Engrain by ByteRush

AGT.08 3 concepts

Durable execution, human-in-the-loop and memory

Build long-running, reliable agents that people can supervise.

  1. AGT.08.01Durable executionCoreSeniorBeing written
  2. AGT.08.02Human-in-the-loopCoreMid-levelBeing written
  3. AGT.08.03Memory for agentsSeniorBeing written

Interview questions in this module

  1. How do you make a long-running agent survive crashes and deployments?
  2. When should an agent ask a human for approval?
  3. How would you give an assistant long-term memory? What can go wrong?