Your coding agent keeps solving the same problem
DeepLearning.AI launches course teaching agents to learn from past sessions via behavioral and knowledge adaptation
“they can run into same problems again and again because they don't remember what they learned yesterday”
DeepLearning.AI, in partnership with Oracle, launched a course on building adaptive AI agents that retain knowledge across sessions via two mechanisms: behavioral adaptation (converting traces into reusable skills) and knowledge adaptation (code knowledge graphs). The course addresses a core limitation of current agents—stateless sessions that waste tokens re-solving identical problems. This is a practical engineering education signal rather than a major industry announcement.