The Anyshift Blog.

We say modeling infrastructure as a graph is optimal for AI, and almost nobody gets why. It's not that models like graphs. It's that a graph is an interface you can simulate: every production incident Annie investigates can be rebuilt as a graph state, at scale, for nearly free. OpenAI's Sol 6.1 maxed out our old eval set, so we built a harder one from real production failures and tuned Annie's brain on half of it. Sol went from 64% to 92% on the held-out half. All made seamless thanks to our graph.

Ghazi Felhi

Oct 23, 2026 · 8 min read

Manifests show what a workload declares, not what it calls. Build a migration dependency inventory from four sources: Kubernetes objects, observed network traffic, cloud identities, and infrastructure code. Then test it before the cutover.

Louis Fradin

Oct 22, 2026 · 9 min read

A Kubernetes outage rarely announces the deployment that caused it. Start from the alert, prove the change window, identify the ReplicaSet and image digest, then trace the rollout back to its CI run and commit.

Louis Fradin

Oct 5, 2026 · 8 min read

Two customer investigations show how a context graph was key to helping agents retrieve the right data by tracing changes and shared dependencies.

Roxane Fischer

Sep 25, 2026 · 5 min read

We were at SREday London on September 24 to talk cascading cloud failures. Photos from the day, plus a walkthrough of the talk: replaying the Cloudflare outage of 18 November 2025 with a dependency graph in hand.

Louis Fradin

Sep 24, 2026

During a production investigation, an agent must connect applications, machines and alerts. Across five integrations and ten tasks, Anyshift graph queries used 83% fewer model tokens and took 47% less time on average than native MCPs.

Anyshift

Sep 23, 2026 · 7 min read

We rebuilt our agent's architecture to separate operational knowledge, model runtime, and side effects. When we added OpenAI Codex support, the pull request only touched one file

Pierre Chollet

Sep 3, 2026 · 7 min read

Unified production context makes AI agents cheaper, faster, and easier to scale. In our live benchmark, resolving relationships before inference cut model-token usage by 83.5%, while reducing response time and estimated cost without changing the task outcome.

Roxane Fischer

Aug 17, 2026 · 7 min read

We tested six models on a bounded task: turn a plain-English infrastructure question into one supported query. Deterministic normalization and execution erased most output differences, leaving Haiku and Luna slightly ahead of Opus on final-answer accuracy. Luna then matched Haiku at 21% of the observed cost.

Stephane Jourdan

Aug 12, 2026 · 9 min read

Annie (our AI SRE agent) had institutional memory from ACE, the agentic context-engineering loop that curates cheatsheets from past runs. It worked, but clients kept catching her trusting stale entries or missing answers buried in her own bloated context. So we added five things on top: (1) a fixed set of memory items always presented to the agent, (2) per-query retrieval over the rest of the memory store, (3) an agent-optimized index of that store, (4) the ability for the agent to query the store mid-run, and (5) tried-and-true memory freshness mechanisms. Production context, now optimized by the AI using it. Here's the reasoning and what a few weeks in production say.

Ghazi Felhi

Jun 10, 2026 · 10 min read

An AI agent in the incident channel can run kubectl and read a dashboard. What it can't do is judge whether the last deploy is the suspect or a red herring. We open-sourced the SRE skills that encode that judgment, runnable offline against fixtures with no credentials.

Louis Fradin

Jun 9, 2026 · 4 min read

Private equity firms are pushing AI across portfolios, but the hard part is no longer experimentation. It is turning sponsor-level AI pressure into governed, production-aware operating workflows that actually move EBITDA.

Roxane Fischer

Jun 2, 2026 · 8 min read

Burned 25 minutes on a Friday-morning page before I realized the responsible commit was in another team's repo. This is the four-command sequence I now run when an alert lands and `git log` on my own service comes up empty, with the outputs at each step and where the search space gets cut.

Louis Fradin

May 15, 2026 · 10 min read

How AI agents learn your infrastructure. A walkthrough of the DevOpsCon Amsterdam 2026 talk: the gap between LLMs and production, structural context as a versioned graph, and ACE for self-improvement without labels.

Louis Fradin

Apr 23, 2026

Temporal workflows stuck in Running with zero pollers, and Temporal still reports a healthy task queue. The root cause lives one layer down: a CrashLoopBackOff in the Kubernetes worker pod, caused by a single bad environment variable. A walkthrough of debugging Temporal workers on Kubernetes the manual way (10 minutes), then with an infrastructure context layer that bridges the two systems (seconds).

Louis Fradin

Apr 8, 2026 · 6 min read

The 10 best AI SRE tools in 2026 compared by architecture, root cause analysis, remediation, and change awareness — from Anyshift's versioned graph to Resolve AI's autonomous agents.

Roxane Fischer

Mar 13, 2026 · 15 min read

AI agents start every run from scratch. ACE (Agentic Context Engineering) gives them institutional memory that evolves through use, cutting root cause analysis time by 30%.

Ghazi Felhi

Mar 11, 2026 · 8 min read

How Anyshift chose Neo4j for building a temporal infrastructure knowledge graph and lessons learned over a year of production use.

Stephane Jourdan

Feb 17, 2026 · 14 min read

The limits of telemetry-only AI approaches to SRE and why topology is the missing piece.

Roxane Fischer

Jan 27, 2026 · 8 min read

Key takeaways from the Civo Navigate SF conference.

Roxane Fischer

Mar 4, 2025 · 3 min read

A talk recording from DevOpsDays Dallas about the challenges of debugging infrastructure quickly.

Roxane Fischer

Dec 12, 2024

A featured interview on Tessl about DevOps with AI and identifying the impact zone.

Roxane Fischer

Dec 12, 2024

GenAI is everywhere. But very often, the cool and exciting demos don't work the same way in production.

Roxane Fischer

Oct 15, 2024 · 7 min read

Managing infrastructure at scale is a complex endeavor that demands meticulous planning, robust tooling, and continuous adaptation.

Roxane Fischer

Sep 19, 2024 · 4 min read

Most infrastructure debugging sessions blow past the one-hour mark for the same five structural reasons: scattered visibility across cloud accounts, missing historical state, terraform plan output that hides downstream impact, runbooks that lag the live infrastructure, and post-merger environments that no one has fully mapped. A walkthrough of each, with concrete examples and what reduces the time.

Roxane Fischer

Jul 30, 2024 · 4 min read

Three structural patterns recur in growing infrastructure orgs: single-repo bottlenecks where dozens of teams share one approval queue, ClickOps and dead IaC code that drift outside any state file, and module version fragmentation that quietly bypasses security patches. A walkthrough of each, with the practices that contain the blast radius.

Roxane Fischer

Jul 30, 2024 · 3 min read