In November 2022, Jake Moffatt used Air Canada’s website chatbot to ask about bereavement fares after a death in the family. The chatbot said the reduced fare could be claimed within 90 days after travel. Moffatt booked at full price and applied. Air Canada refused, because its real policy did not allow retroactive claims.<\/p>\n\n\n\n
The detail that matters most: the chatbot pointed Moffatt to Air Canada’s own bereavement travel page, and that page said the opposite. The correct answer was one click away. The bot still got it wrong.<\/p>\n\n\n\n
When the case reached British Columbia’s Civil Resolution Tribunal in 2024, Air Canada argued, in effect, that the chatbot was responsible for its own words. The tribunal called that “a remarkable submission”<\/a>, held the airline liable for negligent misrepresentation and ordered it to pay C$812.02 in damages, interest and fees.<\/p>\n\n\n\n That was a text chatbot, not a voice agent. On a phone call the same error lands harder. There is no link to click, no transcript to scroll back through, no second tab where the customer might spot the contradiction. They hear the answer once, in a warm and confident voice, and act on it.<\/p>\n\n\n\n More of these calls are coming. In a Gartner survey of 321 customer service leaders<\/a>, 91% said executive leadership was pushing them to implement AI in 2026.<\/p>\n\n\n\n This guide covers what actually reduces false answers on customer calls. The short version: a voice agent is not one model that needs stricter instructions. It is a chain of systems, and every link in the chain can produce a fluent, confident, wrong sentence.<\/p>\n\n\n\n The most useful recent evidence comes from \u03c4-Voice<\/a>, a benchmark published in March 2026 as a voice extension of the \u03c4\u00b2-bench agent benchmark. It put voice agents through 278 realistic customer service tasks across retail, airline and telecom: returns, flight changes, plan changes, each with real policies to follow and real backend actions to take.<\/p>\n\n\n\n A text-based reasoning agent completed 85% of the tasks. Voice agents built on realtime APIs from OpenAI, Google and xAI completed 31-51% with clean audio, and 26-38% once background noise and diverse accents were added.<\/p>\n\n\n\n Two findings matter more than the headline numbers.<\/p>\n\n\n\n First, reviewers traced 79-90% of failures to agent behavior, not to bad audio. The agents made reasoning and policy mistakes even when transcription was accurate.<\/p>\n\n\n\n Second, the failures were specific and familiar to anyone who has run a contact center. Authentication was the biggest bottleneck, with agents mistranscribing names and emails even when callers spelled them letter by letter. And in one simulated call, an agent told the customer “I’ve updated your shipping address” without ever calling the tool that updates it.<\/p>\n\n\n\n Read the numbers with the right caveat. The benchmark tested general-purpose realtime models inside a research harness, not production deployments with custom retrieval, validation and handoff built around them, and the authors note that cascaded speech-to-text, LLM and text-to-speech pipelines were not included. The distance between 85% and 31% is the work production engineering exists to close. It is an argument for building the system around the model with care, not an argument against voice agents.<\/p>\n\n\n\n Here is where that system can break:<\/p>\n\n\n\nA voice agent can be wrong in seven different places<\/h2>\n\n\n\n