Loading…
Topic
Conversational AI
8 posts about Conversational AI. Every summary links to the original.
- 8 posts
- 2 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Posts
Built for you: Powerful updates to Series, Banners, Resolution Bot, and more to help you stay personal at scale - The Intercom Blog
Intercom announced powerful updates to Series, Banners, Resolution Bot, and other tools to help businesses scale personalized customer interactions. Series now enables split testing of up to five message variants, team annotations, company-level goals from company data, and tag removal to streamline workflows. Banners can be non-dismissible to ensure customers take action and trigger Product Tours from the banner for guided walkthroughs. Resolution Bot introduces looping mode to answer multiple questions, auto-closes conversations after three minutes of inactivity, includes a bot intro, and offers bot-only self-service with a configurable link. Additional updates include granular sidebar permissions to restrict inbox access, no-reply post messages, mobile carousel and article triggers from in-app buttons, iOS universal links, and API version 2.3 for exporting conversation data.
Need for speed: how to address leads faster with live chat - The Intercom Blog
A Harvard Business Review study of 1.25 million sales leads found that responding within an hour makes a deal seven times more likely to close than a two-hour response. Live chat on a website is the fastest way to achieve that speed, bypassing the delays of contact forms and email follow-ups. The first tactic is to offer live chat only to prospects matching an ideal customer profile, using tools like Clearbit to filter visitors so SDRs focus on qualified leads. The second is to combine a bot for collecting contact information with human sales development representatives for personalized conversations, avoiding over-automation that annoys prospects. The third is to set proper expectations by stating office hours, displaying average response times when unavailable, and hiding the chat outside business hours, which allows reps to be more thoughtful in their responses.
Principles of Bot Design: Successful Chatbot Design in 2021 [+Tips]
The post argues that early chatbot attempts have failed because they over-relied on natural language processing and artificial intelligence capabilities that do not yet exist, often making users feel duped. It presents eight opinionated design principles to guide practical conversational UI development, starting with never pretending to be human. Other core principles include keeping conversations incredibly simple and bounded to particular subjects with linear flows, using structured input like buttons and custom keyboards to avoid parsing errors, and respecting the chat medium by showing formatted card previews instead of raw URLs. The post also emphasizes providing a human escape hatch and optimizing for end-user experience rather than support team convenience, with admin views maintaining full conversation context. Finally, it notes that these principles should be strongly held as a decision-making north star but allowed to evolve as technical possibilities improve.
How to design an AI agent for resolution instead of rapport
Most conversation design guidance focuses on voice and tone, but consumers prioritize immediate issue resolution (40%), speed (40%), accuracy (38%), and 24/7 availability (38%) over rapport. The post recommends opening with capability, loading context before the first turn using persistent profiles, and designing a second option when the first fails. Escalation should be triggered by conversation rules like a second failed attempt or explicit request, not treated as an error condition. Confirmation turns should be cut except for irreversible actions, and agents should clearly state what they cannot do. An agent with customer history, a backup path, and a clean exit is more helpful than one with a carefully written persona but lacking those features.
Your customers don't want an AI friend. They want an answer.
A Twilio survey of 660 business leaders and consumers reveals a gap: 98% of organizations train AI to act more human, yet customers rank issue resolution, speed, accuracy, and availability above personality. Only 54% of consumers want human-like AI, versus 73% of brands. Behaviors customers call empathetic—acknowledging the specific situation, offering multiple solutions, using conversational language, offering compensation—depend on personalization and context, not tone. 51% of consumers find AI robotic, and 39% of businesses cite weak emotional understanding as a top dissatisfaction driver. The report recommends prioritizing context and personalization over personality, using tools like Twilio Conversation Memory and Conversation Orchestrator to make agents useful before charming.
The #1 AI behavior hurting your customers’ experiences
91% of brands report a drop in customer satisfaction from AI, and the top behavior causing this is losing context when customers change channels, cited by 40% of businesses. Three of the four main behaviors are context-related, with lack of empathy at 39%, inability to handle exceptions at 38%, and failing to understand at 36%. The infrastructure problem includes session boundaries, identity mismatches, channel-specific tooling, and batch timing that prevent context from following the customer, causing 74% of consumers to repeat themselves and 71% to abandon conversations. Twilio’s structural solutions—Conversations, Conversation Memory, and Conversation Orchestrator—attach context to the customer rather than the session and recommend starting with the chat-to-voice transition. To measure improvement, track repeat-explanation rate after a channel change, recognition rate, and abandonment at transition points.
What is AI agent orchestration? How it works in 2026
AI agent orchestration coordinates multiple AI agents working on a single task, deciding routing, carrying context, resolving contradictions, and escalating to humans when needed. It operates at two levels: the agent level, where frameworks like LangGraph route between specialized agents, and the conversational AI level, which preserves customer identity and history across Voice, SMS, and WhatsApp channels. Orchestration comprises four jobs: routing, shared memory and state, conflict resolution, and human escalation, with parallel execution requiring robust memory management. Twilio’s Conversation Orchestrator provides a shared conversation record as a system of record, while Conversation Memory extracts observations and resolves conflicts by updating records with the most recent version. The FAQ section addresses differences from workflow automation, comparison criteria for orchestration tools, and the mechanism for agent-to-human handoffs within the same session without callbacks.
More data won't make your AI smarter (here's what will)
Twilio research found that 99% of companies report something blocks them from understanding customers, with 48% citing connecting data across channels as the top obstacle. The problem isn’t data collection, which has succeeded, but the missing data activation layer that makes context usable in the eight seconds an AI agent has before a customer gives up. Twilio’s solution involves three elements: continuity across channels, real-time profile freshness, and retrieval of relevant history mid-conversation. Twilio Conversations treats touchpoints as a single lifecycle, Conversation Memory syncs new details in real time, and Conversation Intelligence surfaces approved documents alongside history. Twilio recommends starting small by picking one handoff where customers repeat themselves and making context survive it, rather than feeding the AI more data.
Related topics
All topics →Weekly digest
The best engineering reads, once a week.