Kong co-founder Marco Palladino discusses recurring agent workflows, delegationAI agent delegation assigns a bounded task, context, authority, and expected result from one participant to an agent or another agent. and the difficulty of verifying tasks that lack clear success criteriaAn acceptance criterion is a specific condition that must be satisfied before a software change or task can be considered complete.. He describes the risk of loops consuming resources without reaching completion.
Marco Palladino argues that organizations need visibilityAI agent observability makes an agent's state, actions, tool use, failures, resource use, and outcomes visible enough to understand and operate it., bounded permissions and ways to assess outcomes as agents act. He also predicts that documentation and agent-readable services will matter more as agents make more software decisions. His claims and forecasts are presented as his perspective; Kong is a show sponsor.
Watch on YouTube
