WhatsApp Support Agent with OpenCode
Support on WhatsApp is multilingual by default and busiest on the days you least want to be watching it. OpenCode being model-agnostic means the model answering in Portuguese at 2am is one you chose rather than one the harness chose for you. It stays light on each individual message, which suits a channel where most threads run three lines long.
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.
Rodrigo Salgado+55 11 98442 7310
I withdrew R$400 on Saturday, order 88214, and it still has not landed. My bank says there is nothing pending on their side. Can you check what happened?
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect WhatsApp
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.
Support playbook
Everything the agent is allowed to answer from - your products, the fixes you give most often, and your rules on refunds, delivery, and cancellations, written the way you would explain them to a new hire.
Escalation contact
Who takes over when the agent cannot help: a name plus the WhatsApp number it should message, and what belongs to them, such as refunds, outages, or anything involving money.
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
Pick the model your customers speak
Language coverage varies considerably between models, and this harness lets you point the same playbook at whichever one handles your customers best.
Volume without a surprise
Traffic spikes on launch days and delivery delays. Being free to change the underlying model is the simplest lever you have when that happens.
Before you fork
If I change the model later, do I have to redo the setup?
No. The playbook, the escalation contact, and the WhatsApp connection all belong to the agent rather than the model, so it is one field. The running sandbox is rebuilt with the new settings, meaning the switch lands on the next incoming message instead of mid conversation.
Run it with a different agent
Put WhatsApp Support Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.