From Click-Ops to Chat-Ops: AI's Double-Edged Promise
Exploring the transition from manual operations to AI-powered automation and the double-edged promise of conversational infrastructure
Topics Covered
Podcast Summary
Vincent De Smet from Handshakes.ai joins Rohit Raveendran to explore the transition from manual ClickOps to AI-powered ChatOps. They discuss how AI is transforming DevOps practices, the challenges of implementation, and the double-edged nature of AI automation.
From Manual Operations to Conversational Infrastructure
Learn about the journey from clicking through consoles to talking to your infrastructure. Vincent and Rohit explore how natural language interfaces are changing DevOps, the promise of conversational infrastructure management, and the real challenges teams face when implementing AI interpretation and execution systems.
The Double-Edged Nature of AI in DevOps
Discover both the benefits and risks of AI automation in DevOps workflows. They discuss how AI can dramatically reduce barriers to entry for operations while highlighting the critical importance of human oversight, careful design to avoid ambiguity, and the need to balance automation with operational control.
Real-World Implementation Insights
Get practical examples from Handshakes.ai's production deployments, including lessons learned, best practices for AI adoption, and common mistakes to avoid. Understand why the transition from ClickOps to ChatOps is evolutionary rather than revolutionary, and how success requires careful risk management.
Essential insights for teams considering AI-powered operations, covering everything from reducing operational complexity to maintaining safety and control in automated systems.
What You'll Learn
• In-depth insights from industry experts
• Practical strategies you can implement today
• Real-world examples and case studies
• Interactive Q&A and community discussion
Stay Updated
Get our latest live content and insights delivered to your inbox.
Hosts
Vincent De Smet
Rohit Raveendran
Special Guest: This session features expert insights from industry leaders outside of Facets.
Related Content
More Live Content
View all
AI meets MLOps - Making sense of the mess
In this episode of AI x DevOps, Rohit sits down with Görkem Ercan, CTO at Jozu, a company building a DevOps platform for AI agents and models. Görkem, a veteran with over two decades of software experience (including contributions to the Eclipse Foundation), explains why MLOps is fundamentally different from traditional, deterministic DevOps—leading to extreme pipeline fragmentation. ### Standardization is Key Discover why OCI is the recognized standard for packaging AI/ML artifacts, and how the Model Packs project (with ByteDance, Red Hat, and Docker) is defining the artifact structure. Learn how standardization is bringing order to the fragmented MLOps landscape. ### Open Source Challenges Understand the critical challenges maintainers face when receiving large amounts of untested, verbose, AI-generated code. Görkem shares insights on the impact of AI-generated Pull Requests on open-source projects. ### LLM Economics and Strategy Explore why running small, fine-tuned LLMs in-house can be cheaper and provide more predictable, consistent results than generic large providers. Get practical insights on when to build versus buy. ### KitOps Solution Learn how KitOps creates an abstraction that allows data scientists to focus on training while leveraging existing DevOps platforms for deployment. Discover how ModelKits are simplifying the AI/ML deployment pipeline. Essential listening for platform engineers, DevOps practitioners, MLOps engineers, and anyone working at the intersection of AI and infrastructure. Tune in to understand the standardization movement reshaping the future of AI development.
AI x DevOps with Sanjeev Ganjihal - AWS Solutions Architect
Join Rohit Raveendran as he sits down with Sanjeev Ganjihal, Senior Container Specialist at AWS and one of the first 100 Kubernetes certified professionals globally. This deep dive conversation explores the transformative shift from traditional DevOps to AI-powered operations and what it means for the future of infrastructure management. ### Evolution of DevOps and SRE Explore Sanjeev's unique journey from being an early Kubernetes adopter in 2017 to becoming a specialist in AI/ML operations at AWS. Discover how the industry has evolved from manual operations to automated, intelligent infrastructure management and what this means for traditional SRE roles. ### Multi-LLM Strategies in Practice Get insider insights into Sanjeev's personal AI development toolkit, including how he uses Claude, Q Developer, and local models for different tasks. Learn practical multi-LLM routing strategies, code review workflows, and how to choose the right AI tool for specific infrastructure challenges. ### Kubernetes Meets AI Infrastructure Understand the unique challenges of running AI workloads on Kubernetes, from GPU resource management to model serving at scale. Sanjeev shares real-world experiences from supporting financial services customers and the patterns that work for high-performance computing environments. ### The Future of AIOps Dive into discussions about Model Context Protocol (MCP), autonomous agents, and the concept of "agentic AI" that will define 2025. Learn how these technologies are reshaping the relationship between humans and infrastructure, with the memorable analogy of "you are Krishna steering the chariot." ### Security and Best Practices Explore critical security considerations when implementing AI in DevOps workflows, including safe practices for model deployment, data handling, and maintaining compliance in enterprise environments. Perfect for DevOps engineers, SREs, platform engineers, and technical leaders navigating the intersection of AI and infrastructure operations.
Kubernetes Agent for Natural Language Debugging
Discover how Facets' new Kubernetes Agent revolutionizes cluster management by enabling natural language debugging and secure troubleshooting. This episode showcases our AI-powered orchestrator that maintains proper guardrails and permissions while making Kubernetes operations conversational and intuitive. ### Live Demonstrations & Key Features Watch real-time troubleshooting as we diagnose a pod restart issue caused by missing sidecar files, identify and fix Redis deployment memory configuration problems, and demonstrate CPU usage analysis with Prometheus integration. See how the agent maintains security through user-scoped access controls while providing powerful debugging capabilities. ### Technical Deep Dive Explore the architecture behind Facets' Kubernetes Agent and how it orchestrates AI agents with secure infrastructure access. Learn about multi-tool integration supporting kubectl, Helm, and pod exec operations, plus natural language debugging that works with your existing permissions and kubeconfig setup. ### Audience Q&A Highlights Get answers to key questions about historical log analysis capabilities, chat history persistence and session management, integration possibilities with tools like Cursor and MCP, and comparisons with existing tools like ChatGPT and K9s. Plus, discover future plans for custom tool integration and blueprint generation. ### Perfect For DevOps Engineers looking to streamline Kubernetes troubleshooting workflows, Platform Engineers interested in AI-powered infrastructure management, Site Reliability Engineers seeking efficient debugging solutions, and Development Teams wanting to reduce time spent on cluster-related issues.
Related Articles
View allOCI...The Next Standard for AI Infrastructure?
Explore why OCI is emerging as the winning standard for AI/ML artifacts and how standardization is bringing order to the fragmented MLOps landscape with Görkem Ercan, CTO at Jozu
AI DevOps Reality: Field Report from the Enterprise Trenches
Understand the real-world impact of AI in DevOps with AWS Senior Container Specialist, Sanjeev Ganjihal
Unifying Your Toolchain: Introducing the Facets Orchestration Platform
Learn how an infrastructure orchestrator allows platform engineers to become enablers, enabling developers to self-service.