How to build an AI agent that remembers returning customers

Twilio published a guide for building AI customer-service agents that recognize returning customers by combining identity resolution, context recall and write-back, citing Twilio research finding 74% of consumers say they have to repeat themselves to AI assistants and 71% are willing to abandon a conversation if an agent fails to recognize them. The same research found 91% of brands have seen customer satisfaction drop because of AI missteps, with 40% citing lost conversational context between channels or interactions. The guide walks through Twilio Conversation Memory for storage, Conversation Orchestrator for linking conversations to customer profiles, and the open-source Twilio Agent Connect SDK for connecting agents to Twilio's channels and memory.

How to build an AI agent that remembers returning customers Time to read: Written by How to build an AI agent that remembers returning customers introduction A customer texts on Monday about a billing error. Your AI agent sorts it out. Well done. ∗claps∗ But on Wednesday, the same customer calls about a follow-up charge, and…the agent asks for their name, account number, and what the problem is. Again. This situation isn’t a hypothetical either. Really, it’s more like the default experience right now for customers. That’s why our research found https://www.twilio.com/en-us/report/navigating-data-deluge-charting-customer-context : - 74% of consumers said they have to repeat themselves when interacting with an AI assistant - 71% said they're willing to abandon a conversation early if an AI agent fails to recognize them The brands notice, too. 91% have seen customer satisfaction drop because of AI missteps, most notably when an AI loses conversational context between channels or interactions 40% . Woof. Fortunately, there’s a solution: AI customer memory https://www.twilio.com/en-us/blog/insights/ai-customer-memory . Here's how to build an AI agent that recognizes returning customers, loads what it knows before it says hello, saves new facts as it learns them, and carries all of it across channels. What does it mean for an AI agent to remember a customer? toc-heading-10366cb6-8c44-4aec-b8da-b3b0a8e56976 An AI agent remembers a customer when it can identify them across conversations, recall relevant facts from past interactions, and save new details it can use next time. That takes three capabilities working together: 1. Identity: Knowing the person texting today is the person who called last week. 2. Recall: Pulling the right context into the conversation at the right moment. 3. Write-back: Saving what the agent learns so it's there for the next conversation. Then, there’s super-long conversations. These sometimes struggle to include all the context inside a model's limits. Our guide to token limits in long AI support conversations https://www.twilio.com/en-us/blog/insights/token-limits-ai-support-conversations covers that one, but the guide below covers the time between conversations. How to build an AI agent that remembers returning customers how-to-build-an-ai-agent-that-remembers-returning-customers Let’s walk you through building an AI agent that remembers returning customers. Here are the Twilio products we’ll be using: - Twilio Conversation Memory https://www.twilio.com/en-us/products/conversational-ai/conversation-memory to store what your agent knows - Conversation Orchestrator https://www.twilio.com/en-us/products/conversational-ai/conversation-orchestrator to link each conversation to a customer profile - Twilio Agent Connect https://www.twilio.com/docs/conversations/agent-connect , the open source SDK that connects your agent to Twilio's channels and memory. 1. Recognize who's contacting you toc-heading-aac7c6e4-5854-4ff9-896c-fa9c5451d285 Memory starts with identity. Conversation Memory's identity resolution https://www.twilio.com/docs/conversations/memory/identity-resolution matches and merges profiles across channels using phone numbers, WhatsApp handles, email addresses, chat IDs, and your own user IDs. Conversation Orchestrator applies it to every conversation https://www.twilio.com/docs/conversations/orchestrator/concepts/profiles , so a text on day 1 and a call from the same number on day 2 resolve to the same profile. Set GROUP BY PROFILE explicitly to keep them in one conversation. - Link identifiers up front: A customer who texts from one number and calls from another only unifies if both numbers sit on the same profile, so upload profiles with linked identifiers before launch. - Verify before sharing: Phone numbers can change owners, so confirm a profile's traits match the caller before you mention anything sensitive. In Studio, the Resolve Profile widget https://www.twilio.com/docs/studio/widget-library/resolve-profile looks up a caller by phone number or email address and returns their traits for greeting or routing. 2. Decide what to remember toc-heading-cf3c9af3-843e-400f-b171-ebdc4fdebd67 Conversation Memory stores three kinds of memory: - Traits: Structured facts the agent acts on every time, like plan, tier, or preferred language. - Observations: Facts and preferences extracted from conversations, like "Prefers email over phone," which Memory updates as customers add detail or change their minds. - Summaries: Short recaps of each conversation. Turn on memory extraction in your Orchestrator configuration. 3. Load context before the agent says hello toc-heading-79e7dd18-3463-4aa8-b1fd-ff18eceea0a0 This step stops the repeated questions. Conversation Memory's Recall API https://www.twilio.com/docs/api/memory/v1/retrieval/create-fetch-profile-memory returns a profile's most relevant observations and summaries up to 20 and 5 by default , and its date filters let the agent pull up yesterday's conversation. With Twilio Agent Connect, set the memory mode to always every message or once first message only . The default is never, and memory requires Agent Connect's Orchestrator mode, so configure both explicitly. On phone calls, Agent Connect uses ConversationRelay https://www.twilio.com/en-us/products/conversational-ai/conversationrelay for speech-to-text and text-to-speech. Twilio's multi-call memory tutorials build this end to end, with a voice agent that looks up the caller, recalls past calls before the greeting, and saves a summary at hang-up: 4. Save new facts during the conversation toc-heading-1fa03fc5-64ea-4535-bafd-7171ee4cc5a4 Memory extracts observations after a conversation goes inactive or closes. There's no mid-conversation extraction, so when a customer confirms an appointment or changes an address, write it yourself: - Create observations: Add up to 10 at a time to the customer's profile. - Update traits: Patch a defined trait, like preferred channel. Agent Connect only reads profiles, so build the write as a tool backed by your own Memory API call. Twilio's persistent customer memory tutorial https://www.twilio.com/en-us/blog/developers/tutorials/product/build-persistent-customer-memory-with-twilio-agent-connect-and-c shows how preferences extracted after a conversation are saved as traits and used in the next session. 5. Use memory with intention toc-heading-2e2cb2c1-5c42-48e5-b230-8e038706fcf8 Twilio's Inside the Conversational AI Revolution https://www.twilio.com/en-us/report/Inside-the-Conversational-AI-Revolution research found 66% of consumers said they wouldn't prefer or feel uneasy providing an AI agent with all previous context from interactions. A few rules help: - Lead with the useful part: "I see you called yesterday about a duplicate charge. Same issue?" - Confirm what can change: Ask before acting on addresses, plans, or phone numbers. - Let customers correct the record: Update or delete a wrong memory through the Memory API. 6. Carry memory across channels and handoffs toc-heading-c573b421-8558-4aab-aa2d-bd85f83a76b0 Because identity resolves across channels, the profile a text built is the one a call reads. Agent Connect handles Voice, SMS, WhatsApp, RCS, and Chat through one message handler. Memory follows the customer to people, too. Agent Connect's escalation tool https://www.twilio.com/docs/conversations/agent-connect/escalate-to-human-agent passes the conversation ID, memory store ID, and profile ID to Twilio Flex https://www.twilio.com/en-us/flex . Our Agent Connect and Flex handoff tutorial https://www.twilio.com/en-us/blog/developers/tutorials/product/twilio-agent-connect-flex-human-handoff shows a stored language preference shaping the conversation. For voice language switching, see our guide to multilingual AI agents https://www.twilio.com/en-us/blog/insights/multilingual-ai-agents . Make the second conversation better than the first make-the-second-conversation-better-than-the-first Every repeated question tells a customer your AI agent doesn't know them. Recognize them, recall what matters, save what's new, and let memory follow them across channels and to your human team. Do that, and the second conversation goes smoother than the first. And imagine what it looks like by the tenth. And then, there are the times when your AI agent reaches out first: see our guide to building a proactive agent for AI outbound calling https://www.twilio.com/en-us/blog/insights/proactive-ai-agent-outbound-calling . Start for free https://www.twilio.com/try-twilio and build an AI agent with Conversation Memory, or talk to sales https://www.twilio.com/en-us/help/sales about bringing memory to your contact center. Frequently asked questions frequently-asked-questions How do I stop my chatbot from asking the same questions every time a customer returns? Twilio Conversation Memory stores what customers share as traits, observations, and conversation summaries. Agent Connect retrieves that memory before each reply, so the agent starts with what it already knows. Which platforms let an AI agent detect that a customer called yesterday and reference that context automatically? Twilio Conversation Orchestrator links a returning caller to the same customer profile, and Conversation Memory's Recall API filters memories by date, so the agent can pull up yesterday's conversation summary before it replies. Which customer engagement tools let an AI agent remember preferences across sessions? Twilio Conversation Memory saves preferences as traits, like preferred language or channel, and as observations from past conversations. Agent Connect loads them at the start of the next session. What tools let an AI agent update a customer profile mid-conversation based on new information? Twilio Conversation Memory's API lets an agent tool create observations or update traits during a live conversation. Automatic extraction runs later, after the conversation goes inactive or closes. Why does my AI agent forget customers between conversations? Twilio Conversation Memory can only recall a profile it can identify, and it extracts observations after a conversation goes inactive or closes. Check identifier links, extraction settings, and the agent's memory mode. Related Posts Related Resources Twilio Docs From APIs to SDKs to sample apps API reference documentation, SDKs, helper libraries, quickstarts, and tutorials for your language and platform. Resource Center The latest ebooks, industry reports, and webinars Learn from customer engagement experts to improve your own communication. Ahoy Twilio's developer community hub Best practices, code samples, and inspiration to build communications and digital engagement experiences.