The failure everyone imagines from an intake bot is the loop: it tags a task, ClickUp fires an event for the tag, and it tags again. This template kills that with an explicit test of whether the last change came from the agent, run before anything is written. Codex handles work with edges that hard very comfortably, since the job is checking conditions and then making two precise writes.
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.
Landing page for the October 8 partner webinar
TO DOAcreated by Aisyah Rahman
We need this live by September 24 for the partner webinar on October 8. Copy and speaker headshots sit in the shared drive folder linked below, registration should post to HubSpot form 4412. Budget code is MKT-Q4-08.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect ClickUp
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.
Intake rules
How your intake actually works - which list new requests land in, the tags you sort them into, what a request must contain before work can start, and which requests deserve a Slack ping.
Team map
Each type of request paired with the ClickUp member who should own it, plus the person who catches anything matching nothing on the list.
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.
A tag and an assignee, both drawn from lists that already exist in your space. This is exact API work of the kind Codex is strong on, with no prose to compose in the middle of it.
A request matching nothing goes to the person your rules nominate, with the comment saying a human still has to place it properly. Nobody plausible gets picked instead.
There is a run each time, but the large majority stop at the gate after a single read, which is the cheapest thing this agent does. Sorting and commenting only happen for genuinely new intake tasks. If the space is very noisy, scope the trigger to the intake list rather than the whole workspace and the volume drops sharply.
Free to start. Guided setup, a test run against staged conversations, and it's live.