Sold by: Cleric
Cleric is an AI SRE that prevents production incidents. It checks every production change under real traffic, takes on-call by triaging alerts and closing false positives, and brings your team the root cause, the evidence and a fix PR to review. Read-only by default and SOC 2 Type II compliant.
Overview
Image
Issues from alerts and changes
Image
Investigation with a suggested fix
Image
Change verification
Overview
Cleric is an AI SRE for engineering teams that run production systems. Its agents follow every change after it ships, verify it under real production traffic, take on-call alerts, and investigate failures through to a reviewed fix.
The problem
Teams ship more changes than ever, and many regressions only show up under real traffic, days after CI has passed. On-call engineers lose hours to noisy alerts and to piecing together dashboards, logs and recent deploys before they can find the cause.
How it works
Change verification: Cleric reads each change, records what it expects to see in production, and checks the release against real traffic for up to 14 days. When something regresses, it investigates and opens a fix PR with the production evidence attached.
On-call: Cleric acknowledges pages, closes false positives, groups repeat alerts into one issue and resolves what it can. It escalates to an engineer only when needed, with the findings attached.
Investigations: Cleric tests likely causes against your live environment and delivers the root cause, the evidence and a fix PR to review, then confirms recovery after the fix deploys.
Self learning: Cleric maps your services, dependencies and ownership, and learns from every task it completes to improve performance on future tasks.
Works with your stack
Integrations include Datadog, Grafana, Prometheus, New Relic, Splunk, Elasticsearch, Honeycomb, Sentry, Kubernetes, Amazon Web Services, Amazon EKS, GitHub, Bitbucket, PagerDuty, incident.io , Slack, Jira, Confluence, Linear and Notion, plus any HTTP MCP server. Engineers work with Cleric in Slack or the web app, and coding agents can pull investigations over MCP.
Security and deployment
Each customer gets a dedicated, isolated Cleric instance, hosted in the US or EU.
Read-only access to your observability and cloud tools by default. Cleric never merges pull requests without approval and never pushes to your default branch.
Raw logs, metrics, traces and code are queried at runtime and not stored.
Data is encrypted in transit and at rest, and never used to train models.
SOC 2 Type II compliant, with SSO through Google Workspace, Okta, SAML or OIDC and an organization audit log available.
Nothing to install in your clusters or cloud accounts. An optional Connector reaches private resources.
Results
Across customer tenants, Cleric closed 58% of alerts without an engineer between May and October 2026, and 51% of incidents resolved in Q3 2026 were fixed by applying Cleric's suggested remediation.
Pricing and getting started
Choose the Team, Pro or Scale plan on this page and subscribe. You can then set up your dedicated Cleric instance right away at cleric.ai/start and connect your tools. For custom terms or volume pricing, request a private offer.
Highlights
- Catch regressions before customers do: Cleric verifies every code release under real production traffic for up to 14 days, and when something regresses it opens a fix PR backed by the production evidence.
- Fewer pages: Cleric takes the pager, closes false positives and groups repeat alerts, so engineers are only paged when they're needed, with the findings ready.
- Safe by default: a dedicated instance per customer, read-only access by default and no training on your data. 51% of incidents resolved in Q3 2026 were fixed by applying Cleric's suggested remediation.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
Team | 16,800 credits per year. Unlimited users. Email support. | $8,400.00 |
Pro | 36,000 credits per year. Unlimited users. Priority support. | $18,000.00 |
Scale | 72,000 credits per year. Shared Slack channel with Cleric engineers. | $36,000.00 |
Dimension | Description | Cost/unit |
|---|---|---|
additional_credits | Additional credits used beyond your plan's yearly allowance, per credit | $0.50 |
Dimensions summary
You buy a yearly contract built around credits, the unit Cleric consumes for its work. Three plans set your yearly credit allowance: Team, Pro, and Scale. Credits scale upward across these plans, and all cover unlimited users. Support differs by plan: Team includes email support, Pro adds priority support, and Scale adds a shared Slack channel with Cleric engineers. If you use more than your plan's yearly allowance, the additional_credits dimension bills each extra credit. This lets you expand usage without switching plans.
Top-of-mind questions for buyers
A credit is the unit Cleric spends on work. Each production change check costs 2 credits. Each production Issue investigation costs 10 credits. Other agent sessions, called Chats, are free under 30 seconds, then 1 credit per started minute. Idle time is not billed.
Annual plans draw from one credit pool for the year. If you exceed that allowance, the additional_credits dimension bills each extra credit used. You can also set a hard cap. Cleric does not bill overages without written approval.
No. Repeat alerts that join an open Issue are free. Retries, corrections, and additional passes on the same Issue do not consume more credits. Follow-up passes are included in the original 10-credit Issue cost.
cleric.ai
Helpful?
Vendor refund policy
All fees paid are non-refundable. Unused credits expire at the end of the contract term and are not refundable. For billing questions, contact support@cleric.ai .
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
Email , Monday to Friday, 9am to 6pm Pacific. We aim to respond within one business day.
Product documentation is at docs.cleric.ai , and security documentation, including our SOC 2 Type II report, is at trust.cleric.ai .
Depending on your plan, support can also include priority handling, a shared Slack channel with Cleric engineers and a named customer success manager.
Email: (Monday to Friday, 9am to 6pm Pacific)
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
ResolveAI puts its SRE's inside your production stack: on-call, incidents, and operational tasks, so your engineers get back to building. These AI SREs triage alerts, investigate the root cause with 95% accuracy, and cut MTTR by up to 5x. Extend ResolveAI via MCP, API, and Skills to Claude Code, Codex, Cursor, Slack, MS Teams, or your custom agents.
TeamStation AI provides nearshore site reliability and observability engineering for AWS workloads. Team roles, deliverables, and acceptance criteria are scoped in an AWS Marketplace private offer.
Falcon by NeuBird is the first AI SRE agent purpose built for enterprise IT, delivering Autonomous Incident Resolution across hybrid- or multi-cloud environments. It investigates incidents the moment they occur, surfacing root cause and corrective actions before your team even logs in.
Falcon integrates seamlessly with your existing observability and incident management stack-including Datadog, Splunk, CloudWatch, PagerDuty, ServiceNow, and Slack. By automating diagnosis and operating within your existing workflows, Falcon reduces cost of an IT incident up to 80% and dramatically reduces MTTR.
Sherlocks are your SRE teammates that sit in your Slack alert channels to help you manage alerts, do RCAs in seconds and provide short & long term remediation steps.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.