Viewpoint
Full agent traces should include tools and sub-agents
Full agent traces should include tools and sub-agents
Karanam argues that companies should trace the complete execution tree, including tool calls and sub-agents, because omitting those steps makes it difficult to learn from the full interaction.
- Speaker
- Arjun Karanam
- Topic
- Agent Traceability
- Source timestamp
- 3:20
More from this interview
- AI progress needs experience alongside model intelligence
- Agent interactions should become signals for future improvement
- Continual learning can create systems that compound with use
- Feedback should update either models or their surrounding harness
- Corrective behavior provides richer feedback than simple ratings
- Evals should closely reflect real production usage
- Agent tasks should be replayable for evaluation
- Harnesses should enable orchestration instead of rigid workflows
- Agents should access the same capabilities as users
- Tool responses should expose informative execution details
- Open weights enable companies to continually improve owned models
- Model routers can match intelligence to task requirements
- Continual learning should optimize the whole intelligence system
- Learning can avoid direct training on customer data
- Corrective feedback gives stronger reward signals than dissatisfaction
- Feedback scope determines where learned information should live
- Continual learning is most compelling near capability frontiers