.png)
Ask questions about your costs in plain English, right from the product.
The Mavvrik Agent gives you a conversational way to explore your Mavvrik data. You write no queries. You move between no dashboards. You can ask about cloud cost, Kubernetes spend, SaaS cost, GenAI usage, savings, cost allocation, tag coverage, Agentic data, and datacenter cost — and get an answer right in the conversation.
Why this matters: most cost questions don't need a saved dashboard — they need one answer, once. Chat is like asking a colleague who already has the dashboard open, instead of opening it yourself, finding the right filter, and reading the chart. Skills and Connectors extend that same conversation to your team's own conventions and your other tools.
This shows up differently depending on your role:
-
FinOps managers and engineers use Chat for quick, specific answers without leaving their existing workflow.
-
FinOps/platform leads use Skills to make the Agent follow their team's own conventions instead of a generic default.
-
Admins use Connectors to extend the Agent's reach into tools like Jira, GitHub, or Sentry.
Two features extend what the Agent can do for your team:
-
Skills — teach the Agent your team's own conventions, so its answers follow your standard instead of a generic one.
-
Connectors — connect the Agent to the tools your team already uses (Jira, GitHub, Sentry, and others), so it can look things up or act across systems without you leaving the conversation.
In this section
-
Chat — how to ask questions and get answers from your cost data
-
Skill — how to teach the Agent your team's conventions
-
Connector — how to connect the Agent to your other tools
Where to start
Chat works immediately with no setup — start there. Skills and Connectors are both optional, and you can add either (or both) whenever you're ready to customize or extend what the Agent can do.