Designing AI assistants with 50 years of conversation analysis with Liz Stokoe

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

Liz Stokoe joins us as she chats designing AI assistants with 50 years of conversation analysis

Liz Stokoe is an author and professor at the London School of Economics

In this episode

00:00 Introduction
02:20 Welcome Liz Stokoe
06:15 Real insights while designing a product
10:00 Why do conversation analysis?
18:37 Important principles while designing
24:12 Complaints process
27:25 Designing a staged conversation
32:19 Different ways people speak
35:20 Conversation analysis most important discipline
41:14 Quickfire round – good practice or not good?
50:00 Intervention in cases
53:24 Using conversation analysis to prevent fraud
1:01:17 Analysing conversations in real life scenarios
1:04:10 Outro

Register for our upcoming webinar with Quiq here

Timestamps

00:00|Introduction
02:20|Welcome Liz Stokoe
06:15|Real insights while designing a product
10:00|Why do conversation analysis?
18:37|Important principles while designing
24:12|Complaints process
27:25|Designing a staged conversation
32:19|Different ways people speak
35:20|Conversation analysis most important discipline
41:14|Quickfire round – good practice or not good?
50:00|Intervention in cases
53:24|Using conversation analysis to prevent fraud
1:01:17|Analysing conversations in real life scenarios
1:04:10|Outro

Share

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Host

Kane Simms

A strategic AI advisor who, for the past decade, has helped business leaders and product owners transform customer experience using conversational and generative AI.

Share

✓   Link copied

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Top articles and podcasts

Related content

Cobus Greyling: why intents, graphs and conversation design have come full circle
Cobus Greyling on where enterprise AI is really heading: data, security, forward-deployed engineers and conversation design.
From answers to actions: building better government AI
Pete Kowalczyk on knowledge graphs, goal detection and moving AI from answering questions to taking action.
What’s really breaking your AI agents?
Discover where conversational AI projects actually break: contradictory source data, manual process and weak testing.
How Simplyhealth scaled voice AI to resolve 30% of calls
Paul Atkins, Head of Business Optimisation at Simplyhealth, breaks down how they scaled voice AI to resolve almost a third of calls, and what it took to get there.