Covi works best as an iterative collaborator. Start with the outcome you want, let it investigate the relevant Coval data, and then refine or act on what it finds.
Write an effective request
A useful request usually contains three things:
- Goal: what decision or outcome you need.
- Scope: which agent, run, conversations, metric, test set, or time range Covi should inspect.
- Output: how you want the result organized and whether Covi should only investigate or also propose changes.
For example:
Analyze the last seven days of conversations for the support agent. Group the most common resolution failures and recommend test case additions to cover each failure mode. Do not make changes yet.
Common workflows
Work from the current page
Covi receives context about the page and resource you are viewing. Start from a focused page when possible:
- From a run or simulation, ask why cases failed, what changed, or which example deserves attention first.
- From Conversations, ask for recurring patterns, customer pain, operational issues, or metric ideas.
- From a test set, ask for missing scenarios, duplicates, or low-value cases.
- From a metric, ask how to make the evaluation more precise or how its outcomes compare with Human Review.
- From a dashboard or report, ask what moved, what should be investigated, or what should be tracked next.
If the page summary emphasizes the wrong thing, tell Covi what you care about. For example: “Prioritize metric regressions for Tool Call success.”
Ask for evidence and scope
When the result will drive a product decision, ask Covi to make the investigation auditable:
- “How many conversations did you analyze?”
- “What time range and filters did you use?”
- “Link the examples supporting each conclusion.”
- “Separate confirmed findings from hypotheses.”
- “What data was unavailable or excluded?”
Covi can navigate to supported resources and link simulations, conversations, runs, and metrics from its answers. Open those links to verify the source data or continue the investigation in the product.
Review actions before they run
The default action mode is Confirm actions. Covi presents supported changes in a confirmation card that describes what will happen. Review the target resource and proposed values, then confirm or dismiss the action.
You can optionally switch to Auto-run for a limited set of low-cost creation and setup actions. Auto-run shows a visible countdown, and you can press Esc to stop it. Evaluation launches, reruns, metric creation, edits, and destructive actions still require manual confirmation.
Read the confirmation card carefully. Deletions and edits can affect shared
evaluation resources used by other members of your organization.
Know when to narrow the task
Covi may need a smaller scope when a request spans a large number of conversations or several different goals. Split the work when:
- you need detailed evidence across a long time range;
- the analysis mixes setup, diagnosis, and resource creation;
- you need a precise comparison across several agents or versions;
- Covi reports that only part of the requested data was analyzed.
A good pattern is to ask for a high-level census first, select the most important segment, and then request a deeper analysis with examples.
Share feedback
Use the thumbs-up or thumbs-down control on a Covi response to tell the Coval team whether it was useful. When something is wrong, follow with a short correction that identifies the missing data, incorrect conclusion, or action you expected. This helps improve both the current conversation and future Covi behavior. 
