AI Agent Manager
This lab was presented at WSO2Con Africa 2026.
Presenters:
Asanka Abeyweera, Associate Director - Head of Product Management & Architecture, Agent Platform BU, WSO2
Viggnah Selvaraj, Lead Sales Engineer, WSO2
Getting an AI agent to work is only the start. Once it runs, you need to show exactly what it said and why, keep compliance rules in force across agents built by teams that have never met, tell whether quality is improving or slipping, and make sure each agent reaches only the systems it needs.
This hands-on tutorial is about operating agents, not writing them. Using WSO2 Agent Manager, an open control plane for deploying, observing, evaluating, and governing AI agents built with any framework, the presenters take one working agent through the controls an enterprise expects before it goes near real users and real data.
You'll see how to:
- Deploy an agent and move it between environments from one place
- Enforce guardrails and policy centrally, instead of leaving correct behavior to each agent's author
- Read the full record of an interaction, including the tools the agent called and what policy did to the response
- Evaluate quality and safety continuously against live traffic
- Make a proven agent reusable so other teams adopt it instead of rebuilding it
- Give every agent its own identity and limit what that identity can reach
This session is for architects, platform teams, and developers who already have agents running and now have to answer for them.
View the slides: https://wso2.com/library/conference/2026/09/ai-agent-manager-part-1
#WSO2 #WSO2AgentManager #AIAgents