DGDeepak Goyalinblog.deepakgoyal.ai·2h ago · 6 min readShell scripts are the highest-ROI layer under your AI skillsShell scripts are the highest-ROI layer under your AI skills The glamorous layer is the agent. The load-bearing one is the boring shell script underneath — and that's where most of your reliability ac00
DGDeepak Goyalinblog.deepakgoyal.ai·3d ago · 12 min readDeterministic context beats generated context — when structure existsDeterministic context beats generated context — when structure exists The prompt is only about 10% of what your LLM actually sees. Most of the other 90% is context you assemble — and when your data ha12K
DGDeepak Goyalinblog.deepakgoyal.ai·Aug 2 · 10 min readI stopped being my second brain's schedulerI stopped being my second brain's scheduler Cadences 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.10
DGDeepak Goyalinblog.deepakgoyal.ai·Jul 30 · 18 min readBuilding Production RAG on ArXiv — Part 1: Architecture & IngestionBuilding Production RAG on ArXiv — Part 1: Architecture & Ingestion What I'm building, and why Nobody can keep up with AI research anymore. On ArXiv — the open-access preprint server where nearly all 42KN
DGDeepak Goyalinblog.deepakgoyal.ai·Jul 15 · 6 min readSub-Agents Lie About Finishing — and the Fix Isn't a Better PromptA sub-agent on my system reported — cheerfully, in detail — that it had closed six stale tasks. It named each one. It summarized the work. All six were still sitting there, open and untouched. Nothing00
