In this project we will build a Python banking assistant agent using Strands Agents and make it observable and continuously evaluated using Langfuse — step by step. - Source: dev.to / about 19 hours ago

Langfuse is the open-source standard for LLM observability. It traces every LLM interaction — prompts, completions, latency, token usage, cost — and provides the tooling to debug, evaluate, and optimize LLM applications in production. Think of it as "Datadog for LLM calls" with a focus on prompt engineering workflows. - Source: dev.to / 20 days ago

You're monitoring production traffic. You need Langfuse / Phoenix / Helicone / Braintrust for that. Online eval is a different problem class: implicit feedback, drift detection, hallucination rates on your data, not on HellaSwag. - Source: dev.to / 30 days ago

Gateway or proxy attribution. A reverse proxy in front of the model-provider API records the request, computes the cost, and exposes per-customer breakdowns. Open-source options include Helicone, LiteLLM, Langfuse, and OpenLLMetry. Hosted equivalents serve as the AI cost observability layer for teams that want centralized visibility: LangSmith, Datadog LLM Observability, Arize Phoenix. Adds a network hop.... - Source: dev.to / about 1 month ago

Same approach works with Langfuse, Phoenix, Braintrust, or your existing OTel pipeline — the metadata.userId pattern is the universal part. - Source: dev.to / about 1 month ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 1 day ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 4 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 5 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 14 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 15 days ago