# Customer Service Published articles for Customer Service. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents DevFeed: [Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents]() Original publisher: [Read original article]() Author: Maia Bridi Published: 2026-09-09T16:44:02Z Content type: article Language: en Sources: [The Intercom Blog]() Topics: [AI Agent](), [Artificial Intelligence]() Tags: [ai-sentiment](), [customer-service](), [end-user-sentiment](), [news-updates]() ### AI overview A research report on end-user sentiment and conditional trust in AI Agents, especially for customer-service queries. ### Source excerpt We asked over 1,000 end users how they felt about interacting with AI Agents, how capable they think they are, and how much they trust them. Here are our findings. ## How to disclose AI to customers without killing the conversation DevFeed: [How to disclose AI to customers without killing the conversation]() Original publisher: [Read original article]() Author: Jesse Sumrak Published: 2026-09-01T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [Artificial Intelligence](), [AI Agent]() Tags: [ai](), [ai-agent](), [customer-service](), [how-to](), [industry-insights]() ### AI overview This tutorial explains how customer service teams should disclose AI agents at the start of conversations. It recommends brief, explicit introductions that describe the agent's capabilities and provide an immediate way to reach a human. It also discusses research indicating that honest, well-timed disclosure supports customer interactions better than hiding or minimizing AI involvement. ### Source excerpt Teams worry that telling customers they're talking to AI will hurt engagement. Not true. Learn what to say, when, and what to avoid instead. ## Why 78% of customers try to bypass your AI agent DevFeed: [Why 78% of customers try to bypass your AI agent]() Original publisher: [Read original article]() Author: Jesse Sumrak Published: 2026-08-28T00:00:00Z Content type: article Language: en Sources: [Twilio Blog]() Topics: [AI Agent](), [Support](), [Automation](), [Artificial Intelligence]() Tags: [agents](), [ai](), [ai-agent](), [ai-transparency](), [automation](), [customer-service](), [industry-insights](), [support]() ### AI overview Twilio research reports that 78% of consumers have tried to bypass an AI agent to reach a human, while 63% want an easy escalation path. The article attributes this behavior to concerns about transparency, high-stakes tasks, and inefficient interactions, and describes consumers' preferences for disclosure, human escalation, and reliable AI. ### Source excerpt New Twilio research finds 78% of consumers have tried to bypass an AI agent to reach a human. Here's why (and what to do about it). ## How Decagon uses AI for design system saturation DevFeed: [How Decagon uses AI for design system saturation]() Original publisher: [Read original article]() Author: Jenny Xie Published: 2026-07-10T20:30:56.769000Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Figma](), [Model Context Protocol](), [AI-assisted coding](), [agentic-coding](), [Code]() Tags: [agentic](), [agentic-coding](), [agents](), [ai](), [ai-agents](), [code](), [customer-service](), [design](), [developer](), [figma](), [mcp]() ### AI overview Figma MCP and Figma Make helped Decagon scale an organization-wide design system, improve design-to-code handoffs, and support rapid customer-service product development. The article explains how structured Figma libraries give designers, developers, and coding agents a shared source of truth. ### Source excerpt The fast-growing customer experience platform explains how Figma MCP and Figma Make helped them scale a new design system and keep pace with customer requests. ## How Deutsche Telekom is rewiring telecommunications with AI DevFeed: [How Deutsche Telekom is rewiring telecommunications with AI]() Original publisher: [Read original article]() Published: 2026-07-10T07:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [Generative AI](), [ChatGPT](), [OpenAI](), [API](), [Network](), [NOC]() Tags: [ai](), [api](), [chatgpt](), [company](), [customer-service](), [enterprise](), [generative-ai](), [infrastructure](), [network](), [openai](), [operations](), [workflows]() ### AI overview Deutsche Telekom is pursuing an AI-native transformation of its telecommunications business, applying generative AI to customer service, employee workflows, network operations, and customer communications. The company expanded access to ChatGPT Enterprise, encouraged experimentation, and is working with OpenAI and other companies to redesign how work and customer interactions are delivered. ### Source excerpt How Deutsche Telekom is becoming an AI-native telco with OpenAI-transforming customer service, employee workflows, network operations, and the future of voice. ## MUFG aims to become AI-native with OpenAI DevFeed: [MUFG aims to become AI-native with OpenAI]() Original publisher: [Read original article]() Published: 2026-07-07T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [OpenAI](), [Artificial Intelligence](), [AI Strategy](), [AI Chat](), [Security]() Tags: [ai](), [artificial-intelligence](), [banking](), [chatgpt](), [customer-service](), [efficiency](), [enablement](), [enterprise](), [financial-services](), [innovation](), [japan](), [openai](), [operations](), [partner](), [scale](), [security](), [systems](), [technology](), [workflows]() ### AI overview MUFG is working with OpenAI to become an AI-native financial group. It has begun rolling out ChatGPT Enterprise to approximately 35,000 Mitsubishi UFJ Bank employees, combining secure enterprise use, workflow transformation, employee enablement, and new AI-powered customer experiences. ### Source excerpt MUFG uses ChatGPT Enterprise to build an AI-native organization, improve workflows, and deliver new AI-powered financial services at scale. ## How to measure the customer experience as AI scales DevFeed: [How to measure the customer experience as AI scales]() Original publisher: [Read original article]() Author: William Lane Published: 2026-07-01T16:44:49Z Content type: article Language: en Sources: [The Intercom Blog]() Topics: [Artificial Intelligence](), [data]() Tags: [agent](), [ai](), [ai-agent](), [ai-agent-blueprint](), [ai-automation](), [customer](), [customer-service](), [data](), [metrics]() ### AI overview The article explains why CSAT becomes insufficient as AI handles more customer conversations. It recommends evaluating every interaction with AI-powered scoring to provide broader visibility into service quality, resolution, and customer effort. ### Source excerpt Traditional support metrics weren't designed for AI handling most of your conversations. As your Agent takes on more, the gaps in what you can see get bigger. Here's how to measure the full customer experience. ## The new product introduction process: How to make sure your Agent is ready every time you ship DevFeed: [The new product introduction process: How to make sure your Agent is ready every time you ship]() Original publisher: [Read original article]() Author: Sean Reid Published: 2026-06-26T17:40:52Z Content type: tutorial Language: en Sources: [The Intercom Blog]() Topics: [AI Agent](), [Support]() Tags: [agent](), [ai-agent](), [customer-service](), [features](), [how-to](), [npi](), [support]() ### AI overview The article explains Fin's new product introduction process for keeping an AI Agent's knowledge base current with product releases. It recommends involving support early, preparing and reviewing content, removing outdated information, and testing the Agent before launch. ### Source excerpt Every time you launch a product, your Agent's knowledge base needs to keep pace. Here's the NPI process Fin uses to make Agent readiness part of every release. ## Conversation design: How to make your AI Agent communicate like your team DevFeed: [Conversation design: How to make your AI Agent communicate like your team]() Original publisher: [Read original article]() Author: Fred Walton Published: 2026-06-18T16:55:07Z Content type: article Language: en Sources: [The Intercom Blog]() Topics: [AI Agent](), [Artificial Intelligence](), [Support]() Tags: [agent](), [ai](), [ai-agent](), [ai-agent-blueprint](), [ai-automation](), [communication](), [context](), [customer](), [customer-experience](), [customer-service](), [customers](), [designer](), [experience](), [process](), [responses](), [structure](), [support](), [teams](), [trust](), [voice]() ### AI overview This article explains how conversation design helps an AI Agent communicate consistently with a support team. It covers voice, tone, response structure, adapting language to customer context, and designing smooth handoffs to human support representatives. An Intercom example reports that a warmer opening message increased CSAT from 72.8% to 78.4%. ### Source excerpt If nobody on your team owns how your AI Agent communicates, it defaults to sounding like an LLM. Conversation design is the discipline that fixes that. ## How to make the case for giving your AI Agent system access DevFeed: [How to make the case for giving your AI Agent system access]() Original publisher: [Read original article]() Author: Dawn Perrott Published: 2026-06-11T12:04:14Z Content type: tutorial Language: en Sources: [The Intercom Blog]() Topics: [AI Agent](), [Back end](), [knowledge-management](), [AI Platforms/Deployment]() Tags: [2026](), [agent](), [ai-agent](), [ai-agent-blueprint](), [ai-automation](), [backend](), [customer-service](), [deployment](), [how-to](), [integration](), [knowledge-management](), [management-tools]() ### AI overview The article explains why AI Agents need access to backend systems to move from answering customer questions to completing actions. It argues that connecting support agents to CRM, billing, and order-management systems can enable end-to-end resolution, and describes how Intercom's Procedures with system access handled complex workflows better than fixed, scripted Tasks in some cases. ### Source excerpt Without access to your backend systems, your AI Agent can answer questions, but it can't take action. A customer asks to change their payment plan, they get a clear explanation, but a support rep still has... ## AI is becoming a first hire for small businesses DevFeed: [AI is becoming a first hire for small businesses]() Original publisher: [Read original article]() Published: 2026-05-25T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [ChatGPT]() Tags: [ai](), [business](), [chatgpt](), [customer-service](), [global-affairs](), [product-development](), [research]() ### AI overview OpenAI reports that at least four million people in the United States used ChatGPT during March 2026 to plan, start, run, or grow small businesses. The article describes how entrepreneurs use it for tasks such as branding, product development, business validation, marketing, pricing, customer communication, and administrative work. ### Source excerpt New research shows how 4 million Americans use ChatGPT to start, run, and grow small businesses, lowering the cost of entrepreneurship with AI. ## Parloa builds service agents customers want to talk to DevFeed: [Parloa builds service agents customers want to talk to]() Original publisher: [Read original article]() Published: 2026-05-07T11:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [AI Agent](), [Artificial Intelligence](), [OpenAI](), [configuration](), [ChatGPT](), [Deployment]() Tags: [agents](), [ai](), [ai-agent](), [ai-agents](), [apis](), [build-ai-agents](), [customer-service](), [deployment](), [model](), [openai](), [performance](), [platform](), [production](), [real-time](), [routing](), [scale](), [startup](), [voice]() ### AI overview Parloa uses OpenAI models, including GPT-5.4, to power a platform for designing, simulating, deploying, and managing scalable voice-based AI customer service agents. The platform lets business teams configure agent behavior in natural language, connect internal systems and APIs, test realistic conversations, and optimize reliability, latency, and production performance. ### Source excerpt Parloa leverages OpenAI models to power scalable, voice-driven AI customer service agents, enabling enterprises to design, simulate, and deploy reliable, real-time interactions. ## Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents DevFeed: [Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents]() Original publisher: [Read original article]() Author: Rahul Bajaj; Jaya Nupur; Anuj Garg; ben burtenshaw Published: 2026-04-16T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [rlvr](), [openenv](), [Reinforcement learning](), [qwen](), [Large Language Model](), [AI Development](), [Open Source]() Tags: [agents](), [customer-service](), [e-commerce](), [llm](), [open-source](), [openenv](), [qwen](), [reinforcement-learning](), [research](), [rlvr](), [tools](), [training](), [workflows]() ### AI overview Ecom-RLVE introduces EcomRLVE-GYM, a suite of verifiable, multi-turn, tool-augmented e-commerce environments for training conversational agents. It uses procedural task generation, adaptive difficulty, and algorithmically verifiable rewards across shopping and customer-service workflows, with early results from training a Qwen 3 8B model using DAPO. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Improved Gemini audio models for powerful voice experiences DevFeed: [Improved Gemini audio models for powerful voice experiences]() Original publisher: [Read original article]() Author: Bibo Xu Published: 2025-12-12T17:50:50Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [Google](), [Google AI](), [voice ai](), [speech-to-speech](), [Artificial Intelligence](), [real-time](), [Streaming](), [Google Cloud Platform (GCP)]() Tags: [ai-studio](), [audio](), [customer-service](), [enterprise](), [gemini](), [google-cloud](), [none](), [real-time](), [speech](), [speech-to-speech](), [streaming](), [vertex-ai](), [voice]() ### AI overview Google describes upgrades to Gemini 2.5 Native Audio for live voice agents, including better function calling, instruction following, and multi-turn conversations. The model is available across Google AI Studio and Vertex AI, with rollouts to Gemini Live and Search Live. The article also introduces beta live speech-to-speech translation in Google Translate. ### Source excerpt An upgraded Gemini 2.5 Native Audio model across Google products and live speech translation in the Google Translate app. ## The branding for Intercom's AI summit looks like an alien superbloom DevFeed: [The branding for Intercom's AI summit looks like an alien superbloom]() Original publisher: [Read original article]() Author: Jenny Xie Published: 2025-09-19T00:00:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Figma](), [Artificial Intelligence](), [ide]() Tags: [ai](), [branding](), [customer-service](), [design](), [design-systems](), [events](), [figma](), [summit]() ### AI overview Intercom's Creative Studio used Figma to develop the visual identity for Pioneer, its customer service and AI summit. The team explored broad creative concepts through mood boards, collaborated across disciplines, and embedded motion, imagery, and vector assets into a brand system spanning digital campaigns and the live event. ### Source excerpt For the customer service and AI event Pioneer, Intercom's designers used Figma to create a visual language of surreal flowers and shape-shifting pollen. ## Using Generative AI to enhance customer support DevFeed: [Using Generative AI to enhance customer support]() Original publisher: [Read original article]() Author: Davy Costa Published: 2025-05-23T20:28:40Z Content type: article Language: en Sources: [Avenue Code]() Topics: [Generative AI](), [Retrieval Augmented Generation (RAG)](), [Chat Bot](), [Support](), [data](), [Finance]() Tags: [ai](), [customer-service](), [finance](), [generative-ai](), [rag](), [retrieval](), [support]() ### AI overview The article describes a Brazilian credit union system that uses Generative AI and a Retrieval-Augmented Generation (RAG) system to build a customer-support chatbot. The chatbot retrieves relevant information from public website documents and generates responses to questions about the institution's services and policies. The system is fine-tuned with a publicly available finance dataset containing 52K instruction-following examples. ### Source excerpt A credit union system is using Generative AI to enhance customer support, developing an intelligent chatbot designed to provide accurate and timely responses to user inquiries about their services, policies, and other relevant information. ## The ultimate guide to on-call schedules DevFeed: [The ultimate guide to on-call schedules]() Original publisher: [Read original article]() Author: Chris Evans Published: 2024-09-12T13:47:47Z Content type: article Language: en Sources: [The incident.io Blog]() Topics: [incident](), [Incident response](), [Slack]() Tags: [best-practices](), [customer-service](), [engineering](), [guide](), [incident](), [incident-channel](), [incident-management](), [incident-response](), [on-call](), [operational](), [operations](), [outage](), [outages](), [post-mortem](), [slack](), [slack-incident](), [support](), [tools]() ### AI overview A guide to designing and managing on-call schedules, covering scheduling patterns, shift management practices, common mistakes, and ways to support effective incident response while reducing downtime and employee burnout. ### Source excerpt Learn how to create effective on-call schedules that balance operational efficiency with employee well-being. Explore best practices, scheduling patterns, and tools to minimize downtime and prevent burnout. ## Dear Customers, we couldn't have done it without you. With love, incident.io DevFeed: [Dear Customers, we couldn't have done it without you. With love, incident.io]() Original publisher: [Read original article]() Author: incident.io Published: 2024-07-12T17:38:00Z Content type: article Language: en Sources: [The incident.io Blog]() Topics: [incident](), [Slack]() Tags: [awards](), [customer](), [customer-service](), [incident](), [incident-channel](), [incident-management](), [incident-response](), [outage](), [post-mortem](), [reviews](), [slack](), [slack-incident]() ### AI overview incident.io thanks its customers for helping it earn Summer 2024 G2 accolades, including the #1 position in G2's Relationship Index and a second Best Relationship award. The article emphasizes customer relationships, product support, reviews, and the Customer Success team. ### Source excerpt We're over the moon to share our Summer 2024 accolades from G2, including snagging the #1 spot in their Relationship Index! ## How Carvana fuels consistency and scale DevFeed: [How Carvana fuels consistency and scale]() Original publisher: [Read original article]() Author: Caitlin Lee Published: 2024-04-16T00:00:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Figma](), [systems](), [Sketch](), [pdf]() Tags: [config](), [customer](), [customer-service](), [design](), [design-systems](), [design-tools](), [developers](), [e-commerce](), [engineering](), [figma](), [growth](), [libraries](), [pdf](), [platform](), [scale](), [speed](), [standards](), [tools]() ### AI overview Carvana moved its fragmented design system from a PDF-based UI kit, Principle, and Sketch to Figma to create a centralized source of truth for design and engineering. The transition improved handoffs and helped the company maintain consistency and design quality during rapid growth. Figma variables later helped standardize properties such as spacing and corner radii. ### Source excerpt Carvana, the leading e-commerce brand for buying and selling used cars, steers itself through periods of growth and evolution by leveraging its design system and variables. ## Citizen Threat Modeling and more data DevFeed: [Citizen Threat Modeling and more data]() Original publisher: [Read original article]() Author: Adam Published: 2018-03-14T00:00:00Z Content type: opinion Language: en Sources: [Shostack & Friends Blog]() Topics: [data](), [audit]() Tags: [audit](), [customer-service](), [data](), [fraud](), [legal](), [marketing](), [operational](), [outsourcing](), [payment](), [processors]() ### AI overview The article discusses citizen threat modeling and examines PayPal's disclosure of more than 600 companies it might share customer data with. It considers whether this level of disclosure is unusual and how PayPal's categories could inform analysis of secondary data flows, while noting ambiguities in some category names. ### Source excerpt [no description provided] ## Making Customer Support Requests Visible in Real Time to Measure End-User Quality DevFeed: [Making Customer Support Requests Visible in Real Time to Measure End-User Quality]() Original publisher: [Read original article]() Author: espen Published: 2011-07-04T06:50:39Z Content type: article Language: en Sources: [Finn.no]() Topics: [Support](), [Logging](), [real-time](), [HTML](), [App]() Tags: [customer-service](), [html](), [logging](), [making](), [persistence](), [real-time]() ### AI overview The article describes an effort to make customer support requests visible in real time across an organization so teams could better understand the quality of their work. Because existing ticketing and call-center statistics lacked detail, the team observed the support process, introduced paper-based logging, and created an HTML prototype based on that workflow. ### Source excerpt In the post Putting a face on quality we talked about how we wanted to bring our end users closer to our developers by visualizing tweets about our service. This was only one of many tasks we performed in order to get a better feel on how our work effects our users. In this post we'll show you what we did in order to put numbers on end user quality by working with out customer service team. Up until now our customer service team had a hard time visualizing the effect our code had on end users. They where publishing numbers on number of incoming requests, but these numbers where on a weekly basis at best. Research in the wild Therefor we set out with the goal of making all support requests visible in real time for the entire organization. Out hypothesis was that this would provide everyone on our teams from developers, product owners and sales staff with a clear view on what kind of quality they deliver. In order to figure out what our application should look like we set out to see what the reality was and sat with our customer service team to see how they worked. But they had no system in place for logging requests and what area of our service it was about. All we had was the statistics from our support ticket system and call center. These systems did not provide enough detailed information, therefor our Lean task force team encouraged them to start logging requests on paper then put it all into a set of Excel spread sheets. Needless to say this required quite a bit of effort from the people one the customer service team and it was not a solution for the long term. When deciding how to approach creating a application for logging requests we looked at how the analog logging process was performed. Realizing that a request could be for more than one problem area and effect multiple teams we realized that the paper layout was in fact ideal. We created a quick prototype in HTML and had the users test it. This prototype had no persistence and did only show how the process