CoreWeave launches Agent Lens: clusters failing agent traces and turns them into tests, with Claude Code integration
_ScottCondron · x · 2026-10-01
CoreWeave launched Agent Lens in public preview within CoreWeave Forge. It ingests an agent's OpenTelemetry corpus with no config, clusters conversations that fail the same way, and links each cluster to the traces proving it. Teams can turn a cluster into tests, run a fix against the set, and ship when it wins — a loop CoreWeave says Claude Code can run easily over MCP. The tool targets the full improvement loop from tracing to evals, with role-specific views for PMs defining quality and engineers drilling into traces, tool calls, and latency, aimed at enterprise-scale agent reliability.
Related event: CoreWeave Launches Agent Lens for AI Agent Observability(2 posts)→
More from coding & agent
- Hybris MCP Server lets AI assistants manage SAP Commerce Cloud instances — modelcontextprotocol · 2026-10-01
- cua-speedrun: CMU benchmark shows 4.4x speed gap between equal-scoring computer-use agents — arankomatsuzaki · 2026-10-01
- M-Anchor: a deterministic, zero-LLM Python gate that blocks unsupported LLM record updates — Informal-Winter-3190 · 2026-10-01
- Dev Burns Through Claude Weekly Quota in Under Two Days on Opus 4.5 Alone — yihui_indie · 2026-10-01
- Split coding workflow: Opus 5.5 xhigh for planning, Sol 6.1 high for the bulk of coding — haider1 · 2026-10-01
- FV expert: AI folks' view of formal verification is 15 years out of date — tianyin_xu · 2026-10-01