Latest AI and tech news
Every layer of the AI stack grew its own observability. Co-written with BetterDB: how cache decisions and LLM…
A BetterDB cache decision landed inside a LangWatch trace with zero shared code: no plugin, no hook, no agreed…
The real questions teams ask Langy about their agents, and how it answers them from your traces and code, then opens…
Langy is the AI agent LangWatch runs on its own product. A teammate distracted it with an unrelated coding question,…
We leaned into agentic coding and started shipping far more code than our review process could keep up with, so PRs…
Some of our preferences and stories on Claude and Codex at LangWatch.
A fleet of background agents runs a chunk of our engineering, each one scoped to one job and living in its own Slack…
The high-risk deadlines just moved to December 2027, but the transparency rules still land on 2 August 2026. What…
Cost per successful task is run cost divided by success rate. As model subsidies end, it becomes the number that…
Test voice agents the way you test text agents - simulated callers, traces, playback, and judge-based evaluation -…