LangWatch Introduces Langy, an Automated AI Engineer Inside Its Platform

Jul 22, 2026
LangWatch has launched Langy, an AI agent that reads production traces, writes scenario tests, proposes code changes, and opens pull requests directly to a user’s GitHub repository.
LangWatch Introduces Langy, an Automated AI Engineer Inside Its Platform

Announced in a company blog post, LangWatch introduced Langy, an automated AI engineer built into its LangWatch platform. Langy acts as a full coding agent capable of reading production traces, generating scenario tests, proposing fixes, and submitting pull requests to a connected GitHub repository.

Langy can analyze thousands of production conversations, cluster behavior patterns, and create simulation tests to identify and address issues in deployed agents. It then drafts proposed code changes and validates them through continuous integration checks before a developer review.

The system is designed to assist both engineers and domain experts by turning plain language requests into executable tests and code updates. Langy’s operations are also monitored and evaluated within the LangWatch environment, using the same tracing and testing tools available to users. The feature is rolling out now to LangWatch teams, with additional tutorials and videos expected later in the week.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.