# B.O.R.I.S - The Context Layer for AI Agents

B.O.R.I.S - context layer for AI agents. It connects to your AWS organization, GitHub repositories, and Slack workspace so every AI answer starts from how your stack actually works.

## Pages


- [#22 — From Agent Traces to Better Evals with Nikita Kabardin](https://www.getboris.ai/insights/022-from-agent-traces-to-better-evals-with-nikita-kabardin/index.md) — LLM evals can pass while an agent still fails users. Turn production traces into human-reviewed datasets that catch regressions before the next model or prompt change ships. Nikita Kabardin joins the hosts to explain Langfuse’s trace-to-eval workflow, why agents should not control their own grading, and where human review belongs. The conversation also covers reliable pull request workflows, context for autonomous agents, and keeping customer data out of public fixes.

- [#21 — 8 DevOps Jobs to Try With Decision Models](https://www.getboris.ai/insights/021-8-devops-jobs-to-try-with-decision-models/index.md) — DevOps pipelines pay for LLM generation even when they only need a yes, no or label. Decision models offer cheaper classification while keeping thresholds and gates in code. The hosts explore Jev and eight candidate jobs, from alert triage and duplicate detection to PII checks, model routing and GraphRAG. They explain where classifiers fit around agent tool calls, how to route uncertain probabilities for review, and why focused input and deterministic checks still matter.

- [#20 — Become an Agentic Engineer with Kaido Koort](https://www.getboris.ai/insights/020-become-an-agentic-engineer-with-kaido-koort/index.md) — Claude Code can write code, but engineers still need a workflow they can trust. Kaido Koort explains how specs, testing harnesses and validation make agent delegation repeatable. The conversation covers Plepic's six-Friday curriculum, agent-led interviews, competing validator sub-agents, session handoffs and parallel work in Git worktrees, plus the limits of Claude certifications and the attention cost of managing multiple agents.

- [#19 — AI Doom Can Wait. Your Security Alerts Can’t](https://www.getboris.ai/insights/019-ai-doom-can-wait-your-security-alerts-cant/index.md) — AI security triage can cut GuardDuty alert noise and surface evidence for the findings that need attention. The hosts move from AI doom headlines to practical LLM workflows: grouping findings, checking live AWS policies and reviewing recommendations. They cover read-only permission traps, tool guards and spending controls, and explain why assisted investigation and batch analysis should come before unattended agents.

- [#18 — AI Writes Code. What's Your Job? with Julien Bisconti](https://www.getboris.ai/insights/018-ai-writes-code-whats-your-job-with-julien-bisconti/index.md) — An agent writes the code, more agents review it, and the honest answer to what you did all day has gone fuzzy. Almost none of the constraints that still bite are about the model. They are about the context you feed it, the verification you keep, and knowing which problem is worth solving at all. This covers reference implementations instead of longer prompts, a stopping rule for review rounds, why every artifact an agent leaves behind becomes the next agent's context, the credentials sitting in your local transcripts, and why token spend measures nothing you want measured.

- [#17 — DevOps Agents Need Context, Not More Tools](https://www.getboris.ai/insights/017-devops-agents-need-context-not-more-tools/index.md) — Cursor shipped Grok 4.6 at two dollars in and six out, Anthropic replaced its Slack chatbot with Claude Tag, and cloud agents will review a pull request from a one line comment. All good tools. None of them knows which account your service runs in, what depends on it, or what changed last week, so every session starts with the same discovery work. This is about that work, where it costs you the most, and why live infrastructure state belongs in a database rather than in a skills file or a vendor's memory.

- [#16 — How DevOps Makes AI Safe to Scale](https://www.getboris.ai/insights/016-how-devops-makes-ai-safe-to-scale/index.md) — AI adoption stalls when licenses and quotas replace trust, context, and verification. Fernando Gonçalves and Vladimir Samoylov explain how DevOps makes agentic coding safe to scale through checkable starter tasks, organization-specific context, independent tests, Terraform plans, and deterministic gates—while exposing why token metrics, AI-written tests, and advisory Markdown can create false confidence.

- [#15 — Can Origin and Entire Replace GitHub?](https://www.getboris.ai/insights/015-can-origin-and-entire-replace-github/index.md) — GitHub outages and agent-scale workloads are exposing the limits of centralized development platforms—learn where Cursor Origin and Entire could help, and which bottlenecks they cannot fix. Andrey Devyatkin, Vladimir Samoylov, and Fernando Gonçalves examine AI-native Git forges, distributed mirrors, API and Actions limits, repository sovereignty, and whether Git is even the real constraint. They weigh agent-scale throughput claims against human review, CI, internet bandwidth, and the token cost of best-of-N agent fleets, asking whether teams need to leave GitHub or simply reduce their dependence on it.

- [#14 — Loop Engineering in DevOps](https://www.getboris.ai/insights/014-loop-engineering-in-devops/index.md) — Loop engineering solves the coding-agent babysitting problem by giving DevOps teams a way to run larger tasks with evidence, constraints, and a clear definition of done. Andrey Devyatkin, Vladimir Samoylov, and Fernando Gonçalves unpack outer loops around agents, context-window limits, unattended runs, greenfield versus brownfield work, alert batching with SNS and SQS, model mixing, token costs, and why bad code still gets worse when you automate it faster.

- [#13 — cmux vs iTerm with Viktor Vedmich](https://www.getboris.ai/insights/013-cmux-vs-iterm-with-viktor-vedmich/index.md) — cmux terminal workflows: when iTerm slows down AI-agent work, Viktor Vedmich shows how workspaces, session restore, and socket APIs make Claude Code more practical. Andrey Devyatkin and Fernando Gonçalves talk with Viktor Vedmich about his terminal-first agentic stack, Obsidian vault setup, Claude Code on Bedrock, AWS Kiro, spec-driven workflows, MCP search tools, rising token bills, and why open-weight model competition matters for DevOps teams.

- [#12 — Semantic Layers, Context Layers, and Agents That Stop Guessing](https://www.getboris.ai/insights/012-semantic-layers-context-layers-and-agents-that-stop-guessing/index.md) — Two terms keep colliding in infrastructure AI: semantic layer and context layer. They're not the same thing, and conflating them is how teams end up with agents that understand vocabulary but have no idea what's actually running — or agents that know the environment but still guess wrong about what the data means.

- [#11 — Base of Record for Intelligent Systems](https://www.getboris.ai/insights/011-base-of-record-for-intelligent-systems/index.md) — 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](https://www.getboris.ai/insights/010-what-changed-in-our-daily-ai-workflow/index.md) — 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](https://www.getboris.ai/insights/009-code-with-claude-routines-agents-and-the-aws-catch/index.md) — 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](https://www.getboris.ai/insights/008-devops-jobs-agentic-ai-can-actually-do/index.md) — 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 — Agent Memory: When It Helps, When It Hurts, and How to Manage It](https://www.getboris.ai/insights/007-when-agent-memory-helps-and-when-it-hurts/index.md) — Your AI agent just forgot everything. Again. You taught it your stack, your conventions, your preferences — and tomorrow it wakes up like it never happened. Memory is supposed to fix that. Here's what nobody tells you: it can also make things worse. This blog post breaks down exactly how agent memory works, when it helps, when it quietly poisons your sessions, and what to do about it.

- [#6 — The Big AI Squeeze](https://www.getboris.ai/insights/006-the-big-ai-squeeze/index.md) — LLM subsidies are drying up, subscription limits are tightening, and the astronomical data center CapEx has to be paid by someone — spoiler: it is you. In this episode, Fernando Gonçalves, Andrey Devyatkin, and Vladimir Samoylov tackle what they call "the big squeeze": the two-sided pressure of rising AI costs and emerging local-inference technologies that could reshape how teams budget for and deploy AI. Along the way, they debate whether buying a Mac Mini is a rational investment or just hype, reveal the mental gymnastics required to get meaningful work out of a twenty-dollar subscription, and argue that if your AI vendor has no pricing page, that tells you everything you need to know about their business model.

- [#5 — Stop Your Agent Before It Breaks Prod](https://www.getboris.ai/insights/005-stop-your-agent-before-it-breaks-prod/index.md) — Imagine your agent just deleted a production database — could you have stopped it? The hosts argue that yes, three lines of bash in a single hook could have prevented it, and yet most teams have never configured one. In this episode, Andrey Devyatkin, Vladimir Samoylov, and Fernando Gonçalves pull apart the agentic loop — the repeating cycle of reason, act, observe that makes coding agents appear to "think" — and show exactly where hooks slot in to give humans deterministic or automated harness-level control over non-deterministic AI behavior, depending on the hook type. Along the way, they unpack Anthropic's rapid-fire release week (Managed Agents, Routines, Opus 4.7, and the advisor tool pattern), debate whether LLM provider commoditization is real or an illusion, and warn that the same hook mechanism that protects your infrastructure can be weaponized through supply chain attacks.

- [#4 — Harness Engineering: What Claude Code Accidentally Taught Everyone](https://www.getboris.ai/insights/004-harness-engineering-what-claude-code-accidentally-taught-everyone/index.md) — A packaging mistake exposed Claude Code's full source tree to the world — and instead of scandal, the community got a masterclass in how agentic coding tools actually work under the hood. In this episode, Andrey Devyatkin, Vladimir Samoylov, and Fernando Gonçalves unpack what the disclosure revealed about the engineering behind coding agents, introduce the emerging discipline of "harness engineering," and argue that the model is only the horsepower — it is the harness that determines whether the agent gallops toward the right destination or off a cliff. Along the way, they weigh in on NVIDIA's OpenShell sandboxing, Cursor 3.0's agent-first interface, and why Docker containers are not the security blanket many DevOps engineers assume them to be.

- [From Frustration to Product: The Story of B.O.R.I.S](https://www.getboris.ai/insights/from-idea-to-product/index.md) — We're a small team of DevOps engineers who built a context layer for AI agents so they understand your real stack. This is the story of how B.O.R.I.S came to be.

- [#3 — Skills, Powers, SOPs](https://www.getboris.ai/insights/003-skills-powers-sops/index.md) — What happens when your AI coding tool quietly starts billing like a cloud service — and your team burns through a thousand dollars in a week? Vladimir Samoylov returns as the hosts share their sticker-shock moment with Cursor's new pricing before diving into agent skills. From Claude Code skills to Kiro Powers to AWS Strands SOPs, the naming varies but the idea is the same — plugging structured knowledge into an agent's brain on demand.

- [#2 — The Tool Layer: What Makes Agentic AI Possible](https://www.getboris.ai/insights/002-the-tool-layer-what-makes-agentic-ai-possible/index.md) — What happens when your AI coding assistant forgets what it was just working on? Andrey Devyatkin and Fernando Gonçalves break down context windows, how MCP servers can consume a large share of the session before the first message, and why over-specifying agent behavior in project rules often hurts output.

- [#1 — AI in DevOps, 2022 to 2026: From Autocomplete to Action](https://www.getboris.ai/insights/001-ai-in-devops-2022-to-2026-from-autocomplete-to-action/index.md) — What if most AI tools sold into DevOps fail because they only see part of the stack? In this first episode of Agentic AI in DevOps, Andrey Devyatkin and Fernando Gonçalves trace AI tooling from ChatGPT's launch in late 2022 through 2025: they treat context—not model hype—as the constraint, and explain why assistants cut off from source, logs, metrics, and docs tend to guess wrong under real operational load.

- [About](https://www.getboris.ai/about/index.md) — Meet B.O.R.I.S - The infrastructure AI product built from real DevOps experience.

- [Book a demo](https://www.getboris.ai/book-a-demo/index.md) — Book a 30-minute call with the B.O.R.I.S team: a demo, help choosing a plan, or best practices for getting the most out of B.O.R.I.S.

- [FAQ](https://www.getboris.ai/faq/index.md) — Frequently asked questions about B.O.R.I.S — data residency, security, pricing, deployment, and how it compares to other tools.

- [Pricing](https://www.getboris.ai/pricing/index.md) — B.O.R.I.S pricing: the Standard plan at $250 per connected system a month, or a private cloud installation inside your own account.

- [Use Cases](https://www.getboris.ai/use-cases/index.md) — How teams use B.O.R.I.S: grounded coding and review, production support, security, onboarding, and time and token savings, all from one source of truth over MCP.


## Sections


- [Insights](https://www.getboris.ai/insights/index.md)