LangFuse X: Your Langfuse Traces Are Already Yours. Here Is How You Get Them Out.
Last Updated on October 29, 2026 by Editorial Team
Author(s): Rick Hightower
Originally published on Towards AI.
Part 10: Langfuse is open only if you can query and export traces without living in the UI; the Public API and a boring nightly job are how Harbor Desk actually owns its data.
Langfuse is open only if you can query and export traces without living in the UI; the Public API and a boring nightly job are how Harbor Desk actually owns its data.
The article explains that Langfuse’s value comes from owning the read/export path outside the UI: Harbor Desk uses the Project-level Public API (/api/public) with Basic Auth (public key as username, secret key as password) to pull traces, observations, scores, and prompt versions. It clarifies the three different API surfaces so you don’t query the wrong one, recommends using the SDK “api” namespace (with high-performance defaults like observations, scores_v3, and metrics, and warns against deprecated v2/legacy endpoints), and highlights ingest lag so you can’t reliably flush-and-immediately-query in the same process. It then describes the core production pattern—a nightly job that filters yesterday’s failing tickets (e.g., mentions-policy false) and opens a review queue using observations plus scores_v3—and contrasts this with other “exits” like UI export, blob/S3-style exports for warehouses, CLI, and MCP/agent skills. Finally, it gives a “do this today” checklist (authenticate once, query a real ticket, prove lag, sketch the nightly filter, stay off api.legacy) and closes by framing future production concerns (masking, sampling, retention, and cloud vs self-host) as easier once the trusted read path is automated.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ AI Engineering For Production — our new book, coming before the end of 2026. Join the waitlist.
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
![[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector](https://miro.medium.com/v2/resize:fit:700/1*-Doos2nmUT3FPZ-Qxbk3Hw.png "[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector")
