WSO2 is now Choreo LabsLearn more

Trusted AI Governance
Build

Create agents and AI apps with the tools and languages your teams already use.

Connect

Link agents securely to your APIs, data, models and business systems.

Run

Deploy, observe and operate agents and AI apps reliably at any scale.

Govern

Control identity, access, cost and policy for every agent in production.

Agent Management

Developer Platform

  • API Management Cloud

    Design, secure and publish APIs with governance and analytics built in.

    Sign Up Now
  • Integration Cloud

    Connect apps, data and AI agents with low-code and pro-code integration.

    Sign Up Now
  • Identity & Access Management Cloud

    Secure sign-in and access for customers, partners, workforce and agents.

    Sign Up Now
  • Agent Management Cloud

    Build, run and govern AI agents with full visibility and control.

    Sign Up Now
  • Developer Platform Cloud

    Ship cloud-native apps faster on an internal developer platform.

    Sign Up Now

Self-Hosted

Full control over your stack. Deploy directly to your own servers, bare metal, cloud, or Kubernetes environment. Your data never leaves your perimeter.

Product Downloads
Choreo Labs
AI Governance
Platform
Solutions
Resources
22 Sep, 2026

AI Agent Manager

Teams everywhere now have agents that work. Getting one working is real engineering, and it is also the point at which a different set of problems begins. Showing someone exactly what it said and why. Keeping a compliance rule in force across agents written by teams that have never met. Telling whether quality is improving or quietly degrading. Making sure an agent can reach the systems it needs and nothing else.

This tutorial is about operating agents rather than writing them. Using WSO2 Agent Manager, an open control plane for deploying, observing, evaluating and governing AI agents regardless of the framework they are built with, we take one working agent and put it through the controls an enterprise expects before that agent goes anywhere near real users and real data.

We will work through:

  1. Deploying an agent and moving it between environments from a single place
  2. Enforcing guardrails and policy centrally, so that correct behavior is not left to the author of each agent
  3. Reading the full record of an interaction, including the tools the agent called and what policy did to the response
  4. Evaluating quality and safety continuously against live traffic rather than testing once and hoping
  5. Making a proven agent reusable, so that other teams adopt it instead of rebuilding it
  6. Issuing every agent its own identity and limiting what that identity can reach

The session is for architects, platform teams and developers who already have agents working and now have to answer for them.

Speakers

Asanka Abeyweera

Asanka Abeyweera

Associate Director - Head of Product Management & Architecture

WSO2

Asanka's goal is to help enterprises put AI agents to work safely and at scale. As the product manager and architect of Agent Manager at WSO2, he builds the infrastructure that lets organizations run AI agents with confidence and control. Despite holding both product and architectural responsibility, he stays close to the craft and genuinely enjoys building. He believes the next wave of enterprise software will be defined by how well humans and AI agents work together, and he's focused on making that practical for real businesses. With over 12 years of experience across messaging systems, enterprise integration, and developer platforms, he brings deep insight into the highly scalable distributed systems that modern AI agents demand.

Viggnah Selvaraj

Viggnah Selvaraj

Lead Sales Engineer

WSO2

Viggnah is a sales engineer working with customers across the African region, helping them achieve their goals through technical architecture and expertise in WSO2 products. He collaborates closely with customers to understand their challenges and architect solutions that align technology with business outcomes.