3+ hour, 24+ min ago   (340+ words) Langy is a full coding agent inside LangWatch: it reads your production traces, writes Scenario tests and evaluations, opens the pull request on your codebase, and proves the change in your CI. The first thing we did with it: we plugged…...

6+ day, 20+ hour ago   (581+ words) Or Codex, OpenCode, Copilot, Cursor and Pi. Capture full trace history to improve your flow, and track how much you're spending in tokens. Input I did the gcloud auth login hopefully you can continue? Input I have several design change…...

2+ week, 3+ day ago   (1166+ words) A fleet of background agents runs a chunk of our engineering, each one scoped to one job and living in its own Slack channel. We built it before Anthropic shipped the same shape as Claude Tag. On our Slack there…...

2+ week, 6+ day ago   (549+ words) Seven background agents run LangWatch's internal operations: six on Claude Code, one on OpenAI Codex. This Codex vs Claude Code comparison comes from operating both daily: what differs, where each wins, and how we decide. So when someone asks us…...

3+ week, 1+ day ago   (341+ words) 25+ first-class integrations. Python and TypeScript SDKs, every major model provider, every agent framework worth using, OpenTelemetry-native end to end. Wrap your agent in one line. Python and TypeScript, both OpenTelemetry-native. pip install langwatch · decorators for traces, evals, and prompts. npm…...

3+ week, 1+ day ago   (426+ words) Your prompts are scattered across code, notebooks, and someone’s head. LangWatch makes them one versioned source of truth: edit in a playground, ship through pull requests, A/B test in production, and tie every version back to its traces. Used…...

3+ week, 1+ day ago   (84+ words) LangWatch.ai One line of code. Every framework. Python and TypeScript SDKs that trace, evaluate, and optimize your agents in production. OpenTelemetry-native, framework-agnostic, and installable from PyPI and npm. Five minutes. From clone to first trace. Install the SDK, set…...

3+ mon, 3+ week ago   (1152+ words) Most AI agent skills ship untested. A prompt file gets written, someone eyeballs the output a few times, and it goes to production. When it breaks, you find out from users. At LangWatch, we use our own Scenario feature to…...

3+ mon, 4+ week ago   (975+ words) You built an agent. It uses tools, handles multimodal inputs, answers questions from a knowledge base. You demo it to your team and it works great. Ship it. Three days later: the satellite image analysis returns garbage NDVI estimates. The…...