Sign in Try Core free

Reference

How To Use Core

Back to setup docsRaw source

Paste this into your agent

Start with this visible request when you want the agent to help. It keeps the action coming from you, while the linked setup reference stays plain and non-recursive.

Use this in the app you are connecting, then approve only the browser login, app setting, or restart steps that the app requires.

Please help me set up Core for this agent. Core keeps shared context for AI work: it preserves useful context, decisions, files, and what worked across connected tools.

Use this official setup reference:
https://core.gradien.ai/core/docs/reference

Use Core by continuing normal work in the AI tool you already use. The difference is that the agent can read visible Core context before it starts and save useful work back when it finishes.

Daily loop

  1. Ask the AI tool to load relevant Core context for the task.
  2. Do the work in the tool or agent harness you already use.
  3. Review the result and decide what should be kept.
  4. Save the accepted output, decision, source note, or next action back to Core.

Good prompts

  • Pick up this project from the current Core context.
  • Prepare a client update from the sources and decisions attached to this workflow.
  • Save the final decision and next action to Core after I approve them.
  • Search Core for prior context before drafting.

What to avoid

Do not treat Core as a dumping ground for every artifact. Keep context tied to a real workflow, source, person, decision, or next action.

Next docs