Shell scripts are the highest-ROI layer under your AI skillsThe glamorous layer is the agent. The load-bearing one is the boring shell script underneath — and that's where most of your reliability actually lives.6 min read·blog.deepakgoyal.aiAug 10
Deterministic context beats generated context — when structure existsThe prompt is only about 10% of what your LLM actually sees. Most of the other 90% is context you assemble — and when your data has structure, you should build it with code, not another LLM call.12 min read·blog.deepakgoyal.ai12KAug 6
I stopped being my second brain's schedulerCadences that surface what's due, habits that flag a slipping streak, and a live HUD that watches the vault — and it ships without a single background cron. SMRITI v2.1.10 min read·blog.deepakgoyal.ai1Aug 2
Building Production RAG on ArXiv — Part 1: Architecture & IngestionI'm building an open-source system to interrogate the AI-research firehose — RAG now, a multi-agent researcher by the end, in public over five parts. Part 1 is the foundation: the architecture, the ingestion, and the eval bug that would have shipped meaningless numbers.18 min read·blog.deepakgoyal.ai42KNJul 30
Sub-Agents Lie About Finishing — and the Fix Isn't a Better PromptA sub-agent that writes to your system will tell you it succeeded. It's reporting what it intended to do, not what actually landed — and the gap is where silent data corruption lives.6 min read·blog.deepakgoyal.aiJul 15