Beyond the Chatbot: The Real Impact of LLMs on Observability
summary
Examines how large language models (LLMs) affect observability by evaluating what currently works and what still needs improvement. Covers adapting telemetry signals for language models, the potential of LLM-based agents, and practical implementation insights from Grafana Labs that separate hype from concrete opportunities.
AI-written summary · about
chapters (11)
- 0:00LLMs impact on observability
- 1:44Autonomous agents in observability
- 3:08Log analysis with LLMs
- 5:57LLMs for structured data
- 7:00LLM limits in traces
- 8:03AI dashboards and queries
- 9:53Automatic incident summaries
- 11:58Prompt engineering to action
- 13:07MCP protocol integration
- 15:14Agents for incident response
- 16:41Conclusion
related talks
06mObservability for Large Language Models
33mOpening Keynote: LLMs, between fantasy and reality - the poin...
49mA Practical Approach to Using LLMs: Peculiarities and Pitfalls
15mKeynote: Into the Black Box: Observability in the Age of LLMs
51mTowards a Pragmatic Understanding of Large Language Models
23mObservability for LLMs: Understanding What’s Happening Under the Hood
49mLLMops: what's beyond ChatGPT and how you can deploy it
17mArchitecting LLM-Based Chatbots using free open-source LLMs