The failure is a third email to somebody who has missed three times, which reads as automation and costs more goodwill than saying nothing would. The rule is a count checked against the invitee's history before a word is written, and past the limit no draft exists at all, only a Slack line with the dates. Codex handles that lookup and branch cleanly.
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Discovery call (30 min)
ConfirmedSofia Kowalczyk · s.kowalczyk@vantopharma.pl
Marked as a no-show for Tuesday 5 August at 09:00 CEST, hosted by Nadia. She typed at booking: what are you hoping to fix, we run trial logistics across 40 sites and scheduling is still spreadsheets; where did you find us, a LinkedIn post; anything we should know, I am usually in the lab before 10. Two earlier meetings with this team were attended.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Calendly
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Gmail
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Rebooking policy
How you follow up when somebody misses a call: how long you wait, the tone and length you want, the booking link to send, what you will and will not offer to win the meeting back, and how many misses before a rep takes over instead of another email.
Runs on Codex
Preselected for this page — connect your Codex account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
The branch produces nothing to send rather than something softer, which is the only version that holds. A draft sitting in Gmail eventually gets sent by somebody in a hurry.
How many misses are too many is a number you write in the policy. The agent applies it against real scheduled events instead of forming its own view of who is worth chasing.
The rebooking policy is where you name which event types are in scope, and most teams scope it to the booking pages prospects use rather than internal ones. It reads the event type on every run, so a policy naming your discovery and pricing pages keeps the internal weekly catch up out of it.
Free to start. Guided setup, a test run against staged conversations, and it's live.