**Experiment Goal:** Determine if LLMs can autonomously perform root cause analysis (RCA) on live application
Five LLMs were given access to OpenTelemetry data from a demo application,:
* They were prompted with a naive instruction: "Identify the issue, root cause, and suggest solutions."
* Four distinct anomalies were used, each with a known root cause established through manual investigation.
* Performance was measured by: accuracy, guidance required, token usage, and investigation time.
* Models: Claude Sonnet 4, OpenAI GPT-o3, OpenAI GPT-4.1, Gemini 2.5 Pro
* **Autonomous RCA is not yet reliable.** The LLMs generally fell short of replacing SREs. Even GPT-5 (not explicitly tested, but implied as a benchmark) wouldn't outperform the others.
* **LLMs are useful as assistants.** They can help summarize findings, draft updates, and suggest next steps.
* **A fast, searchable observability stack (like ClickStack) is crucial.** LLMs need access to good data to be effective.
* **Models varied in performance:**
* Claude Sonnet 4 and OpenAI o3 were the most successful, often identifying the root cause with minimal guidance.
* GPT-4.1 and Gemini 2.5 Pro required more prompting and struggled to query data independently.
* **Models can get stuck in reasoning loops.** They may focus on one aspect of the problem and miss other important clues.
* **Token usage and cost varied significantly.**
**Specific Anomaly Results (briefly):**
* **Anomaly 1 (Payment Failure):** Claude Sonnet 4 and OpenAI o3 solved it on the first prompt. GPT-4.1 and Gemini 2.5 Pro needed guidance.
* **Anomaly 2 (Recommendation Cache Leak):** Claude Sonnet 4 identified the service restart issue but missed the cache problem initially. OpenAI o3 identified the memory leak. GPT-4.1 and Gemini 2.5 Pro struggled.
Five LLMs were given access to OpenTelemetry data from a demo application,:
* They were prompted with a naive instruction: "Identify the issue, root cause, and suggest solutions."
* Four distinct anomalies were used, each with a known root cause established through manual investigation.
* Performance was measured by: accuracy, guidance required, token usage, and investigation time.
* Models: Claude Sonnet 4, OpenAI GPT-o3, OpenAI GPT-4.1, Gemini 2.5 Pro
* **Autonomous RCA is not yet reliable.** The LLMs generally fell short of replacing SREs. Even GPT-5 (not explicitly tested, but implied as a benchmark) wouldn't outperform the others.
* **LLMs are useful as assistants.** They can help summarize findings, draft updates, and suggest next steps.
* **A fast, searchable observability stack (like ClickStack) is crucial.** LLMs need access to good data to be effective.
* **Models varied in performance:**
* Claude Sonnet 4 and OpenAI o3 were the most successful, often identifying the root cause with minimal guidance.
* GPT-4.1 and Gemini 2.5 Pro required more prompting and struggled to query data independently.
* **Models can get stuck in reasoning loops.** They may focus on one aspect of the problem and miss other important clues.
* **Token usage and cost varied significantly.**
**Specific Anomaly Results (briefly):**
* **Anomaly 1 (Payment Failure):** Claude Sonnet 4 and OpenAI o3 solved it on the first prompt. GPT-4.1 and Gemini 2.5 Pro needed guidance.
* **Anomaly 2 (Recommendation Cache Leak):** Claude Sonnet 4 identified the service restart issue but missed the cache problem initially. OpenAI o3 identified the memory leak. GPT-4.1 and Gemini 2.5 Pro struggled.
Real-time observability and analytics platform for local LLMs, with dashboard and API.
A guide to building a robust logging system in Python, covering structured logging, log levels, handlers, formatters, filters, and integrating logging with modern observability practices.
This article compares three telemetry pipeline solutions – Cribl, Edge Delta, and DIY OpenTelemetry – based on scalability, performance, data management, intelligence, and cost. It details the strengths and weaknesses of each approach to help organizations choose the best solution for their observability and security data needs.
.conf25 offers hundreds of sessions led by industry experts designed to enhance your career. The event is scheduled for September 8-11, 2025 in Boston, Massachusetts.
This article demonstrates how to use the attention mechanism in a time series classification framework, specifically for classifying normal sine waves versus 'modified' (flattened) sine waves. It details the data generation, model implementation (using a bidirectional LSTM with attention), and results, achieving high accuracy.
Traceloop's observability tool for LLM applications is now generally available. The company also announced a $6.1 million seed funding round. The platform extends OpenTelemetry to provide better observability for LLM applications, offering insights into model behavior and facilitating experimentation.
Grafana Labs have launched Grafana 12, bringing significant updates to its visualisation and dashboarding platform. Several new key features are now generally available, including Git Sync, dynamic dashboards, and improvements to Drilldown. A central feature is a new collection of observability-as-code tools, designed to help teams automate observability workflows.
This paper introduces Toto, a time series forecasting foundation model with 151 million parameters, and BOOM, a large-scale benchmark for observability time series data. Toto uses a decoder-only architecture and is trained on a large corpus of observability, open, and synthetic data. Both Toto and BOOM are open-sourced under the Apache 2.0 License.
Datadog announces the release of Toto, a state-of-the-art open-weights time series foundation model, and BOOM, a new observability benchmark. Toto achieves SOTA performance on observability metrics, and BOOM provides a challenging dataset for evaluating time series models in the observability domain.
