Percorsi
Agent design
Planning loops, tool contracts, stop conditions, and human supervision for autonomous workflows.
Blog
3 note di implementazione in questa traccia.
Agentic systems
Why agentic systems need escalation design
Autonomy without escalation policy turns small errors into operational incidents.
8 minimo letto
Agentic systemsDesigning tool contracts for reliable agent actions
Typed tool interfaces reduce hallucinated actions and make retries safe.
7 minimo letto
GovernanceEvidence packets for human approval
Approval flows work when reviewers get concise context, not raw transcripts.
6 minimo letto
Base di conoscenza
2 riferimenti in questa traccia.