How to build agents with filesystems and bash - Vercel
vercel.com · 1,070 words · saved by 1 readers
How to build agents with filesystems and bash, production agents, context management, template, bash
The best agent architecture is already sitting in your terminal Many of us have built complex tooling to feed our agents the right information. It's brittle because we're guessing what the model needs instead of letting it find what it needs. We've found a simpler approach. We replaced most of the custom tooling in our internal agents with a filesystem tool and a bash tool. Our sales call summarization agent went from ~$1.00 to ~$0.25 per call on Claude Opus 4.5, and the output quality improved. We used the same approach for d0 , our text-to-SQL agent. The idea behind this is that LLMs have be
saved by
related reading
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Ampampcode.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Building reliable AI agents · parth sareenparthsareen.com
- Arjun Virkarjunvirk.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Dynamic context discovery · Cursorcursor.com
- Agent-native Architecturesevery.to
- LangChain: the open agent platform to own your intelligencelangchain.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com