# Observability Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/observability
> Markdown URL: https://aitinkerers.org/technologies/observability.md
> Technology record last updated: 2026-02-28T14:48:13Z
> Generated: 2026-09-20T21:48:41Z

The ability to infer a system's internal state from its external telemetry (metrics, logs, traces), allowing operators to diagnose 'unknown unknowns' in dynamic, distributed environments.

Observability is a system property: it dictates how well you can understand a complex application's internal state by examining its outputs. We achieve this by collecting and correlating the three pillars of telemetry data: **Metrics** (time-series data like request latency and CPU utilization), **Logs** (discrete, timestamped events), and **Traces** (the end-to-end path of a request across services). This holistic view is critical for modern microservice and cloud-native architectures, enabling engineering teams to move beyond simple monitoring (known failures) to rapidly pinpointing the root cause of novel, unanticipated issues (unknown unknowns) in production.

- Official technology site: https://opentelemetry.io/docs/concepts/observability-primer/
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [From Local Agent to Emergent Data Scientist](https://nurnberg.aitinkerers.org/talks/rsvp_T0ZyJGZ5BE0)

A local agent gets a stateful Jupyter kernel and a DuckDB database connection instead of fixed tools, giving it a full Python code execution environment. It has to predict outcomes for head and neck cancer patients from cohort data alone, with the current patient's outcome hidden. What I didn't design: the agent trained its own ML models and weighted their outputs based on the patient's individual features, unprompted. Live: I'll show agent traces and behavior in Logfire, walk through the system design, and explain the sandboxed code execution setup.

- Event context: AI Tinkerers Nürnberg: June Meetup (Community Hub) — 2026-06-24 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_T0ZyJGZ5BE0

### [Keeping an "AI" on LLMs with Langfuse](https://london.aitinkerers.org/talks/rsvp_Nc7KY-wgPWg)

As we've been building with LLMs at nPlan, we've often struggled to have good insight into what's happening when we deploy LLMs in the wild. Our client data is quite sensitive so I set out to explore solutions we could self-host and Langfuse was chosen as our LLM observability tool! It gives us fantastic visibility into all our user's questions, what inputs go into LLMs, what data is fetched, and much more. In this talk, I would chat through my experience setting up Langfuse and the benefits we've gotten from LLM observability already.

- Event context: AI Tinkerers London - July Meetup — 2024-07-09 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_Nc7KY-wgPWg

## Related Technologies

- [Agent Orchestration](https://aitinkerers.org/technologies/agent-orchestration) ([Markdown](https://aitinkerers.org/technologies/agent-orchestration.md)) — 2 public demos
- [DuckDB](https://aitinkerers.org/technologies/duckdb) ([Markdown](https://aitinkerers.org/technologies/duckdb.md)) — 9 public demos
- [Jupyter](https://aitinkerers.org/technologies/jupyter) ([Markdown](https://aitinkerers.org/technologies/jupyter.md)) — 8 public demos
- [Jupyter kernel](https://aitinkerers.org/technologies/jupyter-kernel) ([Markdown](https://aitinkerers.org/technologies/jupyter-kernel.md)) — 1 public demo
- [Langfuse](https://aitinkerers.org/technologies/langfuse) ([Markdown](https://aitinkerers.org/technologies/langfuse.md)) — 13 public demos
- [llama](https://aitinkerers.org/technologies/llama) ([Markdown](https://aitinkerers.org/technologies/llama.md)) — 48 public demos
- [LLMs](https://aitinkerers.org/technologies/llms) ([Markdown](https://aitinkerers.org/technologies/llms.md)) — 83 public demos
- [Logfire](https://aitinkerers.org/technologies/logfire) ([Markdown](https://aitinkerers.org/technologies/logfire.md)) — 2 public demos
- [nPlan](https://aitinkerers.org/technologies/nplan) ([Markdown](https://aitinkerers.org/technologies/nplan.md)) — 1 public demo
- [Pydantic AI](https://aitinkerers.org/technologies/pydantic-ai) ([Markdown](https://aitinkerers.org/technologies/pydantic-ai.md)) — 7 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Self-hosting](https://aitinkerers.org/technologies/self-hosting) ([Markdown](https://aitinkerers.org/technologies/self-hosting.md)) — 2 public demos