Three Letters of Reliability: SLI, SLO, and SLA
SLI, SLO, and SLA: let's break down how they differ and how they relate to each other.
more
-
-
Cost per Token Is Becoming Outdated
When it comes to the cost of AI, the first question is almost always the same: how much does a token cost? It's a logical question, especially when choosing between models. But the more complex AI systems become, the less the price of a token says about the real cost of a task.
more
-
The Second‑Look Effect: How Neural Networks Are Actually Changing the Designer's Work
Can AI fully take over routine tasks, and at which stages does it prove useless? Our design team conducted a large‑scale internal audit.
more
-
When Code Writes Itself: The Story of a Virtual Team
Noveo VirtualAgent - not just another AI coder, but a multi‑agent system with shared memory that automatically takes tasks from Jira, writes code, reviews it, and keeps documentation up to date.
more
-
DevOps for Writers: Git and CI/CD Instead of Word and Google Docs
At Noveo, we don't just build software — we build systems. For anything. For everything. From enterprise platforms to... a book.
more
-
Grafana monitoring with Docker. Part 3 - Metrics with Prometheus
Logs — check ✅, traces — check ✅, metrics are next! Andrey, Senior Developer at Noveo, continues his series of posts on monitoring.
more
-
Grafana monitoring with Docker. Part 2 - Traces with Tempo
Having configured Grafana, Loki, and Alloy for log gathering, we will move on to configuring tracing with Tempo.
more
-
How to Build Your Own AI Programming Agent: An Overview of Approaches
In this post, we'll break down the architecture of modern agents, explore approaches to building them — from ready‑made frameworks to building from scratch — and offer practical recommendations.
more
Load more
