“Like Having a Really Bad PA”: The Gulf between User Expectation and Experience of Conversational Agents
A study of the gap between what conversational interfaces lead people to expect and what those systems can actually do.
What it contributes
Interviews with 14 users of conversational agents reveal mismatches between expectations, system capabilities and users' understanding of the interaction.
Read with care
The study concerns assistants before today's LLM systems. Its design questions remain useful, but its findings should not be presented as a current capability benchmark.
Why it belongs here
Read before deciding how a chatbot introduces itself, communicates limits and helps people recover from failures.
Full paper published at CHI 2016, pages 5286–5297.
Source reading depthAuthor-hosted paper's abstract and publication details inspected. This is a source note, not a full critical review.
1,143 citations · OpenAlex ↗
Snapshot: 1 October 2026. Citation counts indicate attention, not reliability; counts differ across databases.