Telegram sales volume is lumpy: a hundred one-line price questions during a launch week, then nothing for ten days. OpenCode is model-agnostic, so you decide what each of those replies is worth and swap the underlying model when the volume changes shape. It is light to point at a narrow job, and answering from a fixed offer sheet is a narrow job.
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.
Kelechi Obi@kelechi_obi
Hi, a colleague forwarded me your channel. We are 12 people here in Lagos and want to start on the 1st. What does that cost, and is there anything off if we pay for the year?
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Telegram
One sign-in. The agent acts through your account, scoped to what this template uses.
Business name
The name customers know you by, spelled the way you want it to appear in chat.
Offer details
What you sell - products or plans WITH prices, in your own words. The agent only ever quotes from this.
Booking link
The full URL you want ready buyers sent to, whether that is a calendar, a checkout page, or a short form.
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.
The same agent runs on whichever model you point it at, so a high-volume DM inbox can sit on something cheap while a considered follow-up sits on something stronger.
Nothing about OpenCode assumes it is editing code. Its general tool use is what fires the Telegram send and hands over your booking link.
The instructions bind every model to your offer details, but yes, weaker models follow rules less reliably. Stage the awkward messages in the Test Run tab, the two word price ask and the angry refund demand, and read the replies before going live. If they drift, move up a model and rerun the same tests.
Free to start. Guided setup, a test run against staged conversations, and it's live.