Knaph

Briefing an agent

Handing over a task so an agent can do it without guessing - the goal and why, the context it can't know, what done looks like and how to check it, and what's off limits - sized to fit how agents work (plan first for big jobs, one task per session).

Depth 1 · Foundation

You can write a brief with a goal, the context it needs, a checkable definition of done and limits, and explain why each part matters.

Sign in to prove what you know with a short quiz, see how deep you've gone, and earn XP for it.

Sign in with Google

Depths of understanding

  1. 1

Your path here

What's still between you and Briefing an agent, depth 1, in the order you can learn it.

  1. 1Language modelDepth 1 · Foundation · Language Models
  2. 2AI agentDepth 1 · Foundation · AI Agents
  3. 3TokenDepth 1 · Foundation · Language Models
  4. 4ProbabilityDepth 1 · Foundation · Probability
  5. 5Next-token predictionDepth 1 · Foundation · Language Models
  6. 6Stateless modelDepth 1 · Foundation · Language Models
  7. 7Context windowDepth 1 · Foundation · Language Models
  8. 8System promptDepth 1 · Foundation · Language Models
  9. 9Tool useDepth 1 · Foundation · AI Agents
  10. 10Agent loopDepth 1 · Foundation · AI Agents
  11. 11Agent harnessDepth 1 · Foundation · AI Agents
  12. 12Agent permissionsDepth 1 · Foundation · AI Agents
  13. 13Planning before actingDepth 1 · Foundation · AI Agents
  14. 14BeliefDepth 1 · Foundation · Epistemology
  15. 15KnowledgeDepth 1 · Foundation · Epistemology
  16. 16TestimonyDepth 1 · Foundation · Epistemology
  17. 17Checking an agent's workDepth 1 · Foundation · AI Agents
  18. 18Briefing an agentDepth 1 · Foundation · AI Agents

Where it fits