[](https://devin.ai/blog)

# What "Copilot for X" Really Takes

CognitionDecember 20, 20221 min read

We recently had the opportunity to collaborate with Shawn “[swyx](https://twitter.com/swyx)” Zhang to share some of our learnings so far (from building Codeium) that would generalize to anyone interested in building their own “Copilot for X” product.

The TL;DR is that to build a “Copilot for X”, you must:

- **Estimate inference scale**: By reasoning about the tradeoff between latency and output quality
- **Build first party**: Third-party APIs will wreck your unit economics
- **Figure out Realtime Infra**: ChatGPT, Dall-E, etc are too slow to keep flow
- **Optimize prompts**: Context window is limited; what info most improves output?
- **Merge model outputs and UX**: Raw model output is unintuitive; long tail of UX.

[Read the whole post](https://lspace.swyx.io/p/what-building-copilot-for-x-really) on swyx’s L-Space Diaries newsletter!