Skip to main content
The Actions page is your team’s to-do inbox for AI output. Two kinds of items land here:
  • Recommendations — AI-drafted next steps for an account, generated by a Play or agent when customer context needs attention.
  • Approvals — agent runs paused at a Review step, waiting for a human decision.
The inbox has two lanes — Strategic (account-level recommendations) and Operational (approvals and system tasks) — with filters for status, a “My Accounts” toggle, and search.

​
Working a recommendation

Each recommendation shows the customer, a Risk / Growth / Neutral chip, what changed (health bucket movement with per-category deltas) or what was noticed (the signals that fired), and a list of suggested next steps. Steps are either:
  • Manual — tick the checkbox when you’ve done it, or
  • Tool steps — click Review to open the Execute modal, where the AI’s draft is ready to edit and send.
The Execute modal adapts to the tool: an email composer (To/Cc/Bcc, subject, rich-text body, contact picker), a Slack message composer, a support ticket form, or a calendar event with attendees pulled from the customer’s contacts. You choose the sender identity — the Quivly bot, your own account, or the account owner. Sending as yourself requires your own Gmail or Slack connection. When you’re done: Mark complete, or Dismiss with a quiet window (1 week to never) so the same recommendation doesn’t come right back. Thumbs up/down feedback tunes future recommendations.

​
Deciding an approval

For Play results, read the finding and supporting evidence before deciding on proposed changes. A result can contain several steps with separate decisions and outcomes. Approving the proposal records your decision; check the execution result before treating each change as complete. Some steps can succeed while others need attention. Proposed changes show readable summaries, source context, and reviewer information. Direct links can open a specific change or a group of related Actions; sharing a link does not grant access or approval permission. Expired proposals need a fresh proposal before approval. A Play configured to Run without review can execute its enabled actions automatically using the publisher’s current workspace access; inspect the recorded outcomes in Actions. Approvals show the workflow context, a snapshot of the data the agent saw, and the proposed change — which you can edit inline before approving. Approve resumes the workflow (with your edits); Reject sends it down the reject branch. Stacked approvals of the same kind can be decided in bulk. Every decision records who decided, when, and any note.

​
FAQ

Configure Plays and agents from the Agents page. Plays monitor account context and surface findings; workflow approvals appear when a run reaches a Review step.
A Play set to Review before running waits for account-owner review. Run without review permits automatic execution using the publisher’s current workspace access. Alerts about new Play Actions follow the Play’s delivery settings. Workflow agents can act autonomously when configured without a Review gate.
Yes — every field in the Execute modal is editable, and approvals support approve-with-edits.