# eStreetz blog

- [Claude, GPT, Gemini. What we actually reach for, and why.](https://estreetz.com/blog/claude-gpt-gemini.md) (Balaji B, 2026-10-14): A working team's notes on model choice in late 2026. Less leaderboard, more "which one do we open when a client calls on a Tuesday".
- [We cut our Claude bill roughly in half. Here's the boring list.](https://estreetz.com/blog/cut-claude-bill.md) (Naveen, 2026-10-09): No clever tricks. Prompt caching, a shorter CLAUDE.md, cheaper models for the grunt work, and the batch API for anything nobody is waiting on.
- [Your agent doesn't need 40 tools](https://estreetz.com/blog/agent-40-tools.md) (Balakrishna, 2026-09-22): We gave an agent every API endpoint we had. It got slower, more expensive and more confused. What we do now instead.
- [RAG is mostly a search problem](https://estreetz.com/blog/rag-is-search.md) (Balaji B, 2026-08-27): When a "chat with your documents" project gives bad answers, the model is usually fine. The search in front of it isn't.
- [The checklist we run before an AI feature ships](https://estreetz.com/blog/eval-checklist.md) (Naveen, 2026-08-06): It fits on one screen. It has saved us from at least three embarrassing launches.
- [Cheap models at the edge. When Workers AI is enough.](https://estreetz.com/blog/workers-ai-enough.md) (Balakrishna, 2026-07-18): Not every AI feature needs a frontier model. A few jobs we moved to open models on Cloudflare, and a few we moved back.