Cortex AI Assistant

We're excited to announce a public beta for the Cortex AI Assistant, available through Slack. It puts all the data in Cortex at your fingertips, without having to leave where you work or having to find the data yourself in the UI. Ask natural language questions about your services, teams, Scorecards, Initiatives, and more without leaving Slack.

It can answer simple questions like, What services does my team own? or Who's on-call for payments-api? or What's the production readiness score for checkout-service?, but it can also do so much more.

Here are a few prompt examples for you to get started with:

• What are the patterns of incidents on my team over the last 2 quarters? What areas do you recommend we invest in to improve the reliability of our services?

• Give me a summary of everything I worked on and my key accomplishments over the last quarter.

• Has there been an increase in PR sizes recently? Does that correlate with longer review times?

• What is our deployment frequency for the last 30 days across the services I own? Are there any patterns that may be causing that to change compared to the last quarter?

See the Cortex AI prompt library for a full list of prompt patterns organized by use case and role.

How it works

The Cortex AI Assistant requires the latest version of the Cortex Slack app. If you installed the app before February 2025, you'll need to update it before you can use the AI Assistant. Slack administrator permissions are required to perform the update.

To install, go to Slack settings in Cortex. Delete the existing configuration and reinstall following the prompts.

When you mention @Cortex in a Slack channel or direct message, the AI Assistant:

1. Interprets your natural language query

2. Determines which Cortex API endpoints to call

3. Retrieves the relevant data from your Cortex workspace

4. Returns a formatted response in Slack

The AI Assistant is currently read-only, so it can query information from Cortex but cannot make changes or write data.

Threading and conversation context

The Cortex AI Assistant supports threaded conversations, allowing you to ask follow-up questions that build on prior context within the same thread. How it works:

• Start a conversation - Mention @Cortex in any private channel or directly to the @cortex app in the with your initial question. The bot responds in a thread.

• Ask follow-ups in the thread - Reply in the same thread with additional questions. The AI assistant retains context from the conversation, so you can drill down without repeating information.

• Each thread is a separate conversation - Context is scoped to the thread. Starting a new top-level message begins a fresh conversation with no prior context.

Available capabilities

The Cortex AI Assistant can access the following Cortex API endpoints:

Capability	Description
Entity details	Look up ownership, metadata, and custom data for any entity
Entity descriptors	View and list entity descriptors (YAML definitions)
Dependencies	List incoming and outgoing dependencies for an entity
On-call	Check who is currently on-call for an entity
Scorecards	List Scorecards, view scores, and get next-step recommendations
Initiatives	List and inspect Initiatives and their progress
Relationships	Explore entity relationships and relationship types
Team details	View team membership, sourcing, and contact channels
Workspace context	Query "my" entities and how they perform against Scorecards
Eng Intelligence metrics / traces	Query DORA metrics, incident trends, PR data, and other engineering performance indicators
Deployments	Search deployments across the workspace by environment, type, entity, and time range; list available deployment environments

Providing feedback

After each response, the AI assistant displays reaction emoji options. You can react with :thumbs_up: (👍) or :thumbs_down: (👎) to provide feedback on the quality of the answer. This feedback helps improve the responses over time.

Crafting effective prompts

Getting useful output from any AI assistant comes down to how you ask. Be sure to write prompts that are clear, specific, and designed to get you the response you need.

• Be specific - Instead of Tell me about services, you could say, Show me all critical services failing the Production Readiness Scorecard. This provides you with more actionable information.

• Combine multiple questions when context helps - Cortex handles complex prompts like Who owns orders-api, when was it last deployed, and are there any open incidents? You receive richer context in response to one question instead of piecing together three separate queries.

• Reference your organization's specific constructs - If you've defined custom Scorecards or Initiatives in Cortex, reference them by name. Cortex understands your organization's specific standards and can query against them directly.

• Use follow-up questions to drill down - Start broad, then go narrow. Show me services with failing Scorecards, followed by What specific checks is checkout-service failing? moves you from landscape view to action items.

• Build a library of your most-used prompts - If you ask the same question every Monday morning, save it. Some teams maintain shared prompt libraries so everyone can benefit from patterns that work.

See the Cortex AI prompt library for a full list of prompt patterns organized by use case and role.

Configuring the Cortex AI Assistant

For instructions on configuring the AI Assistant, refer to Configuring the integration for Slack.

Troubleshooting and FAQ

See Slack integration FAQ and troubleshooting.