Posts
All the articles I've posted.
How can coding agents be used productively in software development?
Deploying coding agents productively requires shifting from conversational, chat-based code generation to harnessed agentic systems.
How to Provide the Right Context Through Rules, Skills, MCP, and Hooks, How to Evaluate Modularization with AI and Architecture Tools, and How to Use Deterministic Checks as Guardrails for Coding Agents
Building reliable AI coding workflows requires treating the model not as an omniscient engineer, but as a probabilistic reasoning engine bounded by deterministic guardrails, structured interfaces, and dynamic context injection.
Decoding AI Your 2026 Glossary to the Latest Buzzwords
It feels like overnight, the world started speaking a new language. If your inbox, newsfeed, and meetings are suddenly flooded with acronyms like LLM, RAG, and GenAI, you aren't alone. As artificial intelligence continues to evolve at breakneck speed, keeping up with the terminology is half the battle.
Agent loop to handle Angular upgrades on a 3–6 month
I’ve experimented with an unattended agent loop for Angular upgrades. suppose to run every 3/6 month. It runs ng update, uses AI for up to 3 remediation cycles, runs the final tests and opens a PR. It worked quite well for minor upgrades package updates, migration cleanup, etc. But for 2–3 version jumps, the first PR was pretty rough some package mismatches it couldn’t resolve, and a bunch of warnings pushed into the PR description instead of actually fixing the issues. For verification I checked the description it updated action items for dev to pick up if any.