# Cleric > Cleric checks every change you ship in production, catches the regressions your tests missed, takes the pager for your alerts, and brings you the cause, the evidence, and a fix PR to review. After the fix deploys, it checks that the issue is resolved. Key facts: - Engineers work with Cleric in Slack, Microsoft Teams, and the Cleric web app. Coding agents such as Claude Code and Cursor can pull Cleric's investigations over MCP. The Cleric docs have their own public MCP server. - Cleric verifies each change for up to 14 days after it deploys, and investigates alerts, monitors, and failed deploys as Issues. - Read-only by default, with write access when you're ready. SOC 2 Type II. US or EU hosting. Customer data is never used for training. - Pricing is public: plans from $700/month, paid in credits for completed work. Every trial includes 1,000 evaluation credits after activation approval, with no time limit. - Start a free trial: https://cleric.ai/start. Explore the product: https://demo.cleric.ai. Book a demo: https://cleric.ai/demo. Contact: https://cleric.ai/contact. An agent may help fill out the form, but a verified person signs in and remains accountable. Declare the company or person you represent in the optional field. Tenant setup and trial credit activation are separate approvals. Uncertain requests reach human review; contact support@cleric.ai for help. - Used by engineering teams at Fubo, LaunchGood, ASAPP, Mixmax, and Mr. Delivery. As of October 2026 (Cleric production data across customer tenants, measured Oct 15, 2026): Cleric closed 58% of alerts on its own: it investigated them, found no action was needed, and closed them without an engineer replying. Alerts across customer tenants, May 20 to Oct 15, 2026. "No action needed" is Cleric’s own verdict. Engineers rated Cleric 4.08 out of 5, with 83% of ratings at 4 or 5 stars. Optional ratings from customer engineers, Sep 15 to Oct 14, 2026. In Q3 2026, 51% of resolved incidents were fixed by applying Cleric’s suggested remediation. Resolved incidents across customer tenants, Q3 2026, as judged by Cleric’s resolution monitor. How we verify Cleric’s fixes: https://cleric.ai/blog/verifying-fixes. - Cleric is made by Agentik, Inc., founded in 2023 and based in San Francisco. CEO and co-founder: Shahram Anver. Raised $9.8M from Zetta Venture Partners and Vertex Ventures US. Named a Gartner Cool Vendor in AI for SRE and Observability (2025). Every public page has a Markdown version at the same path with `.md` appended (the home page is https://cleric.ai/index.md), and returns that Markdown when requested with `Accept: text/markdown`. Machine-readable discovery: https://cleric.ai/.well-known/api-catalog (RFC 9727). https://cleric.ai/llms-full.txt is a short briefing by topic that points to the page covering each one. ## Main pages - [Home](https://cleric.ai/index.md): What Cleric does: checks every production change, takes the pager, and brings you fixes to review. - [Product](https://cleric.ai/product.md): Change verification, alert handling, and the two ways to fix: in Cleric or with your coding agent. - [Technology](https://cleric.ai/technology.md): How Cleric investigates, verifies outcomes for up to 14 days, and improves from verified results. - [Pricing](https://cleric.ai/pricing.md): Plans from $700/month, what each unit of work costs in credits, and the pricing FAQ. - [Integrations](https://cleric.ai/integrations.md): What Cleric connects to by category, MCP for anything else, and integrations built on request. - [The verification loop](https://cleric.ai/verification-loop.md): How Cleric refines, deploys, monitors, and verifies agent-written changes in production. - [Investigation cost calculator](https://cleric.ai/calculator.md): Estimate the annual cost of production investigations for your team, with the formulas. - [Book a demo](https://cleric.ai/demo.md): Book a 30-minute demo with Cleric to discuss your production environment. - [Contact](https://cleric.ai/contact.md): How to reach sales, support, security, press, and careers, plus the mailing address. - [Briefing](https://cleric.ai/llms-full.txt): Short answers by topic, each pointing to the page that covers it - [Case study: How the World’s Leading Community-Based Travel Network is Transforming Incident Response with AI](https://cleric.ai/resources/case-studies/how-the-worlds-leading-community-based-travel-network-is-transforming-incident-response-with-ai.md): BlaBlaCar is partnering with Cleric to bring AI-driven incident response to scale. Learn how their engineering team is using AI to reduce alert fatigue, accelerate root cause analysis, and support fast, reliable operations across a complex global platform. ## Documentation The docs at https://docs.cleric.ai are the source of truth for how Cleric works, what it connects to, and how it handles data. This site does not repeat those details. Every docs page has a Markdown version at the same URL with `.md` appended, and https://docs.cleric.ai/llms.txt lists them all. For the questions below, read the page named. - [How investigations start](https://docs.cleric.ai/usage/how-investigations-work.md): Every way an issue is created, and what Cleric does from investigation to resolution - [Triggers and alert routing](https://docs.cleric.ai/setup/agents-and-triggers.md): How Slack and Microsoft Teams alerts are matched to agents, and how scheduled runs work - [Supported integrations](https://docs.cleric.ai/integrations/supported-integrations.md): Every supported integration, including Slack, Microsoft Teams, GitHub, and Kubernetes, with setup steps and the permissions each one needs. This list is authoritative - [Integrations overview](https://docs.cleric.ai/integrations/overview.md): What Cleric reads from each integration - [Security and data privacy](https://docs.cleric.ai/security/security-data-privacy.md): Access model, data retention, model providers, hosting, SOC 2 Type II, and penetration testing - [EU hosting and data processing](https://docs.cleric.ai/security/eu-hosting-data-processing.md): What is processed in the EU and what is processed in the US - [Subprocessors](https://trust.cleric.ai/?tab=subprocessors): Third parties that process customer data, listed in the Trust Center. The page needs JavaScript - [FAQ](https://docs.cleric.ai/reference/faq.md): Short answers on access, permissions, and data - [Changelog](https://docs.cleric.ai/reference/changelog.md): What has shipped and when - [Trust Center](https://trust.cleric.ai): SOC 2 report, policies, and penetration test reports. The page needs JavaScript; read Security and data privacy above for a text summary - [Vulnerability disclosure policy](https://cleric.ai/vulnerability-disclosure.md): How to report a security vulnerability to security@cleric.ai, response targets, and safe harbor - [Status](https://status.cleric.ai): Current availability and incident history for Cleric services ## MCP servers Cleric runs two MCP servers. The docs server is public and answers questions about how Cleric works. The product server works with a customer's own Cleric data and needs that customer's instance URL and an API key. - [Cleric Docs MCP Server](https://docs.cleric.ai/~gitbook/mcp): Public, no sign-in, streamable HTTP. Search and read the Cleric docs from any MCP client. Add this URL as an HTTP MCP server - [Cleric MCP Server setup](https://docs.cleric.ai/integrations/mcp.md): The product MCP server runs on each customer's instance at https://.app.cleric.ai/mcp and authenticates with a personal API key. Covers setup in Claude Code and Cursor, and every tool and prompt - [MCP discovery file](https://cleric.ai/.well-known/mcp.json): Machine-readable pointer to both servers ## Solutions - [Alert Investigation](https://cleric.ai/solutions/alert-investigation.md): Automate alert investigations for fast, clear answers - [Cloud Infrastructure](https://cleric.ai/solutions/cloud-infrastructure.md): Diagnose failures in any cloud environment - [Debug Deployment Failures](https://cleric.ai/solutions/deployment-failures.md): Catch and fix bad deploys before they escalate - [Fix Recommendation](https://cleric.ai/solutions/fix-recommendation.md): Get precise fix recommendations tailored to your stack - [For Engineering Leaders](https://cleric.ai/solutions/for-engineering-leaders.md): Resilient systems, happier teams - [For Engineers](https://cleric.ai/solutions/for-engineers.md): Stay in flow, let Cleric take the hit - [For SREs](https://cleric.ai/solutions/for-sres.md): Make on-call suck less - [Incident Triage](https://cleric.ai/solutions/incident-triage.md): Filter noise for critical incident triage - [Kubernetes](https://cleric.ai/solutions/kubernetes-environments.md): Find and fix Kubernetes failures fast - [Microservices](https://cleric.ai/solutions/microservices-architectures.md): Trace and resolve issues across services - [On-Call Automation](https://cleric.ai/solutions/on-call-automation.md): Automate on-call response to slash burnout - [Root Cause Analysis](https://cleric.ai/solutions/root-cause-analysis.md): Uncover root causes with clear, evidence-backed analysis ## Comparisons - [Compare Cleric](https://cleric.ai/compare.md): How Cleric compares with the AI agents built into AWS, Azure, Datadog, Grafana, and PagerDuty. - [Cleric vs AWS DevOps Agent](https://cleric.ai/compare/aws.md): AWS gives you an agent. Cleric gives you a learning system for production. - [Cleric vs Azure SRE Agent](https://cleric.ai/compare/azure.md): Azure gives you an Azure agent. Cleric gives you a learning system for production. - [Cleric vs Bits AI SRE](https://cleric.ai/compare/datadog.md): Bits AI SRE investigates inside Datadog. Cleric investigates all of production. - [Cleric vs Grafana Assistant](https://cleric.ai/compare/grafana.md): Grafana investigates inside Grafana. Cleric gives you a learning system for production. - [Cleric vs PagerDuty SRE Agent](https://cleric.ai/compare/pagerduty.md): PagerDuty gives you an incident agent. Cleric gives you a learning system for production. ## Optional - [Blog](https://cleric.ai/blog.md): All Cleric blog posts, newest first. - [Michael Saah](https://cleric.ai/blog/author/michael-saah.md): Blog posts by Michael Saah from the Cleric team. - [Cleric](https://cleric.ai/blog/author/cleric.md): Blog posts by Cleric from the Cleric team. - [Peter Richens](https://cleric.ai/blog/author/peter-richens.md): Blog posts by Peter Richens from the Cleric team. - [Shahram Anver](https://cleric.ai/blog/author/shahram-anver.md): Blog posts by Shahram Anver from the Cleric team. - [Willem Pienaar](https://cleric.ai/blog/author/willem-pienaar.md): Blog posts by Willem Pienaar from the Cleric team. - [Jev the Decider: JIT for Agents](https://cleric.ai/blog/jev-the-decider-jit-for-agents.md): Constraining action spaces for faster, cheaper agents - [Roll for initiative: our week at AI Engineer World’s Fair 2026](https://cleric.ai/blog/roll-for-initiative-ai-engineer-worlds-fair.md): Everyone knows agents can write code, but the open question is what happens after the code is merged. - [Our LLM judge scored worse than chance until we made it compare](https://cleric.ai/blog/measuring-an-sre-agent-without-ground-truth.md): 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. - [How we verify Cleric’s production fixes](https://cleric.ai/blog/verifying-fixes.md): 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. - [You’re renting your institutional knowledge](https://cleric.ai/blog/youre-renting-your-institutional-knowledge.md): Most AI agents rent knowledge back through forward-deployed engineers. The ones worth buying compound verified memory in systems you own. - [How Cleric uses Tailscale to securely automate software operations](https://cleric.ai/blog/how-cleric-uses-tailscale-to-securely-automate-software-operations.md): An AI SRE has to access the same private resources a human engineer would. We use Tailscale to get there. - [Stop Reviewing Agent Output. Start Reviewing Agent Decisions.](https://cleric.ai/blog/stop-reviewing-output-start-reviewing-decisions.md): When agents can produce anything, the bottleneck shifts from code to judgment. You manage that by reading the decisions, not the outputs. - [Why Your AI SRE Needs Memory](https://cleric.ai/blog/why-your-ai-sre-needs-memory.md): Investigation logic is becoming a commodity. What won’t commoditize is operational memory: the ability to capture and persist engineering judgment. - [Hooks Won’t Secure Your AI Agent](https://cleric.ai/blog/hooks-wont-secure-your-ai-agent.md): AI Agents require strict network controls in order to keep the data they handle secure. - [Cleric launches the first self-learning AI SRE](https://cleric.ai/blog/cleric-launches-the-first-self-learning-ai-sre.md): 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. - [The Self-Improving AI SRE](https://cleric.ai/blog/the-self-improving-ai-sre.md): We’ve proven that our self-learning AI SRE approach works. Now we’re ready to scale. - [Agent Engineering Is Not Software Engineering](https://cleric.ai/blog/agent-engineering-is-not-software-engineering.md): Agent startups hire differently. ML fundamentals and domain intuition matter more than years of software engineering. - [Cleric Named a Cool Vendor in the 2025 Gartner® Cool Vendors™ in AI for SRE and Observability](https://cleric.ai/blog/cleric-named-a-cool-vendor-in-the-2025-gartner-cool-vendors.md): 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. - [The Hidden Complexity of Building an AI SRE](https://cleric.ai/blog/the-hidden-complexity-of-building-an-ai-sre.md): 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. - [What’s Good for AI Agents is Good for Engineers](https://cleric.ai/blog/whats-good-for-ai-agents-is-good-for-engineers.md): Engineers and AI agents work best under the same conditions. They need clean codebases, fast feedback, and clear observability. - [9 Months In: How BlaBlaCar and Cleric Are Reimagining Incident Response with AI](https://cleric.ai/blog/how-blablacar-and-cleric-are-reimagining-incident-response-with-ai.md): 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. - [Why Your Engineers Are Drowning in Alerts](https://cleric.ai/blog/why-your-engineers-are-drowning-in-alerts.md): 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. - [What is an AI SRE?](https://cleric.ai/blog/what-is-an-ai-sre.md): 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. - [Introducing Cleric: The first autonomous AI site reliability engineer](https://cleric.ai/blog/introducing-cleric.md): 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. - [AI SRE Glossary](https://cleric.ai/glossary.md): Key concepts in AI SRE, operational memory, and tribal knowledge capture. - [What is a Self-Learning AI SRE?](https://cleric.ai/glossary/what-is-a-self-learning-ai-sre.md): A self-learning AI SRE is an AI SRE that improves investigation quality over time by learning from prior investigations, engineer feedback, and environment changes. The operative phrase is over time. Not every agent that uses an LLM does this. - [What is Alert Fatigue?](https://cleric.ai/glossary/what-is-alert-fatigue.md): Alert fatigue is what happens when engineers are exposed to so many low-value alerts that they stop trusting the alert stream. The problem is not only noise. It is the learned belief that most interruptions are not worth the interruption. - [What is an AI SRE?](https://cleric.ai/glossary/what-is-an-ai-sre.md): An AI SRE is an AI agent used in production operations to investigate issues, gather evidence across tools, explain likely causes, and surface emerging risks before they become incidents. Alerts are one input, not the whole job. - [What is Cross-Service Incident Correlation?](https://cleric.ai/glossary/what-is-cross-service-incident-correlation.md): Cross-service incident correlation is the work of connecting alerts across multiple services to determine whether they are separate problems or different symptoms of the same underlying issue. In distributed systems, getting this wrong wastes a lot of engineering time. - [What is Episodic Memory in AI SRE?](https://cleric.ai/glossary/what-is-episodic-memory-in-ai-sre.md): Episodic memory is Cleric’s term for the stored history of past investigations: what happened, what was checked, what the evidence showed, and how engineers corrected the system. It is how repeated incidents stop looking brand new. - [What is Investigation Memory?](https://cleric.ai/glossary/what-is-investigation-memory.md): Investigation memory is the retained history of how prior incidents were investigated: the alerts, hypotheses, evidence, findings, and corrections. It is the case history an AI SRE uses so recurring problems do not require full rediscovery. - [What is Operational Memory?](https://cleric.ai/glossary/what-is-operational-memory.md): Operational memory is Cleric’s term for the operational context an AI SRE accumulates over time: environment structure, past investigations, and debugging procedures. The point is simple. The system should not start from zero on every alert. - [What is Procedural Memory in AI SRE?](https://cleric.ai/glossary/what-is-procedural-memory-in-ai-sre.md): Procedural memory is Cleric’s term for reusable debugging know-how: the investigation order, checks, and heuristics teams use on recurring problem types. It is not just what the system knows. It is how the system approaches the work. - [What is Root Cause Analysis?](https://cleric.ai/glossary/what-is-root-cause-analysis.md): Root cause analysis (RCA) is the work of identifying the conditions that actually caused an incident instead of stopping at the symptom that surfaced first. In production, that often means following a causal chain across code, configuration, infrastructure, and timing. - [What is Semantic Memory in AI SRE?](https://cleric.ai/glossary/what-is-semantic-memory-in-ai-sre.md): Semantic memory is Cleric’s term for the infrastructure and environment context an AI SRE uses during investigations: services, dependencies, ownership, configuration, and recent changes. It is the part that helps the system orient before it starts guessing. - [What is Tribal Knowledge in SRE?](https://cleric.ai/glossary/what-is-tribal-knowledge-in-sre.md): Tribal knowledge in SRE is the undocumented operational judgment engineers accumulate about a production environment: what is normal, what is dangerous, and where to look first when something breaks. It is useful, fragile, and expensive when it stays trapped in people’s heads. - [Blog RSS feed](https://cleric.ai/blog/rss.xml): New blog posts as they are published - [Resources](https://cleric.ai/resources.md): Case studies, webinars, podcasts, events, and reports - [About](https://cleric.ai/about.md): Cleric’s mission, origin, team, funding, and investors. - [Careers](https://cleric.ai/careers.md): Open roles at Cleric (in person, San Francisco), what the team is building, and benefits. - [Executive briefing](https://cleric.ai/executive-deck.md): Five-slide executive deck: what changes, how Cleric works, the capacity math, and the next step.