Long-Term Analysis of Langfuse LLM Traces with ClickHouse
A verification log on normalizing Langfuse Observations and Scores into ClickHouse, then using SQL to inspect model-level cost, prompt-version quality trends, and retry-driven cost increases.
Tag
#observability
The Loop Ran, but I Could Not Tell What Worked
A verification article on sending a generate, evaluate, feedback, and regenerate loop to Langfuse so the improvement path can be traced by attempt, not just by final output.
Can Langfuse Assistant Serve as an Entry Point for Operations Investigation?
Testing the Langfuse Assistant public beta against existing Sakana Fugu observations and ground truth calculated through the Public API.
Observing the Sakana Fugu API with Langfuse: Understanding Hidden Costs in Multi-Agent Systems
A hands-on report instrumenting Sakana Fugu's OpenAI-compatible API with Langfuse, measuring how latency, token consumption, and TTFT change across Level 1–3 tasks.
Observing the Black Box of a Multi-Agent API with Sakana Fugu and Langfuse
I subscribed to Sakana Fugu to understand its nature as an OpenAI-compatible API and to plan how to observe its black-box cooperative reasoning from the outside.
Eve's TUI vs HTTP Event Streams: A Side-by-Side Look at Tool Calling
A hands-on log comparing how the same weather tool call looks in Vercel's Eve agent framework when observed from the TUI versus the HTTP API, separating the developer-friendly display from the integration-friendly event stream.
Streaming Flue Observe Events to Langfuse: Monitoring an Issue Triage Agent
An experiment log where I redact Flue 1.0 Beta observe events before sending them to Langfuse, tracking the issue triage workflow's runId, model, and results.
Observing Eve TUI Execution and Tool Calls with Langfuse
A hands-on comparison of two ways to send Eve tool-calling executions to Langfuse as trace/span/generation data.
Before Using Flue: Figuring Out What This Framework Actually Is
A rough summary of how Flue thinks about harnesses, agents, workflows, skills, tools, sandboxes, and persistence — before actually running anything.
Reassessing My Morning Briefing Worker Now That Langfuse Monitors Has Arrived
I compare Langfuse Monitors with my custom Slack morning briefing worker to figure out which responsibilities should move to the official feature and which should stay custom.
How Much of Your LLM Traffic Can Cloudflare AI Gateway Actually Log?
Using Cloudflare AI Gateway as an OpenAI-compatible endpoint, I walk through its logging, payload controls, metadata, cost estimation, and OTel integration to see how far it can serve as an entry point for LLM observability.
Why Success Logs Alone Aren't Enough for Operations
A short note on log design: clean success logs alone don't help you diagnose failures or improve recovery.