product builders.
IoT Ambient Intelligence Product Strategy
Read more →
Agents Assemble: The New Fragmentation in AI Agent Frameworks
Dive into the AI agent framework wars! Compare OpenAI, Google ADK, AWS Bedrock, Smol Agents. Explore multi-agent systems & future trends. Expert analysis.
OpenAI Google ADK AWS Bedrock
Read more →
Experiments as First-Class Citizens
Stop treating ML experiments as disposable! Learn why elevating experiment tracking to first-class infrastructure is crucial for robust MLOps, reproducibility & Software 2.0.
Experiment Tracking Reproducibility
Read more →
Navigating the Modern Landscape of Machine Learning Training Infrastructure
A comprehensive overview of modern ML training infrastructure, covering cloud agnosticism, spot instances, on-premise solutions, heterogeneous hardware, distributed training, and emerging GPU cloud providers.
Skypilot Distributed Training GPU Cloud
Read more →
When (and How) to Invest in MLOps at Your Startup
A practical guide for startup founders on when and how to invest in MLOps - from early stage flexibility to scaling infrastructure, with key principles and pitfalls to avoid.
Model Deployment Data Pipelines Observability
Read more →
Building Tech Products for India: A First-Principles Playbook
Explore why building tech for India means rethinking everything from the ground up—addressing local habits, scale, price sensitivity, and cultural diversity with first-principles design.
India Product Localization Digital India
Read more →
The Emergence of the full stack ML engineer
The history of Full stack, Machine learning which results in the mergence of the ML full stack engineer
Full Stack Cloud Infrastructure
Read more →
Machine learning ain't Javascript
Problems in the ML ecosystem. Fragmentation in machine learning, that keeps preventing the stack from growing higher. How I took a stab at the issue.
PyTorch Ecosystem Fragmentation
Read more →
Pipenv and Pyenv - The Python Productivity Combo
A guide to setting up a productive Python environment using Pipenv and Pyenv
Pipenv Pyenv
Read more →