SMS Support Agent with OpenCode
Support texts arrive in whatever language your customers speak, and the agent is told to answer in that same language. OpenCode lets you choose the model underneath, so a line taking Spanish and Portuguese all day can run on something that handles both well, and a purely English line does not have to pay for that. The playbook, the escalation contact and the Twilio number stay put when you change it.
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.
Ana Sofia Guzman+52 55 1234 8890
hola, cn i chnge the delivery to fri? order 88214, nobodys home thurs. thx
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Twilio
One sign-in. The agent acts through your account, scoped to what this template uses.
Business name
The name your customers know you by, written exactly as you would put it in a text message.
Support playbook
Everything the agent is allowed to answer - your hours, delivery and returns terms, the common fixes, and the exact wording for anything sensitive. It only ever answers from this.
Escalation contact
Who takes over when the agent cannot help - the name and number or team, and when they are reachable, written so the agent can say it in one short line.
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
Match the model to language
Replies go out in whichever language the customer wrote in, which makes the model doing the writing the decision that matters most on a multilingual line.
High volume, your cost curve
A busy number is a lot of small runs. Choosing the model yourself is how you control what each one of them costs.
Before you fork
Which model should I start with?
Start on something strong while you are still writing the playbook, since weak replies at that stage are usually a gap in your rules and you want to see that clearly. Once the staged texts read the way you want, run the same three on a cheaper model and compare them side by side. You supply the provider key during setup, so the spend is yours either way.
Run it with a different agent
Put SMS Support Agent to work on OpenCode
Free to start. Guided setup, a test run against staged conversations, and it's live.