Writing a form response into a sheet is mostly mechanical, which makes this the template where a small model earns its place. OpenCode lets you choose one, and the only part needing more is the half finished submission where the agent has to decide what it cannot parse. Your columns, labels and alert criteria stay identical whichever model you point it at.
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
Internal request form: new starter kit
Submitted 08:41. Request type: IT equipment. Site: Leeds head office. Who is it for: two new starters in payroll, both starting 1 September 2026. What do you need: two laptops, docking stations, and headsets. Needed by: 28/08/2026. Contact number: 0113 496 0182. Anything else: they share a desk, so one monitor arm each is plenty.
Aoife Brennan · a.brennan@northgatecare.co.uk
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Google Forms
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Google Sheets
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 sheet is laid out - the exact columns in order, what belongs in each one, the labels you use for request types, and the date and phone formats you want. The agent writes every row to match this.
Alert criteria
Which submissions are worth interrupting someone for - the request types, urgency words, sites, or people that mean somebody should look now rather than at the end of the day.
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.
Clean submissions are a mapping exercise, and there is no premium worth paying for mapping.
The half finished entry is the only submission that separates models, so it is the one to compare on before you decide.
Two places: putting a guess into a blank cell instead of leaving it empty, and deciding on its own that something is urgent when your criteria do not say so. Both are visible in one look at the staged freezer failure and the half finished entry. If neither goes wrong, a small model is fine for the other ninety percent.
Free to start. Guided setup, a test run against staged conversations, and it's live.