Cohere class explains how to evaluate LLM apps with tracing, evals, and feedback loops
Cohere · youtube · 2026-08-04
Cohere session shows how to evaluate LLM apps in production
Laurie Voss’s session focuses on practical evaluation and observability for real AI systems. It covers how to:
- instrument an app with Arize
- trace multi-step and agentic workflows
- set up evals that catch failures
- use eval feedback to automatically improve the app
The goal is to give attendees a concrete picture of what production-grade evaluation looks like in practice.
More from coding & agent
- Codex edited a full three-camera episode end to end in under 3 hours — danshipper · 2026-08-04
- CTO says an engineer automated 60% of his job with an AI agent and got promoted — sloppenheimer · 2026-08-04
- Google Cloud says GKE Agent Sandbox lifts agent density from 61 to 274 per node — rseroter · 2026-08-04
- A tool now exports React components for agent-driven integration — evilrabbit_ · 2026-08-04
- Excalidraw shares a short guide to setting up MCP in ChatGPT Plus — Vjeux · 2026-08-04
- Merge Agent Handler adds six connectors for broader business workflow access — shensi · 2026-08-04