Cleric, a startup that provides artificial intelligence teammates for production engineering, today announced the launch of its AI-powered site reliability engineer agent, capable of continuously learning from incidents to give administrators a jumpstart on resolving issues.

Alongside the agent launch, the company announced it has raised $9.8 million, led by Vertex Ventures US and Zetta Venture Partners.

The company’s system is integrated deeply into site reliability monitoring and platform architecture. When an incident happens, it acts immediately to investigate and uncover root causes by thinking through them, forming hypotheses and testing them against its knowledge. Only once it comes to a confident conclusion does it publish its findings to Slack with links to relevant evidence.

“We designed Cleric to reason about systems the way experienced engineers do: by correlating context across logs, metrics and configurations, not just reacting to individual alerts,” said Willem Pienaar, Cleric’s co-founder and chief technology officer.

For extremely tricky cases, Cleric doesn’t stop at delivering findings. Engineering teams can chat with Cleric’s AI system to guide its reasoning through back-and-forth conversation or examine detailed diagnostics to collaborate using their own lived experience.

The system uses confidence scores and learns from feedback, improving its capabilities every time it interacts with the platform and other engineers.

“Any system operating at scale needs to adapt continuously,” said co-founder and Chief Executive Shahram Anver. “Production isn’t static. It’s a living environment. Cleric learns from every incident, alert and human decision to evolve how it supports operations.”

The company stated that site engineers are frequently overwhelmed by alerts, tickets and incidents from production. Although tools exist to help prioritize these events, the subsequent investigation can exhaust even the most dedicated teams. Keeping systemwide information and historical knowledge constantly in mind can lead to burnout.

The new site reliability engineering agent keeps all of this operational data in its “mind,” providing incident response teams with everything they need to trace incidents and resolve them.

Cleric’s AI doesn’t require businesses to change anything about their setups to integrate it. It will work with existing observability systems, continuous integration and deployment platforms and incident tooling. This includes platforms such as Datadog Inc. and Grafana Labs and PagerDuty Inc.

Early adopters of Cleric’s platform revealed that its capabilities freed up 20% to 30% of engineering capacity lost to repetitive troubleshooting.

Community-based travel app BlaBlaCar from Comuto SA, a customer of Cleric since early 2025, reported that the platform helped resolve not only day-to-day issues faster but also helped unveil insights into long-term reliability improvements. “Our goal isn’t complete alert coverage,” said Maxime Fouilleul, head of infrastructure and operations at BlaBlaCar. “It’s intelligent coverage, using Cleric’s insights to proactively eliminate systemic issues.”

Cleric said now that its product has proven itself valuable in real-world production environments, learning from high-frequency operational data, it’s ready to scale. With the new funding, the Cleric is rolling out to more customers and expanding its research and development team in San Francisco to deepen integrations with more observability and infrastructure platforms.

Images: Cleric