Covi is in beta. Please reach out to the team with any feedback.
How Covi is designed to work
Grounded in your organization
Covi works from the organization you currently have open and can use the
active page as context for your question.
Evidence before action
Covi can investigate results, explain its reasoning, and link you to the
underlying resources before you decide what to change.
You stay in control
Covi proposes supported changes in a confirmation card. Edits, launches,
and destructive actions require review before they run.
One continuous workflow
You can investigate a failure, improve evaluation coverage, launch new
work, and inspect the result in the same conversation.
What Covi can do
Capabilities vary by resource. If Covi cannot complete a requested action directly, it should explain the gap and help you take the next available step.
From question to action
1
Ask
Describe the outcome you want, the scope to inspect, and any constraints.
2
Investigate
Covi reads the relevant Coval data, explains what it found, and links to
supporting results when available. It uses its knowledge base of evaluation
in the Coval platform and expertise in voice AI agent development to inform
its guidance.
3
Refine
Ask follow-up questions, narrow the scope, or request a concrete plan.
4
Act
When Covi can complete the next step, it presents the proposed action for
confirmation. After it runs, Covi returns a receipt and a path to the
result.
Scope and reliability
Covi is scoped to the organization you currently have open. Chats persist separately for each user within the organization and are not shared organization-wide threads. Covi cannot inspect another organization, your local files, or other browser tabs. For high-impact decisions, treat Covi as an investigation partner rather than the final source of truth. Ask what it analyzed, review the linked examples, and verify completed work on the relevant Coval page. Large analyses may need a narrower time range or several focused passes.Using Covi
Learn how to open Covi, write effective requests, work with page context, and
review proposed actions.