Responsible AI, Real Results with Citizens Advice

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

In this episode on the VUX World podcast, we chat all about the innovative AI journey of Citizens Advice with Stuart Pearson.

We discover how a nonprofit organisation is revolutionising customer support through Caddy, an intelligent AI assistant that reduces average handle time by 50% while maintaining a rigorous ethical approach.

Stuart shares the meticulous process of developing an internal AI tool that supports contact centre agents, highlighting the importance of responsible AI implementation. From initial challenges with chatbots to creating a sophisticated AI solution, this podcast reveals how organisations can leverage artificial intelligence to enhance productivity, improve service delivery, and ultimately help more people.

In this episode

00:00 – Episode intro
03:30 – Welcome Stuart Pearson
04:54 – What Citizens Advice is
06:30 – Identifying key issues
11:35 – Revisiting the chatbot
14:05 – Thinking about the role of AI
18:45 – Content to agent
22:53 – Identifying content
25:06 – Retrieval and generation
28:18 – Reducing handle time
29:24 – Levels of advice
34:21 – Adopt long term philosophy
36:47 – No room for error
38:15 – Challenges faced & advice
47:24 – Using LLMs
51:16 – Outro

Subscribe to VUX World.

Subscribe to The AI Ultimatum Substack.

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.