Agentic AI in DevOps

A malicious package lands, and production scans only answer part of the question. Developer laptops may already hold it, while security teams spend hours finding out where they're exposed.Andrey Devyatkin and Vladimir Samoylov join guest Mohit Bansal to explore Webflow's reduction of supply chain triage from hours to minutes, endpoint inventories, MCP credential risks, repository maturity gates and AWS account boundaries for AI agents.What you will learn:How Webflow reduced supply chain triage from hours to minutesWhy developer laptops belong in every malicious-package investigationWhere MCP configs and agent transcripts leave credentials exposedHow repository graduation gates focus remediation on productionWhy patching a base image still requires rebuilding and redeployingMaybe try B.O.R.I.S, our context layer for AI agents: https://www.getboris.aiEpisode page, show notes and links

Agents can produce pull requests faster than teams can review them, even while Git stays fast. Hosting platforms face real scaling pressure, but most teams hit other limits first.Andrey Devyatkin, Vladimir Samoylov and Fernando Piviani examine GitHub, GitLab and Cursor Origin's storage changes, Anthropic's Scion, file APIs that avoid unnecessary clones, and Entire's transcript checkpoints as a way to preserve intent without overlooking secrets and access controls.What you will learn:Why Git hosting scale problems rarely require ordinary teams to migrateWhich agent lookup jobs can use file APIs instead of clonesWhy short-lived credentials and separate transcript access boundaries matterHow intent blocks help reviewers assess agent pull requestsWhy faster pushes do not eliminate coordination around a shared refMaybe try B.O.R.I.S, our context layer for AI agents: https://www.getboris.aiEpisode page, show notes and links

An agent can pass its evals and still disappoint customers. Production traces help only when someone turns real successes and corrected failures into tests worth trusting.Andrey Devyatkin, Vladimir Samoylov and Fernando Piviani join Langfuse engineer Nikita Kabardin to discuss golden datasets, human review of evals, reliable pull request workflows, context for autonomous agents, and permission boundaries between customer data and public fixes.What you will learn:Build a golden dataset from successful traces and corrected failuresRecognize when an agent improves its scores by changing the gradingMove pull request state transitions from prompts into deterministic codeUnderstand why unattended agents need context beyond local Markdown filesKeep private customer traces out of public development workflowsMaybe try B.O.R.I.S, our context layer for AI agents: https://www.getboris.aiEpisode page, show notes and links

An alert needs triage, a ticket needs a duplicate check, and a frontier LLM is generating answers for both. Decision models could make those routine checks cheaper, provided the thresholds and gates stay in code.Andrey Devyatkin, Vladimir Samoylov and Fernando Gonçalves explore Jev, eight DevOps use cases, agent tool hooks, probability thresholds and local alternatives, including where classifiers fall short.What you will learn:How decision models differ from LLMs with structured outputWhy uncertain probabilities belong in a review band around 0.5How pre-tool and post-tool hooks can filter expensive agent workWhere alert triage, duplicate detection and GraphRAG could benefitWhy classifier checks cannot replace permissions or deployment policyMaybe try B.O.R.I.S, our context layer for AI agents: https://www.getboris.aiEpisode page, show notes and links

Claude Code can produce more code than an engineer can comfortably review. Trusting that output takes a repeatable workflow, protected learning time and checks that catch a solution to the wrong problem.Andrey Devyatkin and Fernando Gonçalves join Kaido Koort to explore agentic engineering training, agent-led specs, validator sub-agents, session handoffs, verification versus validation, and what Claude certifications actually demonstrate.What you will learn:How six Fridays progress from brownfield orientation to parallel agentsHow competing validator sub-agents expose trade-offs before implementation startsHow transcript-based wrap-ups turn forgotten decisions into actionable issuesWhy verification and validation need separate gates for agent outputHow autonomy, parallelism and skill usage reveal different learning gapsMaybe try B.O.R.I.S, our context layer for AI agents: https://www.getboris.aiEpisode page, show notes and links