Here at EdgeTier, we've just reached a milestone on the EdgeTier system. We are introducing our first Generative AI feature to the product: Interaction Summaries.
This feature pulls out the most important points from every customer conversation, so it’s faster to understand what happened. It will definitely save you lots of time if you’re someone who reads through customer chats and emails every day.
We’re data enthusiasts at heart, keen to ensure that your insights are powered by the latest advancements in AI tech. It was a rewarding journey bringing this feature to life, and this launch signals the start of a transformative wave of GenAI features that will redefine the EdgeTier experience.
So let’s dive in further.
What are Interaction Summaries?
The Interaction Summaries feature offers concise bullet-point summaries of your customer interactions. When you open an interaction, you can now quickly review this section to get info on customer sentiment, primary issues discussed, and resolutions provided, so you can make informed decisions without sifting through the entire conversation.
How Are Interaction Summaries Generated?
To develop this feature, we built a new service that combines the power of Claude AI and AWS Bedrock. Here’s a closer look at the technology behind our AI-powered summarisation:
Claude AI: Uses a large language model (LLM) to understand and distil conversations into essential points. First, you pick an interaction to summarise. Then, Claude AI analyses the conversation’s context, uses our prompts to detect the key elements of the interaction, and generates a coherent summary for you.
AWS Bedrock: Provides the robust and scalable infrastructure needed to process these summaries efficiently. It ensures that our AI models run smoothly and deliver reliable results, so we can display the summaries for you in just a few seconds.
Custom Prompts: In collaboration with our expert Data Science team, we’ve developed tailored prompts that guide the AI in pinpointing the most relevant information in each conversation. These prompts ensure that the summaries are not only accurate but also insightful, highlighting the main reason for contact, your customers’ emotions, and the solutions offered by the agent.
Safety and Privacy
We realise that introducing new services that process conversation data could raise concerns. Rest assured, EdgeTier remains fully ISO27001 compliant. When you use our new LLM features, we can ensure that your information will remain secure and private.
Why EdgeTier?
With our all-in-one conversation intelligence platform, contact centres can analyse 100% of support conversations in real time, react faster to customer issues and deliver actionable insights, benefiting your entire business.
- Real-Time Issue Detection: Spot problems as they happen and address them before they escalate, keeping customers happy and loyal.
- Actionable Feedback: Share valuable insights with your team to enhance products, services, and customer experiences.
- Targeted Training: Use automated QA to identify training needs and support your team's performance, increasing CSAT.
- Prevent Future Issues: Leverage customer feedback to anticipate and prevent future problems, ensuring a smoother customer journey.
I’m incredibly excited about the potential of Interaction Summaries to save time and raise awareness of what’s going on in your contact centre. To quote our CEO, Shane Lynn, “The new wave of AI, ‘Large Language Models’ (LLMs), can’t do everything (yet). However, they are exceptional at processing batches of text. Any business process involving lots of messages, content, text, or communications will benefit from this technology. Customer service is the obvious place, and there’s huge enthusiasm (and perhaps some hype!).”
