What we build with large language models
Generative AI is easy to demo and hard to ship. A demo answers three questions well. A product has to answer ten thousand, show where each answer came from, refuse what it should not answer, and cost less to run than the person it helps.
We have shipped this for our own products. Crodo answers questions about whatever is on your screen and takes actions in your apps. Building it taught us more about search, speed and cost than any client brief could, and that experience goes into your project.
How an LLM app is built
Our LLM app development process
- Discovery, week 1. Which questions, which documents, which users. We collect a sample and write the first fifty test questions with you.
- Prototype, weeks 2 to 3. Search and answers on your real documents, scored against the test questions. We compare two or three models on quality, speed and cost.
- Build, weeks 4 to 10. Permissions, the interface inside your tools, cost controls, monitoring and weekly demos.
- Run. Quality dashboards, a monthly review of wrong answers, and improvements on a retainer or a full handover.