MavenAGI is a new software company for the AI era. They recently launched an AI customer service agent, built on the flexibility of GPT-4, which a number of companies like Tripadvisor, Clickup and Rho are already using to save time and better serve their customers.
Customer support is expensive yet disappointing
In today's customer service environment, no one is winning.
Service representatives face repetitive work, demanding ticket volume, disorganized documentation, and delays in escalations. Customers get frustrated explaining issues and waiting for answers, and companies struggle to meet their desire for good customer service. Up to 90% of consumers expect an “immediate” customer service response, and more than half of consumers say they’d drop a company and use a competitor after just one bad customer service experience.
For all this frustration, the average support ticket still costs $40, mostly in labor but also in overlapping systems used to store knowledge. MavenAGI CEO Jonathan Corbin saw customer support as a pain point ready for an overhaul. “Existing systems and siloed data have made it challenging to deliver a great experience in a cost-effective manner," he says, "Companies have long thought they had two options for support: low cost or high quality.”
Training GPT-4 to set a new standard of customer support
Many efforts have been made to use chatbots for customer service, but the experience has by and large been unsatisfying. Bots often misunderstand the question, give unhelpful answers, or sound like robots. AI models were not advanced enough to give human-quality answers.
That changed with GPT-4. CPO Eugene Mann says, “GPT-4 was the first time we looked at something that looked like human intelligence and could solve that last-mile problem of communication.”
MavenAGI works by training GPT-4 to the context of customer service in three stages:
- Maven processes and ingests large volumes of diverse content regardless of format. This includes information from knowledge bases and customer interaction logs from platforms like Salesforce, Zendesk, Freshdesk, Slack, SMS, etc.
- Maven integrates into CRMs and enterprise APIs to understand the context of the user to personalize responses and take actions on behalf of the user. Combining content, context and APIs, Maven leverages GPT-4’s ability to adapt to each enterprise’s unique tone of voice and uses GPT-4’s reasoning capabilities to answer questions, take actions and suggest follow ups.
- Maven then self-evaluates, critically analyzing its answers to make sure it’s confident that it’s providing the right answer and action.
“One of the advantages of this generation of AI versus the last generation models is actually you don't really need that much data for any given customer,” CTO Sami Shalabi says. “Evaluation at scale is the magic sauce. The Maven approach has been validated with over 1M customer interactions. Our platform provides the tools that the head of support, CX, and product need to confidently answer any question their customers throw at it.”
Improving support at several touchpoints
MavenAGI offers a full range of channels for a better support experience, each highlighting a different benefit to using GPT-4 for custom agents:
- For customers looking for self-service assistance, Smart Search instantly provides the right answer in customer-facing knowledge bases or help centers.
- For customers who are looking for direct support, an AI chatbot uses GPT-4’s capacity for natural conversation to guide customers to quickly find the answers to many questions on their own. MavenAGI automatically discerns whether a question is outside of its capabilities and can route it to a representative.
- Once a customer’s question has been escalated, AI and humans work together. Maven leverages GPT-4’s fast processing to recommend resources and responses to representatives in real time. The customer doesn’t need to provide much context because Maven can reference past interactions that contain the answer or point to an obscure piece of a knowledge base.
Because Maven natively integrates with most CRMs and support tools, and can ingest structured or unstructured data, it can start answering tickets and assisting humans right away. It also continually learns after the initial training.
The results of integrating MavenAGI have been positive for companies like HubSpot and TripAdvisor. Across all organizations implementing MavenAGI, the average results are:
- Answering 93% of customer support questions autonomously
- Reducing the average time to resolve customer issues by 60%
- Improved customer service representatives’ productivity by 2X, providing more time for human interactions and spending less time finding the correct response for customer questions.
- Decreased the cost per ticket from $40 to $8, an 80% reduction.
Planning to build more on top of OpenAI’s models
Using AI to improve customer support is just the beginning for MavenAGI. They see great potential in using OpenAI foundational models to improve other business functions and processes.
MavenAGI aims to unlock the human potential trapped in input/output tasks. Customer interactions extend beyond support, and combining the technology of Maven and OpenAI will improve the coordination of customer-facing functions like support, sales, and marketing.
