Campaign landing
AI agents and multi-agent harnesses
A successful tool call does not mean a successful task. Production agents need task-level success criteria, not only step-level telemetry.
Agents look fast in demos and still fail in production. Loops, invented tools, missing approval gates, and silent side effects show up the moment real users and real permissions arrive.
Why common approaches fail
Most teams ship a prompt plus a tool list. That skips the harness: role boundaries, tool registries, egress controls, eval gates, and operator handoff. A successful tool call is treated as success even when the task is unfinished.
Related failure modes
Evidence
Full capability write-up: AI agents and multi-agent harnesses.