Want to find out what we've been up to? Check out this deep dive with Cerebral Valley and Shahram! cerebralvalley.ai/blog/cleric-yo…

Similar to an SRE teammate, Cleric's AI agent helps engineering teams debug complex production issues.  See how they used LangSmith to resolved incidents by: 📖 Comparing investigation strategies side-by-side 📊 Tracking performance to improve resolution times 🤓 Learning

Building a reliable AI agent requires evaluating both online and offline performance data. LangSmith has made this a breeze. Plus Harrison Chase and the team have been super responsive to our feedback!

So what exactly *is* an AI SRE? We wrote a deep dive on how AI agents can help with production operations - investigating issues, diagnosing problems, and driving them to resolution. cleric.io/blog/what-is-a… cc Jeremy Lewi Niall Murphy Daniel Jeffries Rachel Chalmers Harrison Chase

In this episode of the MLOps Community Podcast, we chat with Willem Pienaar about how his team at Cleric is building an AI SRE that helps engineering teams autonomously root cause production applications.

A lot of AI products are hitting a performance wall. Join me at @DataCouncilAI tomorrow, where I introduce Labyrinth - the simulation environment we built at Cleric to create deterministic tests for complex non-deterministic environments. datacouncil.ai/talks25/chaos-…

We’ll be at the AI Agent Builder Summit in SF on Sept 4. Cleric automates incident investigations in Slack so teams resolve alerts faster with verifiable results. Come see the demo. luma.com/aiagentsummit

Patrick Debois at Cleric’s roundtable: tests, linters, and execution don’t guarantee LLM code is correct. It helps speed, not reliability. How do you verify outputs? youtube.com/shorts/rvx_Rr9…

Live at the AI Agent Builder Summit in SF. Cleric automates incident investigations and posts verified findings in Slack. Stop by for a demo.

Great conversations at the AI Agent Builder Summit. Cleric automates investigations and delivers verified findings in Slack to cut MTTR. Missed us? Book a demo here: cleric.ai/demo

great chart - Patrick Debois did a great talk on this same topic recently - youtu.be/KAWymeija2Y?si…

Heading to NYC for AI Agent World Tour next week. Excited to meet other teams building with agents. Who’s going? luma.com/agentsummitNYC

An autonomous, self-improving AI SRE agent? At our upcoming webinar, learn more about AI SRE challenges, how engineers can change their approach, and the ways Cleric empowers them to do so: Tues, Dec 16, 4pm ET/1pm PT REGISTER: cleric.ai/webinar

How do you track AI SRE success? At Cleric, we look at trust (via a rating system) and engagement (whether you’re coming back to the tool). Learn more from our webinar → cleric.ai/webinar

AI SRE doesn't replace engineers. Instead, it gives engineers their time back. In our webinar, we talked about Cleric's approach to creating a self-learning AI SRE, and how it actually works in production. → cleric.ai/webinar