Build an SMS Triage Bot on Telnyx Edge Compute

Support SMS inboxes are usually a routing problem before they are an AI problem.

Someone asks about billing. Someone else needs technical support. A third person wants to talk to sales. The app has to understand the message, pick the right destination, reply to the customer, and remember what happened.

This TypeScript example does that on Telnyx Edge Compute with the Agent SDK.

Code: https://github.com/team-telnyx/telnyx-code-examples/tree/main/agent-sms-triage-bot

agent-sms-triage-bot

receives inbound SMS webhooks, classifies each message into one of four topics, looks up the route for that topic, replies by SMS, and stores triage history in durable actor state.

The topics are:

billing

support

sales

general

The default route table maps those topics to queue names:

billing -> billing-queue
support -> support-queue
sales   -> sales-queue
general -> general-queue
php
Inbound SMS
  -> POST /webhooks/sms
  -> TriageAgent.triage(from, text)
  -> Telnyx AI Inference classifies topic
  -> durable route table lookup
  -> SMS reply
  -> triage history update

The app uses one TriageAgent

actor per inbound number. That actor stores route rules, recent history, total messages, and topic counts.

POST /webhooks/sms

receives Telnyx message.received

eventsPOST /debug/triage

simulates inbound SMSPOST /routes

updates the route tableGET /routes

lists route rulesGET /history

returns recent triage historyGET /debug/state

inspects actor stateGET /health/liveness

and GET /health/readiness

provide health checksThe core class is TriageAgent

.

It extends the Agent SDK Agent

class and uses durable state for:

The AI classification call uses the Telnyx binding:

const completion = await this.env.TELNYX.ai.openai.chat.createCompletion({
  model: this.env.AI_MODEL || "moonshotai/Kimi-K2.6",
  messages: [
    { role: "system", content: CLASSIFY_SYSTEM_PROMPT },
    { role: "user", content: `Customer message: "${text}"` },
  ],
  max_tokens: 2000,
  temperature: 0.2,
});

The SMS reply uses the same binding pattern:

await this.env.TELNYX.messages.send({
  from: state.fromNumber || state.phoneNumber,
  to: from,
  text: replyText,
});

That means the example does not hardcode an API key in application code. Messaging and inference both go through this.env.TELNYX

.

After deploying with telnyx-edge ship

, you can test without sending a real SMS:

curl -X POST https://agent-sms-triage-bot-<id>.telnyxcompute.com/debug/triage \
  -H "Content-Type: application/json" \
  -d '{"from":"<customer-number>","to":"<triage-number>","text":"Why was I charged twice this month?"}'

Example response:

{
  "action": "triaged",
  "from": "<customer-number>",
  "to": "<triage-number>",
  "text": "Why was I charged twice this month?",
  "topic": "billing",
  "route": "billing-queue",
  "confidence": 0.95
}

Then inspect the actor history:

curl "https://agent-sms-triage-bot-<id>.telnyxcompute.com/history?number=<triage-number>"

For a small support workflow, this keeps the first version compact:

You can later replace queue names with real integrations: Slack, Zendesk, Salesforce, email, or an internal queue.

Before using this with real customer traffic, I would add:

Resources: