<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Cleric blog</title><description>Insights on AI SRE, operational memory, and tribal knowledge capture from the Cleric engineering team.</description><link>https://cleric.ai</link><item><title>Jev the Decider: JIT for Agents</title><link>https://cleric.ai/blog/jev-the-decider-jit-for-agents</link><guid isPermaLink="true">https://cleric.ai/blog/jev-the-decider-jit-for-agents</guid><description>Constraining action spaces for faster, cheaper agents</description><pubDate>Fri, 25 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Roll for initiative: our week at AI Engineer World’s Fair 2026</title><link>https://cleric.ai/blog/roll-for-initiative-ai-engineer-worlds-fair</link><guid isPermaLink="true">https://cleric.ai/blog/roll-for-initiative-ai-engineer-worlds-fair</guid><description>Everyone knows agents can write code, but the open question is what happens after the code is merged.</description><pubDate>Tue, 01 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Our LLM judge scored worse than chance until we made it compare</title><link>https://cleric.ai/blog/measuring-an-sre-agent-without-ground-truth</link><guid isPermaLink="true">https://cleric.ai/blog/measuring-an-sre-agent-without-ground-truth</guid><description>We rank an agent’s investigation traces by comparing them in pairs and turning the wins into an Elo score. Grading each trace on its own scored worse than chance. Comparison made the ranking work, and it catches regressions our other evals miss.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How we verify Cleric’s production fixes</title><link>https://cleric.ai/blog/verifying-fixes</link><guid isPermaLink="true">https://cleric.ai/blog/verifying-fixes</guid><description>A correct diagnosis isn’t the same as a fixed problem. We built a verifier that checks Cleric’s fixes against the best ground truth available: production itself.</description><pubDate>Wed, 22 Jul 2026 00:00:00 GMT</pubDate></item><item><title>You’re renting your institutional knowledge</title><link>https://cleric.ai/blog/youre-renting-your-institutional-knowledge</link><guid isPermaLink="true">https://cleric.ai/blog/youre-renting-your-institutional-knowledge</guid><description>Most AI agents rent knowledge back through forward-deployed engineers. The ones worth buying compound verified memory in systems you own.</description><pubDate>Sun, 07 Jun 2026 00:00:00 GMT</pubDate></item><item><title>How Cleric uses Tailscale to securely automate software operations</title><link>https://cleric.ai/blog/how-cleric-uses-tailscale-to-securely-automate-software-operations</link><guid isPermaLink="true">https://cleric.ai/blog/how-cleric-uses-tailscale-to-securely-automate-software-operations</guid><description>An AI SRE has to access the same private resources a human engineer would. We use Tailscale to get there.</description><pubDate>Fri, 01 May 2026 00:00:00 GMT</pubDate></item><item><title>Stop Reviewing Agent Output. Start Reviewing Agent Decisions.</title><link>https://cleric.ai/blog/stop-reviewing-output-start-reviewing-decisions</link><guid isPermaLink="true">https://cleric.ai/blog/stop-reviewing-output-start-reviewing-decisions</guid><description>When agents can produce anything, the bottleneck shifts from code to judgment. You manage that by reading the decisions, not the outputs.</description><pubDate>Fri, 17 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Why Your AI SRE Needs Memory</title><link>https://cleric.ai/blog/why-your-ai-sre-needs-memory</link><guid isPermaLink="true">https://cleric.ai/blog/why-your-ai-sre-needs-memory</guid><description>Investigation logic is becoming a commodity. What won’t commoditize is operational memory: the ability to capture and persist engineering judgment.</description><pubDate>Thu, 19 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Hooks Won’t Secure 
 Your AI Agent</title><link>https://cleric.ai/blog/hooks-wont-secure-your-ai-agent</link><guid isPermaLink="true">https://cleric.ai/blog/hooks-wont-secure-your-ai-agent</guid><description>AI Agents require strict network controls in order to keep the data they handle secure.</description><pubDate>Fri, 30 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Cleric launches the first self-learning AI SRE</title><link>https://cleric.ai/blog/cleric-launches-the-first-self-learning-ai-sre</link><guid isPermaLink="true">https://cleric.ai/blog/cleric-launches-the-first-self-learning-ai-sre</guid><description>We created the first AI site reliability engineer (SRE) agent that continuously learns from every incident so software engineers can focus on building instead of firefighting.</description><pubDate>Tue, 09 Dec 2025 00:00:00 GMT</pubDate></item><item><title>The Self-Improving AI SRE</title><link>https://cleric.ai/blog/the-self-improving-ai-sre</link><guid isPermaLink="true">https://cleric.ai/blog/the-self-improving-ai-sre</guid><description>We’ve proven that our self-learning AI SRE approach works. Now we’re ready to scale.</description><pubDate>Tue, 09 Dec 2025 00:00:00 GMT</pubDate></item><item><title>Agent Engineering Is Not Software Engineering</title><link>https://cleric.ai/blog/agent-engineering-is-not-software-engineering</link><guid isPermaLink="true">https://cleric.ai/blog/agent-engineering-is-not-software-engineering</guid><description>Agent startups hire differently. ML fundamentals and domain intuition matter more than years of software engineering.</description><pubDate>Mon, 08 Dec 2025 00:00:00 GMT</pubDate></item><item><title>Cleric Named a Cool Vendor in the 2025 Gartner® Cool Vendors™ in AI for SRE and Observability</title><link>https://cleric.ai/blog/cleric-named-a-cool-vendor-in-the-2025-gartner-cool-vendors</link><guid isPermaLink="true">https://cleric.ai/blog/cleric-named-a-cool-vendor-in-the-2025-gartner-cool-vendors</guid><description>We’ve been named a Cool Vendor in the 2025 Gartner Cool Vendors in AI for SRE and Observability report. We see this as validation of our approach to building a self-improving AI SRE.</description><pubDate>Wed, 12 Nov 2025 00:00:00 GMT</pubDate></item><item><title>The Hidden Complexity of Building an AI SRE</title><link>https://cleric.ai/blog/the-hidden-complexity-of-building-an-ai-sre</link><guid isPermaLink="true">https://cleric.ai/blog/the-hidden-complexity-of-building-an-ai-sre</guid><description>Building an AI SRE isn’t just connecting an LLM to dashboards. It means reasoning through hidden dependencies, conflicting signals, and cascading failures in live production systems.</description><pubDate>Thu, 18 Sep 2025 00:00:00 GMT</pubDate></item><item><title>What’s Good for AI Agents is Good for Engineers</title><link>https://cleric.ai/blog/whats-good-for-ai-agents-is-good-for-engineers</link><guid isPermaLink="true">https://cleric.ai/blog/whats-good-for-ai-agents-is-good-for-engineers</guid><description>Engineers and AI agents work best under the same conditions. They need clean codebases, fast feedback, and clear observability.</description><pubDate>Thu, 14 Aug 2025 00:00:00 GMT</pubDate></item><item><title>9 Months In: How BlaBlaCar and Cleric Are Reimagining Incident Response with AI</title><link>https://cleric.ai/blog/how-blablacar-and-cleric-are-reimagining-incident-response-with-ai</link><guid isPermaLink="true">https://cleric.ai/blog/how-blablacar-and-cleric-are-reimagining-incident-response-with-ai</guid><description>BlaBlaCar runs one of the most advanced reliability stacks in the industry, but even strong systems hit limits as scale grows. By integrating Cleric into their alerting workflow, they’re using AI to reduce manual toil and bring faster, more consistent investigations to every team.</description><pubDate>Thu, 05 Jun 2025 00:00:00 GMT</pubDate></item><item><title>Why Your Engineers Are Drowning in Alerts</title><link>https://cleric.ai/blog/why-your-engineers-are-drowning-in-alerts</link><guid isPermaLink="true">https://cleric.ai/blog/why-your-engineers-are-drowning-in-alerts</guid><description>Modern engineering teams are overwhelmed by on-call duties and alert fatigue, leaving little time for innovation. Cleric acts as an AI SRE teammate that intelligently investigates incidents, helping engineers stay focused by offloading the cognitive burden of production support.</description><pubDate>Thu, 15 May 2025 00:00:00 GMT</pubDate></item><item><title>What is an AI SRE?</title><link>https://cleric.ai/blog/what-is-an-ai-sre</link><guid isPermaLink="true">https://cleric.ai/blog/what-is-an-ai-sre</guid><description>Engineering teams are deploying AI agents to handle production operations. This deep dive shows how AI SREs work: building system understanding, investigating issues, and driving resolution. You’ll learn their current capabilities and limitations, and how they will change the way engineering teams operate.</description><pubDate>Thu, 12 Dec 2024 00:00:00 GMT</pubDate></item><item><title>Introducing Cleric: The first autonomous AI site reliability engineer</title><link>https://cleric.ai/blog/introducing-cleric</link><guid isPermaLink="true">https://cleric.ai/blog/introducing-cleric</guid><description>We’re excited to announce that we’re building an autonomous AI SRE, called Cleric, backed by Zetta Venture Partners in a $4.3M seed round. Cleric is an AI teammate designed to autonomously manage, optimize, and heal software infrastructure.</description><pubDate>Thu, 21 Mar 2024 00:00:00 GMT</pubDate></item></channel></rss>