AIGov Meetup Singapore: Agentic AI Governance

AI agents are no longer just chat assistants. A year ago, most of us used AI to answer questions or suggest a few lines of code. Today, agents write whole features, run shell commands, install packages, call APIs and push changes to real systems. Many of them do this with very little human input.

That is a big step forward. It is also a big shift in risk. An agent that can run rm -rf can also delete the wrong folder. An agent that can read your .env file can also send your secrets somewhere you never planned. An agent that can call a tool can also call the wrong one, many times, very fast.

So every team that uses AI agents now has to answer two hard questions:

1. How do we keep these agents safe?
2. How do we know the same rules apply to every agent, on every laptop, across the whole company?

This is what agentic AI governance is about. And this is what we will talk about at the AIGov Meetup Singapore on October 29th.

What the evening is about

This is an evening of talks, live demos and good conversation with practitioners from Docker, Thoughtworks and Cloudera. Each speaker looks at a different layer of the problem:

• Sandboxing and policy: how to run coding agents in an isolated space, with clear rules on what they can reach.
• Verification: how to check what an agent did, instead of just trusting it.
• Data and platform governance: how to keep control of the data and systems that agents touch at scale.

Put together, these talks give you a full picture. You will leave with ideas you can try with your own team the next morning.

Who should come

This meetup is for you if you are:

• A developer using Claude Code, Cursor, Codex or other coding agents every day
• A platform engineer who has to support these tools across many teams
• A security lead who wants to know what agents are doing on company machines
• Or just curious about where agentic AI is heading

No deep background is needed. Bring your questions.

Event details

Agenda

Define Once, Enforce Everywhere: Governing AI Coding Agents with Docker Sandboxes

Ajeet Singh Raina, Developer Advocate, Docker

Most teams today have no single place to set rules for their coding agents. Each developer sets things up their own way, on their own laptop. That makes it very hard to know what any agent can actually do.

This talk shows a different approach. With Docker Sandboxes, each agent runs inside an isolated sandbox. Platform and security teams write the policy once: which folders the agent can see, which network hosts it can reach, and which secrets it can use. That same policy then applies to every agent, whether it is Claude Code, Codex, Gemini CLI or another tool.

Expect a live demo of an agent hitting a policy wall, and a look at how teams can roll this out without slowing developers down.

Trust the Agent, But Verify: AI Governance with Agent/works

Shen Ting Ang, Thoughtworks

Guardrails are only half the story. Once an agent has done its work, you still need to check what it did and why. This talk looks at how Thoughtworks approaches AI governance with Agent/works, and how teams can build trust in agents through verification rather than blind faith.

Talk by Cloudera

Speaker and topic coming soon

Agents are only as safe as the data they can reach. Cloudera will share their view on data and platform governance in the age of AI agents. We will update this post once the details are confirmed.

See you there

AI agents are moving fast, and the rules around them are still being written. The best way to get this right is to learn from each other: what worked, what broke, and what we would do differently.

Come for the talks, stay for the conversations. Food and drinks are on us, and there is plenty of time to meet the speakers and other practitioners.

Seats are limited, so please register early.

Register here

See you in Singapore on October 29th!