WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

No Keys for the Robot: GitOps as the Control Plane for Autonomous Agents

Jaroslaw Gajewski

Are you giving autonomous AI agents direct deployment keys? Prevent runaway automation by treating AI like a junior developer who must propose operational fixes via GitOps pull requests.

Pause
Mute Enter Fullscreen
#1 about 3 min

Real-world risks of autonomous AI agents in production

Unconstrained AI automation causes runaway costs and destructive infrastructure events when given direct access.

#2 about 3 min

Managing autonomous agent trust and cloud permission gaps

Treating AI agents like unpredictable new hires emphasizes the risk of granting overly permissive cloud identities.

#3 about 3 min

Routing agent decisions through standard delivery pipelines

Forcing AI-proposed infrastructure changes through standard CI/CD and review processes prevents dangerous direct executions.

#4 about 3 min

Implementing read-only access and zero trust policies

Restricting autonomous agents to read-only infrastructure permissions ensures all operational changes are safely routed through Git.

#5 about 3 min

Standardizing the infrastructure control plane with Crossplane

Structuring infrastructure as code tools creates a uniform entry point for all control plane modifications proposed by agents.

#6 about 4 min

Leveraging GitOps for AI auditing and instant rollbacks

Git repository history inherently provides compliance-ready audit trails and deterministic rollback capabilities for flawed AI decisions.

#7 about 2 min

Enforcing core security gates for AI agentic workflows

Infrastructure reconciliation, policy as code, and branch protections actively block unauthorized operations and enforce governance.

#8 about 2 min

Walking through an agent-driven GitOps deployment workflow

A conceptual runbook demonstrates an AI generating pull requests while GitOps controls successfully block direct cluster modifications.

#9 about 8 min

Strategies for safely phasing autonomous agents into production

Gradually expanding agent permissions from staging reviews to robust production workloads prevents catastrophic downtime and normalizes on-call operational models.

Matching moments

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann +2 · LIVE

2:40 min

Enforcing developer accountability when leveraging AI programming agents

Daniel Siegl · Coffee With Developers

2:34 min

Balancing developer autonomy with the adoption of coding agents

Clemens Wasner Clemens Wasner +4 · WWC Europe 2026

2:18 min

Managing security risks introduced by autonomous AI agents

Christian Heilmann Christian Heilmann · WWC 2025

1:03 min

From read-only models to excessive agency

Alex Olivier Alex Olivier · WWC Europe 2026

2:28 min

Mitigating excessive agency through scoped tool access

Deepu Deepu · WWC 2025

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 1 month ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
about 1 month ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
about 1 month ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
about 1 month ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
about 1 month ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
about 1 month ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Responsible AI Architecture with Zero Trust Agents

Ashok Prakash

Staff ML Engineer at Apple

Ashok Prakash
Open session

World Congress 2026 North America

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal, Dor Cohen

Yoav Gal
Dor Cohen
Open session

World Congress 2026 North America

Zero-Trust Architecture for Agentic AI: Securing Multi-User Access and Third-Party Integrations

Borko Djurkovic

Member of Technical Staff at Cohere

Borko Djurkovic
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

Give the Agent a Budget, Not a Token

Sachin Malhotra

MTS @Anthropic

Sachin Malhotra

Related videos

The day the chatbot asked for sudo thumbnail
27:48
WWC Europe 2026 • about 1 month ago

The day the chatbot asked for sudo

Alex Olivier

What Production Knows: Closing the Loop Between AI Agents and the Systems They Build thumbnail
26:33
WWC Europe 2026 • about 1 month ago

What Production Knows: Closing the Loop Between AI Agents and the Systems They Build

May Walter

What AI Can Learn from Version Control - Daniel Siegl (Syntevo) thumbnail
38:14
Coffee With Developers • 9 months ago

What AI Can Learn from Version Control - Daniel Siegl (Syntevo)

Daniel Siegl

Running AI at Scale: The Secret Ingredients thumbnail
30:04
WWC Europe 2026 • about 1 month ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

Agentic employees in world's most downloaded FinTech app thumbnail
30:37
WWC Europe 2026 • about 1 month ago

Agentic employees in world's most downloaded FinTech app

Sasa Fajkovic

Building a Multi-Agent Orchestration Engine That Actually Follows the Rules thumbnail
29:01
WWC Europe 2026 • about 1 month ago

Building a Multi-Agent Orchestration Engine That Actually Follows the Rules

Hussein Jundi, Torsten Stiller

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.