Damien/Notebook
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

blog/mlops-observabilite-reseau-ia #26

Merged
Damien merged 9 commits from blog/mlops-observabilite-reseau-ia into main 2026-07-19 14:36:04 +00:00
Conversation 0 Commits 9 Files Changed 58 +7 -7
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 6a7500130e - Show all commits

14
content/blog/aiops-observabilite-reseau-ia/index.en.md
View File

@@ -11,7 +11,7 @@ tags:
- AI Agents - AI Agents
--- ---
I just finished building a full observability stack on my EVPN/VXLAN lab: topology, telemetry, and near real-time visualization. While building it, I realized I wasn't just doing monitoring — I was preparing a network to one day be "seen" by an AI. This first article sets the frame for a five-part series: why observability is the mandatory prerequisite before plugging an agent into your infrastructure. I just finished building a full observability stack on my EVPN/VXLAN lab: topology, telemetry, and near real-time visualization. While building it, I realized I wasn't just doing monitoring : I was preparing a network to one day be "seen" by an AI. This first article sets the frame for a five-part series: why observability is the mandatory prerequisite before plugging an agent into your infrastructure.
<!--more--> <!--more-->
@@ -26,7 +26,7 @@ The result is a stack combining four building blocks:
- a **time-series database** for metric storage; - a **time-series database** for metric storage;
- a **visualization layer** automatically regenerated by cross-referencing topology and metrics. - a **visualization layer** automatically regenerated by cross-referencing topology and metrics.
It works today. But it's not the stack itself that made me write this article: it's a realization I had while building it. I wasn't just setting up monitoring — I was laying the foundations of a pipeline that could, one day, allow an AI agent to reason about my network. And that has a name. It works today. But it's not the stack itself that made me write this article: it's a realization I had while building it. I wasn't just setting up monitoring : I was laying the foundations of a pipeline that could, one day, allow an AI agent to reason about my network. And that has a name.
## AIOps, not MLOps ## AIOps, not MLOps
@@ -59,7 +59,7 @@ Observability, then, is not an end in itself. It's **the condition of possibilit
What helped me structure all this was thinking in stacked layers, and accepting that you don't skip a step: What helped me structure all this was thinking in stacked layers, and accepting that you don't skip a step:
1. **Infrastructure first.** Is the base data reliable, complete, up to date? Topology, metrics, logs. 1. **Infrastructure first.** Is the base data reliable, complete, up to date? Topology, metrics, logs.
2. **The model next.** What's built on top: a correlation rule, a model, an LLM — does it receive quality inputs, and can its relevance be measured over time? 2. **The model next.** What's built on top: a correlation rule, a model, an LLM : does it receive quality inputs, and can its relevance be measured over time?
3. **Agent behavior last.** Can its answers and actions be trusted, and can they be audited? 3. **Agent behavior last.** Can its answers and actions be trusted, and can they be audited?
The order isn't negotiable. An agent built on top of a shaky layer 1 inherits all its weaknesses in cascade, with the added bonus of the illusion of reliability that comes from an assertive answer by construction. You can't make up for a poorly instrumented infrastructure with a better prompt. The order isn't negotiable. An agent built on top of a shaky layer 1 inherits all its weaknesses in cascade, with the added bonus of the illusion of reliability that comes from an assertive answer by construction. You can't make up for a poorly instrumented infrastructure with a better prompt.
@@ -101,10 +101,10 @@ That's why observability comes first, and the agent comes last: not because AI i
## Resources ## Resources
### Concepts ### Concepts
- [What is AIOps?](https://www.ibm.com/think/topics/aiops) — definition and origin of the term (Gartner) - [What is AIOps?](https://www.ibm.com/think/topics/aiops) : definition and origin of the term (Gartner)
- [Model Context Protocol — official documentation](https://modelcontextprotocol.io/docs/getting-started/intro) - [Model Context Protocol : official documentation](https://modelcontextprotocol.io/docs/getting-started/intro)
- [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) — the original announcement, which frames well the problem MCP solves - [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) : the original announcement, which frames well the problem MCP solves
- [Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) — the reference article on context engineering, including the phenomenon of context window saturation - [Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) : the reference article on context engineering, including the phenomenon of context window saturation
- *Observability Engineering* (O'Reilly, 2nd edition), Charity Majors, Liz Fong-Jones, George Miranda: the field's reference book, with a chapter dedicated to the rise of agents and LLMs - *Observability Engineering* (O'Reilly, 2nd edition), Charity Majors, Liz Fong-Jones, George Miranda: the field's reference book, with a chapter dedicated to the rise of agents and LLMs
### My repo ### My repo