# Cleric product: Catch failures before your customers do

> Cleric checks your changes in production and investigates regressions, bringing you fix PRs with the evidence to review them. Read-only by default. SOC 2 Type II.
>
> Markdown version of https://cleric.ai/product for AI agents and LLMs. Site index: https://cleric.ai/llms.txt

Cleric covers three stages of production work: catching what your tests miss, handling your pages, and getting the fix done. Engineers work with Cleric in Slack, Microsoft Teams, and the Cleric web app, where changes, issues, and chats each have their own view.

- Start free trial: https://cleric.ai/start
- Explore the product: https://demo.cleric.ai
- Book a demo: https://cleric.ai/demo

## Catch what your tests miss

Cleric checks how your changes behave under real traffic and investigates the regressions your tests missed.

### Track your PR into production

Cleric analyzes your PR, then tracks its deployment to check that production behaves as you intended.

For each change, Cleric records what is expected in production (for example: p95 latency stays at or below 200 ms, retry rate stays at or below 0.5%) and compares it with what it observes after deployment. When an expectation is not met, Cleric flags the regression in the change’s Slack or Microsoft Teams channel, opens a fix PR, and confirms recovery once the fix deploys.

### Catch delayed regressions

Cleric keeps checking your changes for days after deployment, letting you know when it finds a regression or verifies your release.

Verification runs for up to 14 days. For example, a cache warm-up change that passes its first checks can start degrading on day 9 as the working set grows past the warmed key set. Cleric reports the deviation (cache hit rate and p95 latency) to the team with its explanation.

## Only the pages that need you

Cleric handles your urgent alerts and investigates low-priority issues before they interrupt your day.

### Leave the pager to Cleric

Cleric acknowledges your pages, closes false positives, and resolves what it can, escalating to you only when you’re needed, with the findings attached.

A typical escalation: Cleric acknowledges the page, rules out deploy, config, and capacity causes, confirms the cause (for example, a retry storm introduced by a specific PR), and escalates with the investigation. The engineer receives the affected service, why a person is needed, the decision required, and the evidence, including the causes that were ruled out.

### Find the issues buried in the noise

Cleric deduplicates your low-priority alerts and investigates the underlying problems, so you can get them resolved before they become urgent.

For example, 23 low-priority alerts over six days (18 duplicates of one slow-response alert and 3 related cache alerts) become one issue with a cause and a fix PR, without anyone being paged.

## Fix it your way

With the investigation done, you can finish the fix in Cleric or take the findings and production context to your coding agents.

### Fix it in Cleric

You can review the fix PR and its production evidence in Cleric before approving the change. Once it deploys, Cleric checks that your issue is resolved.

### Use your existing tools

Ask your coding agent to pull the investigation from Cleric over MCP, or have Cleric create a Linear, Jira, or GitHub issue with the findings and production context.

Over MCP, a coding agent such as Claude Code or Cursor receives the issue, the finding, the evidence, and any existing fix PR, and can continue from there. The investigation goes with the handoff either way.

Set up the Cleric MCP server in Claude Code or Cursor with your instance URL and a personal API key: https://docs.cleric.ai/integrations/mcp.md

Cleric’s docs have their own public MCP server, with no sign-in, for agents that need to search or read them: https://docs.cleric.ai/~gitbook/mcp

## Built to plug right into your stack

Connect your whole stack in an afternoon. Read access by default, write access when you’re ready.

Every integration by category, with what Cleric uses each one for: https://cleric.ai/integrations.md

The docs list every supported integration, with setup steps and the permissions each one needs: https://docs.cleric.ai/integrations/supported-integrations.md

## Prevent incidents in your own stack

Try Cleric on your production changes to see the regressions it finds in your stack and review the fixes it writes.

- Start free trial: https://cleric.ai/start
- Explore the product: https://demo.cleric.ai
- Book a demo: https://cleric.ai/demo
- How it works: https://cleric.ai/technology.md
- Pricing: https://cleric.ai/pricing.md