# eStreetz

> eStreetz Technologies is an AI-native product and engineering company in India. We build AI agents, workflow automation and custom software, and make EQO (personal AI agent) and Uniwork (business OS). Enquiries: naveen@estreetz.com

## Pages

- [Home](https://estreetz.com/index.md): Who we are, what we build, how to work with us
- [Blog](https://estreetz.com/blog/index.md): All posts
- [Cookie policy](https://estreetz.com/cookies.md): What we store and why

## Blog

- [Claude, GPT, Gemini. What we actually reach for, and why.](https://estreetz.com/blog/claude-gpt-gemini.md): 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): 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): 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): 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): 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): Not every AI feature needs a frontier model. A few jobs we moved to open models on Cloudflare, and a few we moved back.

## Optional

- [Everything in one file](https://estreetz.com/llms-full.txt)