Insights on B.O.R.I.S - Your AI DevOps Teammate

#12 — Semantic Layers, Context Layers, and Agents That Stop Guessing

Fri, 12 Jun 2026 00:00:00 +0000

Summary

If you work in data, “semantic layer” means one precise thing: the place where “active customer” or “recurring revenue” gets defined once so every dashboard agrees. If you build agents, the word starts doing two jobs at once — and a second term, “context layer,” shows up claiming the same ground. This episode of Agentic AI in DevOps picks up directly where episode #11 left off, with Andrey Devyatkin, Vladimir Samoylov, and Fernando Gonçalves untangling the two. The short version: a semantic layer tells an agent what your data means; a context layer tells it what’s actually running, where it lives, and what’s connected to what. The hosts argue you usually want both — and along the way they get blunt about vendors who promise you can fire your analytics team, about agent memory that “comes stale” and quietly biases every session, and about a Kent Beck line that sums up the whole moment: typing got faster, thinking did not.

#11 — Base of Record for Intelligent Systems

Fri, 05 Jun 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

The hosts of Agentic AI in DevOps make the case that the “second brain” idea — long a personal-productivity meme — is exactly what AI agents need to be useful inside a real engineering environment. Without a system of reference, the agent burns its context window rediscovering what is running where, hallucinates the gaps, and needs credentials it should not have. The episode also marks a pivot: B.O.R.I.S is no longer pitched as a replacement DevOps engineer, but as a context layer for engineering systems — and the acronym now stands for Base of Record for Intelligent Systems. Fernando Gonçalves rejects pure RAG as enough on its own (the relationships are what matter), Andrey Devyatkin turns “do you take notes?” into a hiring question, and the half-hour closes with a token-maxing post-mortem and the reminder that you can outsource the legwork to agents but not the decisions.

#10 — What Changed in Our Daily AI Workflow

Sun, 31 May 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

In a less-structured episode, the hosts of Agentic AI in DevOps compare day-to-day workflows: what they actually run, what they have stopped doing, and how their habits have shifted since the early autumn. Fernando Gonçalves keeps the classical engineering ritual — linting, tests, coverage targets — and bakes it into a skill so the AI cannot skip past quiet bugs. Vladimir Samoylov has rewired the harness with hooks for audit logs, command-failure journals, and a daily “dead code” sweep, and tracks a new personal metric: average working hours without a human. Andrey Devyatkin argues that the second shift at 9 PM is the wrong time to drive an agent — the sharpest decisions belong to a fresh 5 AM mind — and shells Claude Code out to Codex to cross-review its own plans. The closing exchange wanders into whether AI is “the last thing humans will invent,” and the hosts disagree: imagination, accidents, and champagne all live outside the training data.

#9 — Code with Claude: Routines, Agents, and the AWS Catch

Fri, 15 May 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

Anthropic’s Code with Claude developer conference in San Francisco on May 6, 2026 dropped a wave of platform features aimed squarely at coding teams, and the hosts walk through what actually matters for builders. Andrey Devyatkin reads the SpaceX–Anthropic compute deal as one of the cleverest business moves of the year — xAI is sitting on underutilized GPUs, and “the enemy of my enemy” gets to raise everyone’s usage limits. The episode dissects routines, outcomes/goals, multi-agent orchestration, the advisor pattern, dreaming, and the new Anthropic-on-AWS path that is not Bedrock, with Fernando Gonçalves flagging an easy-to-miss compliance gotcha: on that path, data still leaves AWS for Anthropic. The closing read on OpenAI is sharp — a two-month free Codex trial for new Codex users on eligible enterprise accounts, which the hosts call “a little bit of a desperate attempt” after Anthropic’s enterprise adoption crossed OpenAI’s.

#8 — DevOps Jobs Agentic AI Can Actually Do

Fri, 08 May 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

After seven foundation-laying episodes, the hosts of Agentic AI in DevOps take the practitioner’s tour: which DevOps jobs agentic AI actually does well, and which still fight back. Andrey Devyatkin reframes the “AI deleted my production database” headlines, arguing they are functionally identical to “my terminal deleted my database” — the human gave the credentials and confirmed the action — and walks through why infrastructure-as-code is harder for agents than application code (one word: state). The hosts dig into the gap between C-suite adoption claims and practitioner reality, with Fernando Gonçalves noting that “use AI” is now a manager KPI, and they land on documentation, runbooks, and postmortems as the place where agents quietly earn their keep right now.

#7 — When Agent Memory Helps and When It Hurts

Wed, 29 Apr 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Key Topics

News: Hermes Agent and the Rise of Memory-First Agents

Andrey introduces Hermes Agent, the self-improving open-source agent from Nous Research that positions memory as its centerpiece. Like OpenClaw — the self-improving personal assistant released earlier in 2026 — Hermes can build its own skills and connect through multiple communication platforms (Telegram, Discord, Slack, WhatsApp). The difference is that Hermes ships with a built-in memory system: a MEMORY.md file (approximately 800 tokens) where the agent stores environmental facts, conventions, and learnings, and a USER.md file (approximately 500 tokens) for profile and preferences, both stored in the home directory under .hermes/memories. Past conversations persist in SQLite with full-text search and LLM summarization. Memory plugins like Mem0 can augment the built-in system. Andrey urges listeners to keep the Hermes memory architecture in mind as a reference point for the main discussion.

#6 — The Big AI Squeeze

Wed, 22 Apr 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Key Topics

The Vercel–Context AI Supply Chain Breach

The episode opens with the Vercel security incident, where a compromised credential at Context.ai — a third-party AI tool used by a Vercel employee — led to unauthorized access to Vercel’s internal systems. Vladimir breaks down the chain of assumptions that made the breach possible: the Vercel engineer assumed Context AI was handling security properly, the Google Workspace administrator assumed the platform was secure by default, and Context AI did not even know a company of Vercel’s size was connected to their legacy product. Every party assumed someone else was doing the hard security work. Vladimir warns this pattern will repeat as AI-accelerated development outpaces security diligence — “all the tools look beautiful and nice, but maybe not everywhere perfect.”

#5 — Stop Your Agent Before It Breaks Prod

Fri, 17 Apr 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Key Topics

News: Anthropic’s April Blitz — Managed Agents, Routines, Opus 4.7, and the Advisor Tool

Fernando kicks off the news with Anthropic’s launch of Managed Agents — a hosted infrastructure service that lets users run Claude-based agents on Anthropic’s servers without keeping a laptop on. For technical audiences used to CI/CD, the reaction is a collective shrug: scheduling agents is something they could already do by installing Claude Code or OpenCode as a GitHub Action, setting a cron schedule, and pointing it at a token provider. But Fernando points out that for non-technical users, the ability to schedule an agent that “did something by itself” can genuinely feel like magic. Fernando also mentions Routines, a related feature that lets users define workflows where the agent reasons through which tools to call rather than following a rigid step-by-step sequence.

#4 — Harness Engineering: What Claude Code Accidentally Taught Everyone

Mon, 13 Apr 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Key Topics

NVIDIA OpenShell and the Agent Containment Problem

Vladimir introduces OpenShell, NVIDIA’s open-source sandboxing runtime related to the NemoClaw stack. OpenShell operates across four layers — network, filesystem, process, and inference — all configurable through a single YAML policy schema. The hosts frame this in the context of a growing concern: agents running locally on developer machines inherit full user permissions, making prompt injection, malicious skills, and supply chain attacks real threats.

From Frustration to Product: The Story of B.O.R.I.S

Fri, 03 Apr 2026 00:00:00 +0000

We’re a small team of DevOps engineers who got tired of watching AI tools fail at the one thing they should be good at - understanding the infrastructure they’re supposed to help with. So we built something different.

B.O.R.I.S is an AI DevOps teammate that actually knows your systems, remembers your environment, and works alongside your team - not in a private chat window, but right where your engineers already communicate.

#3 — Skills, Powers, SOPs

Mon, 30 Mar 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Key Topics

The Cursor pricing wake-up call

The episode opens with a cautionary tale. The team’s annual Cursor subscription renewed and shifted from generous included request allotments toward stricter usage-based overages tied to actual API costs. Within a single week, costs hit roughly a thousand dollars — per developer. Andrey notes they are “late to the party” since monthly subscribers felt the pain back in July 2025, but annual subscribers only got hit now. Fernando stresses the importance of watching automatic recharge settings: “You might get a surprise at the end of the month — or like happened to us, after a week.”

#2 — The Tool Layer: What Makes Agentic AI Possible

Mon, 23 Mar 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

The episode treats the context window as the hidden budget behind every agentic coding session: not only how many tokens fit, but how much of that budget is already spent on system prompts, tool schemas, and project files before real work starts. Andrey Devyatkin and Fernando Gonçalves survey recent product news, then walk through what fills the window, why quality often slips well below the advertised maximum, and concrete habits—CLI where it beats MCP, sub-agents, plan mode, and periodic audits of preloaded context—that teams use to keep sessions sharp.

#1 — AI in DevOps, 2022 to 2026: From Autocomplete to Action

Tue, 17 Mar 2026 00:00:00 +0000

Spotify Apple Podcasts RSS

Summary

The hosts move from late-2022 chat assistants toward agents that can run commands and touch real systems, and they keep returning to a single constraint: context. Without code, logs, metrics, and how the team actually runs things, even a strong model behaves like a new hire asked to debug a production incident blind. The episode walks a rough yearly timeline—quiet foundational work in 2024, then a crowded 2025 of terminal agents, AWS CLIs, and spec-driven IDEs—then asks which “AI products” can ever work when they only own a sliver of the operational picture.