Thoughts on AI, system design, and building with emerging tech.https://blog.jainamshah.workers.dev/https://blog.jainamshah.workers.dev/blog/benchmark-naive-vs-optimized-prompts/https://blog.jainamshah.workers.dev/blog/benchmark-naive-vs-optimized-prompts/I benchmarked naive vs optimized prompts across 10 roles with PromptFoo. Sales jumped 3.02→7.86. Legal hit 410s latency. Cost is not quality.Thu, 09 Apr 2026 00:00:00 GMTJainamhttps://blog.jainamshah.workers.dev/blog/data-engineers-mcp-toolbox/https://blog.jainamshah.workers.dev/blog/data-engineers-mcp-toolbox/MCP servers fail in production not because models are weak, but because they lack the context human engineers rely on. Here is how to fix that.Sun, 15 Feb 2026 00:00:00 GMTJainamhttps://blog.jainamshah.workers.dev/blog/end-of-cheap-tokens/https://blog.jainamshah.workers.dev/blog/end-of-cheap-tokens/AI compute is becoming a perishable resource. From the Qwen moment to Provisioned Throughput — how AI billing is evolving like airline tickets.Sun, 01 Mar 2026 00:00:00 GMTJainamhttps://blog.jainamshah.workers.dev/blog/llm-wiki-access-problem/https://blog.jainamshah.workers.dev/blog/llm-wiki-access-problem/I built a wiki that auto-captures every Claude session. Getting other tools to read it required treating the wiki as a server, not a folder.Tue, 14 Apr 2026 00:00:00 GMTJainam