Twilio Agent Connect (TAC)
Legal information
Twilio Agent Connect is not PCI compliant or a HIPAA Eligible Service and should not be used in workflows that are subject to HIPAA or PCI.
Connect AI agents to Twilio's platform. TAC is an SDK that acts as middleware between your LLM applications and Twilio services — Voice, messaging channels, Conversation Memory, and Conversation Orchestrator — so you can focus on your agent's intelligence.
Take the next steps with Twilio Agent Connect (TAC)
from tac import TAC, TACConfigfrom tac.channels.sms import SMSChannelfrom tac.channels.voice import VoiceChannelfrom tac.server import TACFastAPIServertac = TAC(config=TACConfig.from_env())sms_channel = SMSChannel(tac)voice_channel = VoiceChannel(tac)async def handle_message_ready(message, context, memory):# Process with your LLM and return the response — TAC routes it to the correct channelllm_response = await your_llm.generate(message)return llm_responsetac.on_message_ready(handle_message_ready)# Start the TACFastAPIServer to handle webhooks and WebSocket connectionsserver = TACFastAPIServer(tac=tac, voice_channel=voice_channel, messaging_channels=[sms_channel])server.start()
Take the next steps with Twilio Agent Connect (TAC)
Get started
TAC supports multiple starting points. Build from scratch with the quickstart, add TAC to an existing agent, or follow an integration guide for AWS Bedrock or Microsoft Foundry.
What you can build with TAC
- Connect LLM-powered agents to Twilio's communication channels with a unified interface.
- Retrieve customer context from Conversation Memory to personalize every interaction.
- Define custom tools, search knowledge bases, and configure escalation to human agents.
- Integrate with AWS Bedrock, Microsoft Foundry, OpenAI, or any LLM provider.
Related products
Conversation Orchestrator, Conversation Memory
Organize voice calls, SMS, and WhatsApp messages into conversations that link to customer profiles and are accessible for AI agents and analytics.
Product documentationStore and retrieve customer profiles, traits, and conversation context for personalized AI experiences.
Product documentation