Telnyx 推出跨邮件、语音和短信携带上下文的 AI 智能体

Omnichannel Context-Carrying Agent — customer context follows across channels

AI agent that carries customer context across email, voice, and SMS so customers never repeat themselves. When a customer calls after emailing, the AI greets them with: "I see you contacted us about changing your booking. Are you calling about the same request?"

Why Telnyx

Telnyx is an AI Communications Infrastructure platform — email, messaging, voice, and AI on one private, global network. This sample uses four Telnyx APIs (Email, Messaging, Call Control, AI Inference) from a single API key to demonstrate seamless cross-channel context carrying with customer identity resolution.

Telnyx API Endpoints Used

• Send Email: POST /v2/emails — API reference
• Send Message: POST /v2/messages — API reference
• Create Call: POST /v2/calls — API reference
• Answer Call: POST /v2/calls/{call_control_id}/actions/answer — API reference
• Speak: POST /v2/calls/{call_control_id}/actions/speak — API reference
• Gather Speech: POST /v2/calls/{call_control_id}/actions/gather — API reference
• AI Inference: POST /v2/ai/chat/completions — API reference

Telnyx Webhook Events

This app handles these webhook events:

• email.received — Inbound email triggers AI reply flow
• call.initiated — Incoming call triggers identity lookup and answer
• call.answered — AI generates contextual greeting from cross-channel history
• call.speak.ended — TTS playback finished, begins speech gathering
• call.gather.ended — Customer speech captured, AI processes with full context
• call.hangup — Call ended
• message.received — Inbound SMS triggers AI reply with cross-channel context

Architecture

         Customer contacts on any channel
              │         │         │
          Email in   Call in   SMS in
              │         │         │
              ▼         ▼         ▼
        ┌─────────────────────────────┐
        │         Flask app.py        │
        │                             │
        │  ┌───────────────────────┐  │
        │  │  Customer Identity    │  │
        │  │  Registry (SQLite)    │  │
        │  │  email ↔ phone ↔ id   │  │
        │  └───────────┬───────────┘  │
        │              │              │
        │  ┌───────────▼───────────┐  │
        │  │  Cross-Channel        │  │
        │  │  Context Store        │  │
        │  │  (SQLite)             │  │
        │  └───────────┬───────────┘  │
        │              │              │
        │  ┌───────────▼───────────┐  │
        │  │  Telnyx AI Inference  │  │
        │  │  (context-aware       │  │
        │  │   greeting + reply)   │  │
        │  └───────────┬───────────┘  │
        │              │              │
        │     ┌────────┼────────┐     │
        │     │        │        │     │
        │  Email API  SMS API  Voice  │
        └─────────────────────────────┘
              │        │        │
              ▼        ▼        ▼
           Customer receives contextual
           responses on every channel

The key differentiator: when a customer switches channels (e.g., emails then calls), the AI resolves their identity, loads the full cross-channel conversation history, and generates a greeting that references their prior interaction — so they never have to repeat themselves.

Environment Variables

Copy .env.example to .env and fill in:

Agent / CLI access — provision the resources above via the Telnyx CLI:

telnyx auth login
telnyx available-phone-numbers list --country US --features sms,voice
telnyx number-orders create --phone-number +15551234567
telnyx messaging-profiles create --name "Context Carrying Agent"

Setup

Option A — Demo mode (no credentials needed)

git clone https://github.com/team-telnyx/telnyx-code-examples.git
cd telnyx-code-examples/omnichannel-context-carrying-python

pip install -r requirements.txt

python demo/demo_server.py

The demo walks through "Sarah's Booking Change" — she emails about rescheduling, then calls and hears the AI greet her with full context from her email. No Telnyx credentials required.

Programmatic / CLI setup

# Install CLI — https://developers.telnyx.com/development/cli
go install github.com/team-telnyx/telnyx-cli/cmd/telnyx@latest
telnyx auth login

# Provision resources
telnyx available-phone-numbers list --country US --features sms,voice
telnyx number-orders create --phone-number +15551234567
telnyx messaging-profiles create --name "Context Carrying Agent"

For full API discovery, point your agent at llms-full.txt.

Option B — Production mode (with credentials)

git clone https://github.com/team-telnyx/telnyx-code-examples.git
cd telnyx-code-examples/omnichannel-context-carrying-python

cp .env.example .env    # ← fill in your credentials
pip install -r requirements.txt
python app.py           # starts on http://localhost:5000

Register a customer and test the flow:

# Register a customer identity
curl -X POST http://localhost:5000/customers/register \
  -H "Content-Type: application/json" \
  -d '{
    "id": "cust_sarah_chen",
    "name": "Sarah Chen",
    "email": "sarah@example.com",
    "phone": "+15551234567"
  }'

Webhook Configuration

1. Expose your local server:

   ngrok http 5000

2. Copy the HTTPS URL and configure in Telnyx Portal:

   • Call Control Application → Webhook URL → https://<id>.ngrok.io/webhooks/voice
   • Messaging Profile → Inbound Webhook URL → https://<id>.ngrok.io/webhooks/messaging
   • Email → Inbound Webhook URL → https://<id>.ngrok.io/webhooks/email

API Reference

POST /customers/register

Register a customer identity for cross-channel resolution.

curl -X POST http://localhost:5000/customers/register \
  -H "Content-Type: application/json" \
  -d '{"id": "cust_001", "name": "Sarah Chen", "email": "sarah@example.com", "phone": "+15551234567"}'

GET /customers

List all registered customers.

curl http://localhost:5000/customers

GET /customers/<id>/context

View cross-channel context for a customer.

curl http://localhost:5000/customers/cust_001/context

GET /conversations

View all cross-channel conversation history, grouped by customer.

curl http://localhost:5000/conversations

POST /demo/journey

Trigger the full scripted demo journey (demo server only).

curl -X POST http://localhost:5555/demo/journey

GET /health

Health check endpoint.

curl http://localhost:5000/health

Webhook Endpoints

POST /webhooks/email

Receives Telnyx Email webhook events. On email.received: resolves customer identity by email, stores the message, and triggers AI-generated reply in a background thread.

POST /webhooks/voice

Receives Telnyx Call Control webhook events. On call.initiated (incoming): resolves customer by phone and answers. On call.answered: loads cross-channel history and generates a contextual greeting. On call.gather.ended: processes customer speech with full context.

POST /webhooks/messaging

Receives Telnyx Messaging webhook events. On message.received (inbound): resolves customer by phone, stores message, and triggers AI reply with cross-channel context.

Testing

python -m pytest smoke_test.py -v

Troubleshooting

Agent Discovery

This example is part of the Telnyx Code Examples catalog.

• Agent signup: telnyx.com/agent-signup.md — automated account provisioning via agent mail
• Agent CLI: github.com/team-telnyx/ai/tree/main/cli
• LLM-optimized docs: llms-full.txt
• Example index: llms.txt

Related Examples

• Omnichannel AI Agent (Python)
• Omnichannel AI Receptionist (Python)
• AI Email Agent (Python)
• AI Voice Agent with Function Calling (Python)

Resources

• Telnyx Email API Guide
• Telnyx Messaging Guide
• Call Control Guide
• Telnyx AI Inference
• Telnyx Python SDK
• Telnyx Email API Product
• Telnyx SMS API Product
• Telnyx Voice AI Product
• Telnyx Developer Docs
• Telnyx Portal