Loading…
Topic
Chatbot
9 posts about Chatbot. Every summary links to the original.
- 9 posts
- 1 company
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
Our biggest releases of 2022: A next-generation Inbox, our most powerful Messenger yet, and the introduction of tickets - The Intercom Blog
Intercom’s 2022 releases include a fully customizable Messenger with no-code design, brand matching, and a News section for proactive announcements. The company introduced a messenger-first ticketing solution that allows teams to collaborate without switching tools, reducing costs and improving response times. The next-generation Inbox features faster load times, shortcuts, improved Smart Replies, dark mode, and a manager-specific view. A visual bot builder enables no-code creation of sophisticated automation flows, while Custom Actions and Custom Objects let bots access external data for higher self-solve rates. Other releases include Switch for moving phone calls to chat, in-product Surveys, and Instagram message management within the Inbox.
8 New Features To Increase Conversions And Grow Your Business
Intercom announced eight new features aimed at helping sales, support, and marketing teams manage volume and capacity more efficiently to increase conversions and grow their business. Custom Bots can qualify leads automatically, book meetings, and work 24/7 without code, connecting to the tech stack and accelerating sales cycles by delivering qualified leads when prospects are live. The new Intercom App Store offers over 100 apps for acquiring, engaging, and retaining customers, including Zoom Webinars, Content Showcase, Coda, and PieSync, along with a new Messenger framework and Developer Hub for building custom apps. Updated webhooks and APIs provide more flexibility to trigger actions based on conversation tags, check teammate availability with the Admins API, and run assignment rules at any point in a conversation. Other additions include downloadable conversation transcripts for both teammates and customers, and free developer workspaces for safe building and testing.
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.
The Ultimate Customer Support Tech Stack for 2024
Customer support teams face inefficiencies from outdated and disconnected tools, with 54% unable to personalize support and 50% wasting time switching between applications. The modern support tech stack should be built around a connected framework like Intercom’s Support Funnel, which integrates three layers: proactive messaging to preempt issues, self-serve bots and knowledge bases for repetitive queries, and human support with automated workflows. An all-in-one platform such as Intercom provides the foundation, offering live chat, chatbots, a team inbox, integrations, and reporting capabilities. The stack should also integrate with specialized tools like Stripe for subscription management, Aircall for phone support, and RemoteHQ for co-browsing, as well as automation tools like Zapier. This approach aims to scale personalized support without proportional cost increases, improving customer satisfaction and retention while shifting support from a cost center to a value driver.
Building bots for success: The custom bot that saved logistics platform Stuart over 2.5k hours per week - The Intercom Blog
Stuart, a logistics platform owned by GeoPost, faced the challenge of scaling support for its delivery partners without slowing response times or losing the personal touch. After analyzing their support journey, Head of LiveOps Andrew Baylis and Program Manager Marina Alejo identified that manual handling of every conversation was inefficient and implemented an Intercom Custom Bot, the courier bot. The bot operates across four delivery stages, resolving common queries automatically and collecting context before routing complex issues to agents, reducing manual intervention to 55%. As a result, the bot saves over 2,500 support team hours and automatically resolves 55,000 chats per week, with response times under 30 seconds and resolutions four times faster. Additionally, handling time per case is two minutes faster and delivery partner satisfaction has increased by 4%, with plans to further expand self-service capabilities.
Automation in action: Proven ways to boost the bottom line with self-serve support - The Intercom Blog
Self-serve support combines automation and human expertise to deliver scalable yet personal customer service. The Conversational Support Funnel framework integrates proactive, self-serve, and human support layers to balance efficiency and personalization. Case studies demonstrate significant gains: Stuart reduced support workload by over 2,500 hours weekly using Custom Bots, and in a test with a pharmacy client, 70% of inbound queries were resolved through self-serve. SMARTY saved 7,000 support team hours annually with Resolution Bot, achieving a 99% reduction in median first-response time. Livestorm maintained a 94% customer satisfaction score while automatically resolving one in four queries, and Rugs.com increased support efficiency tenfold by switching from phone to chat. The post notes that 57% of support teams now measure revenue impact, and self-serve support lowers response times, frees agents for complex issues, and drives retention and expansion.
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.
Meet Fin: Intercom's AI chatbot, Powered by GPT-4
Intercom launched Fin, an AI chatbot powered by GPT-4 and fine-tuned for customer support, combining existing Resolution Bot technology with the new model. Fin answers questions solely using content from a business’s existing help center, reducing hallucinations by constraining its knowledge base and refusing out-of-domain queries. It requires minimal setup, automatically ingesting articles from Intercom or Zendesk help centers, and updates responses when articles change. Fin links to source articles for verification, handles multi-turn conversations, and seamlessly passes unanswered queries to human support representatives. Limitations include potential inaccuracies, high cost of GPT-4, and latency of 10 or more seconds, but Intercom expects improvements, is exploring configuration settings for creativity tradeoffs, and is rolling out a limited beta with a waitlist.
A complete guide to Fin, the AI bot transforming customer service
Intercom has launched Fin, an AI chatbot powered by OpenAI’s GPT-4 and Intercom’s proprietary technology, now available to all customers. Fin ingests existing support content to resolve up to 50% of queries, providing answers constrained to approved materials to minimize hallucinations. The bot is designed to be trustworthy, controllable, and seamless, with features like custom actions, audience targeting, and the ability to hand off complex queries to human agents. Fin is priced per resolution, charging only when a query is successfully resolved without human escalation. Upcoming features include multilingual support in 43 languages, integration of conversation data, and email as a channel.
Related topics
All topics →Weekly digest
The best engineering reads, once a week.