Form volume is spiky: a campaign lands and a quiet form becomes two hundred responses in a day. OpenCode lets you pick the model underneath, so the per response cost is a decision you make rather than inherit, and one you can revisit when the volume moves. The routing criteria and team notes stay exactly as you wrote them.
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.
New response
Book a demo: Amara Nwosu
Submitted 09:12 WAT from the pricing page. What brings you here: We run 14 cold storage depots and our stock counts still live in spreadsheets. Company and size: Ridgeport Foods, 340 staff. Your role: Head of Operations. How many people would use this: 26 supervisors across the depots. Budget: Signed off, up to 40,000 USD this year. Timeline: Live before the December peak, so onboarding starts in October. Anything else: We trialled two tools last year and both fell over at sites with poor connectivity.
Amara Nwosu · amara.nwosu@ridgeportfoods.ng
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Typeform
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.
Routing criteria
Who each kind of lead goes to and what makes one worth a call - the answers, company sizes, budgets or timelines you route on, the owner for each route, and what rules a response out entirely. The agent routes on this and nothing else.
Team notes
What your reps want to see in a lead summary - the answers they read first, the context that helps them open a call, and how blunt the verdict should be. This shapes both the HubSpot note and the Slack ping.
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.
Each response is one run, so a campaign week multiplies whatever you picked. Owning that choice is the difference between a predictable bill and a surprise.
Your routes, owners and disqualifiers live on the agent, so changing model never means rewriting how leads are scored.
The routing itself is rule following and usually survives a cheaper model intact. Where it shows is the vague response with blanks and no budget, because calling something genuinely unknown instead of inferring it takes discipline. Run the staged late night enquiry on both and check whether a headcount or a budget got invented.
Free to start. Guided setup, a test run against staged conversations, and it's live.