Marcel Scherenberg
Infrastructure as Prompts: Creating Azure Infrastructure with AI Agents
#1about 3 minutes
The challenge of translating business needs to cloud infrastructure
Broad business requests for cloud and AI adoption create a vast and confusing solution space, often leading to choice paralysis for clients.
#2about 4 minutes
Shifting from technology-first to problem-first AI adoption
Instead of starting with AI technology and searching for a problem, the focus should be on defining a business problem first to create real value.
#3about 3 minutes
The slow and complex manual infrastructure deployment workflow
The traditional process for deploying cloud infrastructure involves a slow, iterative cycle between roles like architects, engineers, and SecOps, often taking weeks.
#4about 3 minutes
How AI agents can accelerate infrastructure deployment
AI agents can accelerate the initial deployment phase by translating natural language business requirements into infrastructure code, reducing communication costs and enabling rapid experimentation.
#5about 4 minutes
Designing a multi-agent system for Azure infrastructure
The proposed multi-agent system mirrors real-world roles like cloud architect, engineer, and SecOps, using tools like the Azure CLI and Terraform to automate deployment.
#6about 7 minutes
Live demonstration of deploying Azure resources from a prompt
A live demo showcases how AI agents collaborate to interpret a natural language request, generate and correct Terraform code, validate it for compliance, and prepare it for deployment.
#7about 3 minutes
Key takeaways for implementing AI agent solutions
Focus on creating real-world value by providing agents with the right tools and knowledge, defining a clear scope, and building modular, reusable solutions.
Related jobs
Jobs that call for the skills explored in this talk.
Wilken GmbH
Ulm, Germany
Senior
Kubernetes
AI Frameworks
+3
Matching moments
04:57 MIN
Increasing the value of talk recordings post-event
Cat Herding with Lions and Tigers - Christian Heilmann
01:32 MIN
Organizing a developer conference for 15,000 attendees
Cat Herding with Lions and Tigers - Christian Heilmann
03:17 MIN
Selecting strategic partners and essential event tools
Cat Herding with Lions and Tigers - Christian Heilmann
02:54 MIN
Automating video post-production with local scripts
Cat Herding with Lions and Tigers - Christian Heilmann
03:15 MIN
The future of recruiting beyond talent acquisition
What 2025 Taught Us: A Year-End Special with Hung Lee
03:28 MIN
Why corporate AI adoption lags behind the hype
What 2025 Taught Us: A Year-End Special with Hung Lee
03:48 MIN
Automating formal processes risks losing informal human value
What 2025 Taught Us: A Year-End Special with Hung Lee
05:18 MIN
Incentivizing automation with a 'keep what you kill' policy
What 2025 Taught Us: A Year-End Special with Hung Lee
Featured Partners
Related Videos
26:35Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure
Ricardo
23:33Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact
Oliver Will
28:53Agentic DevOps: How AI-Powered Automation Transforms Software Delivery on GitHub and Azure
Mike
27:07Rethinking Workflows in the Agentic Era
Eric Jadi & Rene Pajta
23:39Building Blocks for Agentic Solutions in your Enterprise
Dennis Zielke & Rene Pajta
25:32Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP
Viktoria Semaan
39:11Agents for the Sake of Happiness
Thomas Dohmke
24:24Best practices: Building Enterprise Applications that leverage GenAI
Damir
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
Fde
Azure
Python
JavaScript
Computer Vision
Natural Language Processing
Allianz Group
Municipality of Madrid, Spain
Remote
GIT
JSON
YAML
Azure
+7
Coduct Solutions GmbH
Berlin, Germany
JIRA
Azure
Figma
Confluence
Powershell
+1
Coduct Solutions GmbH
JIRA
Azure
Figma
Confluence
Powershell
+1
Smartedge Solutions Ltd
Charing Cross, United Kingdom
Azure
DevOps
Terraform