Calendly Meeting Prep Agent with OpenCode
The part of this brief that separates models is the last section, where the agent takes what to say from your positioning notes and matches it against what the invitee actually asked for. OpenCode lets you pick the model doing that matching while the sections, the length limit and the HubSpot lookups stay fixed. Everything else in the run is retrieval.
Watch it work before it's live
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.
Product demo (30 min) booked by Hana Kobayashi
ConfirmedHana Kobayashi · h.kobayashi@sakuraworks.jp
New booking for Thursday 10:00 JST, 30 minutes, with the account team. What would you like to cover: we manage 60 designers across three studios and approvals still run over email, so nothing is traceable. How did you hear about us: a colleague in our Osaka office already uses you. Anything else we should know: we need SSO, and our security review usually takes about four weeks.
Set up in minutes
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 HubSpot
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.
Brief format
The sections you want in a pre-call brief, in the order your reps read them, and how long it can run before they stop reading. Write it the way you would brief a new rep on their first day.
Positioning notes
How you pitch, the objections that come up on first calls and the answers you give to them, and the competitors people bring up by name. The agent only says things that appear here.
Runs on OpenCode
Preselected for this page — connect your OpenCode 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.
Why OpenCode for this agent
Positioning is the hard part
Choosing which of your objection answers fits a booking that mentioned a cheaper competitor is judgement, and that is where the model choice is felt.
Retrieval does not need much
The contact, the deals and the booking answers are lookups, so most of the run is indifferent to how strong the model is.
Before you fork
Which model should I compare on?
Use the staged renewal booking with the competitor quote, because it forces a choice between your positioning notes and admitting that nothing covers it. A weaker model tends to reach for a general pitch line rather than the specific answer you wrote. If both models say plainly when nothing covers the objection, the cheaper one is doing the job.
Run it with a different agent
Put Calendly Meeting Prep Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.