# [[Actually Useful AI Observability Explained - AI at Grafana]]
<iframe width="560" height="315" src="https://www.youtube.com/embed/0000000" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
plugins:: ""
Related:: ""
## Pre-production
### Thumbnail
![[Actually Useful AIOps Explained - AI at Grafana.png]]
### Title
1. actually useful ai for observability (51)
2. how ai is changing observability (24)
3. ai-assisted observability (19)
4. ai observability (63)
5. ai for observability (48)
6. ai and observability (69)
7. ai for observability explained (40)
8. aiops (66)
9. agentic engineering for observability (47)
10. agentic ai for observability (20)
11. ai sre (69)
12. AI-assisted observability (19)
13. observability with ai (71)
14. genai observability (16)
15. ai observability explained (37)
16. agentic observability (18)
17. agentic engineering (54)
18. ai + observability (77)
### Hook
- The AI landscape is chaotic af (see [[OpenClaw]]'s name changes in 48 hours)
### Structure
#### Intro
- What is AI Observability?
- It could be:
- Observability of an AI app
- AI-assisted Observability
- What problem is it trying to solve?
#### AI Observability
- Observing AI systems (non-deterministic)
- Watch this Grafana ❤️🔥 OpenTelemetry Community Call about Observability for GenAI apps
#### AI-assisted Observability
- Learning + Doing (teaching you to drive + driving)
##### Learning
- LLMs, but also AI-assisted Pathfinder guides
- Assistant - Learn mode
##### Doing: The Autonomy Gradient AI Observability
![[Developer Advocacy for Grafana Assistant.svg]]
###### Interface
- [[Generative AI]]
- Can be a chat conversation with an LLM where it gives you answers through text.
- Can be a visual interface created by an LLM, such as how Assistant can create dashboards for you
- Will ChatGPT/other LLMs be the interface for everything? No.
- Did everything get reduced to an API? No.
- We will have both.
###### Analysis
###### Forecasting
###### Orchestration
- [[Agentic AI]]
###### Optimization
###### Continuous Control
###### Co-design
#### An AI SRE
- Is a fully autonomous AI SRE possible? No.
- This has happened over and over again in technology. Did
- Drivers will still matter.
- Instead, it's more productive to ask: What can you do in the AI space that is futureproof?
- If removing AI breaks your observability system, you're doing it wrong. Your telemetry should outlive your AI experiments.
- Anchor on Observability primitives ([[Telemetry]] signals) not AI tools
- Use replaceable AI layers - or make it someone else's problem to switch out and test LLM versions as needed.
-
### Outro
AI will be transformative, but success hinges on making that transformation safe, durable, and trustworthy.
### Related videos and resources
### Pinned comment
```
```
### Timestamps
00:00 Intro
## Post-production
- [ ] Create captions using Rev, then edit them.
- [ ] Take a thumbnail photo and create one for YouTube (1280 x 720).
- [ ] Add description.
- [ ] Include the title and any keywords in the first few sentences, but in a natural way.
- [ ] Add related videos and resources as links.
- [ ] Add end screen.
- [ ] Add cards if necessary.
- [ ] Add chapters/timestamps for YouTube if longer than 5 minutes.
- [ ] Add mid-roll ads/check monetization settings.
- [ ] Add pinned comment.
- [ ] Post video preview on Patreon.
- [ ] Schedule on YouTube.
- [ ] Add video to relevant playlist(s), or create a playlist if necessary.
- [ ] Schedule on Mastodon.
- [ ] Create a blog post on [site](https://nicolevanderhoeven.com).
- [ ] Add to [video-database](obsidian://open?vault=obsidian-playbook&file=video-database%2FVideo%20database).
- [ ] Add to other notes in my vault as appropriate.