# Jobs for your agent, one prompt each.

Source: https://corespeed.io/use-cases

CoreSpeed use cases are jobs you hand to the agent you already use, written up so you can run them today. Each page names the job in one line, gives you one prompt to paste into Claude Code, Codex or Cursor, lists the tools it calls, and links the post that explains it at length.

- [Competitive research](https://corespeed.io/use-cases/competitive-research) (Markdown: https://corespeed.io/use-cases/competitive-research.md): Competitive research with an agent is two steps: find sources, then read the few that matter. Your agent searches the web with web__search, reads pricing pages and changelogs with web__scrape, and writes a one-page brief to Notion with a source on every claim. No search provider account is needed; each call is priced in credits.

## Questions

### Does the prompt work on a machine without CoreSpeed?

Yes. It starts with the setup line, so a new agent adds CoreSpeed and signs you in first. On a set-up machine it goes straight to the job.

## Related pages

- [Glossary: the words of AI agents at work](https://corespeed.io/glossary): Short definitions of the words teams meet when they give AI agents real work, each resting on a page of the CoreSpeed documentation.

Reviewed 2026-11-10.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)