Live roundtable & demos · Sep 10 · 1 PM ET · CloudGeometry × Tigera

Agents are writing production code. Who signed off, and what did they touch?

Two things have to be true before anyone is comfortable with agents in production: a human stays accountable for what gets built, and somebody knows what the agent touched to build it. CloudGeometry and Tigera have been working on each end of that problem. This session brings both together, live.

  • How a governed lifecycle keeps a senior engineer signing off at every gate with a named person accountable for the outcome
  • How runtime enforcement gives every agent an identity, credentials that expire in minutes, and a record of every call including the ones that didn't run
  • What to do about shadow agents and delegation chains before your auditor asks about them
CloudGeometry Tigera

Hosted by CloudGeometry and Tigera · a roundtable conversation on AI agents and observability, with live demos to back the methodology.

Registration

Save your seat

Live roundtable + demos · Thursday, September 10 · 1:00 PM ET / 10:00 AM PT / 6:00 PM UK. Registrants get the calendar invite first, plus the recording.

🎙 Roundtable 🖥 Live demos 🎥 Recording included 💬 Open Q&A

Loading registration form…

We'll only use your details to send you the invite, the recording, and related session materials.

Trusted by engineering teams at

Sinclair Broadcast Group AWS TetraScience Gemini Health Ryder Symphony Longroad Energy Nexar Origami Royal Ambulance DiffusionData Gali Health
The Premise

Approval without enforcement is a signature on something you can't see. Enforcement without accountability is a wall your team routes around by Friday.

Most teams have half the answer. Lifecycle governance tells you a human approved the change. Runtime enforcement tells you what the agent could reach. Neither is enough on its own, and the gap between them is where incidents, sprawl, and awkward audit conversations live.

One layer on its own

  • Sign-offs on changes nobody can trace at runtime
  • Guardrails your team quietly works around
  • Shared service accounts and long-lived keys in a secrets file
  • Agents running that nobody inventoried

Both layers together

  • Every change traced from intent to implementation to sign-off
  • Policy enforced in the path of every agent call
  • One identity per agent, credentials that expire in minutes
  • A record of every call that ran, and every call that didn't
The Two Layers

One problem, two ends.

CloudGeometry runs the lifecycle. Tigera runs the guardrails. In the session, we walk through how a single agent action runs through both layers, then demo each one live.

CloudGeometry Lifecycle

AI-MSL

Accountability for what gets built

Agents work on requirements, implementation, tests, and documentation, grounded in a live model of your real system, not a prompt full of guesses.

  • A senior engineer signs off at every gate, from requirement to release
  • A named person is accountable for the outcome, not a model
  • Every change is traceable: intent, implementation, tests, approval
Tigera Runtime

Lynx

Enforcement for what agents can reach

Lynx sits in the path of every agent call and decides what that agent is allowed to reach, while it runs.

  • An identity per agent, not a shared service account
  • Credentials that expire in minutes, not keys living in a secrets file
  • A record of every call that ran, and every call that didn't

The demos tie the two together: watch one agent-built change pass its lifecycle gates while its runtime calls are allowed, denied, and recorded in real time.

What You'll Take Away

Eight things you'll leave with, in one session.

01

Keep a human accountable

Where senior-engineer sign-off gates belong when agents write the requirements, the code, the tests, and the docs.

02

Ground agents in the real system

Why agents grounded in a live model of your system produce reviewable change, and prompt-context agents produce surprises.

03

Give every agent an identity

What per-agent identity looks like in practice, and why shared service accounts make agent activity impossible to attribute.

04

Retire the secrets file

How credentials that expire in minutes change the blast radius of a misbehaving or compromised agent.

05

See the calls that didn't run

Why a record of denied calls is as valuable as a record of executed ones, for debugging and for evidence.

06

Find your shadow agents

How to surface the agents already running in your environment that nobody registered, approved, or remembers deploying.

07

Untangle delegation chains

What happens when agent A calls agent B with agent C's permissions, and how identity plus enforcement keeps the chain visible.

08

Answer next year's audit questions

The evidence your auditor is going to ask for about AI agents, and what it takes to have it on hand instead of reconstructing it.

The Format

A roundtable first, demos to back it up.

Part 01Conversation

The roundtable

Both teams on what they've learned putting agents into production: where sign-off gates hold, where guardrails get routed around, and what broke before the model worked. Candid, practitioner to practitioner, not scripted.

shadow agentsdelegation chainssign-off gates
Part 02Screen share

The demos

Two short demos in support of the methodology, not instead of it. One agent-built change passes its lifecycle gates in AI-MSL, while Lynx allows, denies, and records the same agent's runtime calls.

gate: approvedcall: denied · logged
Part 03Your questions

Open Q&A

Bring your questions about shadow agents, delegation chains, and what your auditor is going to ask you next year. The session ends when the useful questions do.

Live, with open Q&A. Can't make it? Register anyway. Every registrant gets the recording and session materials.

The Speakers

One from each end of the problem.

Tim Wolfe, CloudGeometry
The lifecycle end

Tim Wolfe

CloudGeometry

What it takes to run agents on real production systems: requirements, code, tests, and docs, with a senior engineer signing off at every gate and a named person accountable for the outcome.

Tigera speaker
The runtime end

Speaker announced soon

Tigera · Lynx

An identity per agent, credentials that expire in minutes, and enforcement in the path of every call. From the team behind Project Calico.

Announcing shortly · register for updates
Who It's For

Built for the people who have to answer for agents in production.

01
CTO · VP Engineering · Head of Platform

You're being asked to put agents on production systems.

Before you say yes at scale, you need to know what accountability and observability look like in practice.

You leave with

A gate model you can defend, to the team and to the board.

02
Security Engineering · Architecture

Agents are a new class of principal in your environment.

Broad delegated access, no fixed identity, and activity your current tooling wasn't built to attribute.

You leave with

An identity and enforcement pattern for every agent call.

03
Platform · SRE

You inherit every change an agent ships and every credential it holds.

When something breaks at 2am, the question is what ran, what was blocked, and who approved what.

You leave with

The record to answer it: ran, denied, approved, and by whom.

Self-Assessment

Think your agents are under control? Prove it.

Eight questions on how AI agents behave inside a production environment. They're the questions your security team, your platform team, and eventually your auditor will ask, so it's better to miss them here.

Agent Governance Readiness Check
8 questions

Two minutes, eight questions, instant score. No grading on a curve. These are the standards agent-run change gets held to once security and audit get involved.

The Bottom Line
The teams that win with agents won't be the ones running the most of them. They'll be the ones that can say, for every change: who approved it, and what it touched.

Join CloudGeometry and Tigera for a working conversation on accountability and observability for AI agents, with live demos of both layers.

Save my seat Free · Sep 10, 1 PM ET · recording included

Looking for a coding-assistant comparison or a prompt-engineering tutorial? This isn't that session. It's about the operating and security model around the agents.

CloudGeometry

About CloudGeometry. CloudGeometry is a strategic engineering partner helping enterprises adopt AI-powered software delivery with governance built in. AI-MSL, its platform and managed service, maintains, modernizes, and extends production software systems, with human sign-off at every lifecycle gate, full traceability of every change, and all code and assets remaining under client ownership and control.

Tigera

About Tigera. Tigera, the team behind Project Calico, builds runtime security and observability for cloud-native workloads. Lynx applies that discipline to AI agents: an identity per agent, credentials that expire in minutes, and policy enforced in the path of every call, with a record of every call that ran and every call that didn't.

AI Agents: Accountability + Observability · live Sep 10, 1 PM ET · CloudGeometry × Tigera

Save my seat