Ahmed Elyamany

Value Selling Advisor & Co-founder | Axcieve

July 2, 2024

Sales Enablement became an essential approach In our dynamic world of complex businesses, a primary objective for organizations is to enable sellers to drive revenue growth and deliver measurable results to top management. Many are wondering, How will Generative AI change the horizons for sales effectiveness and enablement? Tools like ChatGPT, DALL-E, and Azure OpenAI are revolutionising the way we envision customer interaction and sales processes. If you’ve ever questioned, “How can I make AI work for my specific organization’s and department’s needs?” Keep reading on, this post may be precisely where you need to be.

Harnessing Generative AI for Advanced Sales Enablement

Think of a Large Language Model (LLM) as a knowledgeable wise guru, they are great at advising on generic high-level human inquiries. Yet, even the most adept guru needs an assistant for detailed and, source-cited responses. This is where the true challenge and opportunity if we try to apply LLM to specific business domain such as enterprise sales enablement.

In the sales world, generic responses are not sufficient. Sales team needs nuanced, data-driven insights in each step of sales’ cycles. This requires tailoring LLM models to understand and align with unique business context. Imagine a scenario where Generative AI is not just a tool but a part of your team, trained on your data, ready to provide instant, accurate recommendations to customer and sellers’ queries, closing technical knowledge gaps of your sales reps, and transforming conversations with prospects into productive valuable relationships.

In this post, I am discussing two techniques that we are using in Axcieve, to enable this tailoring process: fine-tuning and Retrieval Augmented Generation (RAG). Both can be leveraged to optimize LLMs for specific sales needs, transforming them from generic answer machines into specialized assets that align with and advance your sales strategy. Customizable LLM have the potential to empowers your team to understand and effectively respond to each customer pain point more deeply, timely and build trust more rapidly.

Section 1: Navigating LLM Limitations in the Sales Arena

Before talking about the two techniques, let’s just have a quick recap on the capabilities and limitations of Large Language Models (LLMs). How they can transform customer interactions, and where standard LLM will fall short in the highly specialized and ever-changing domain of sales. (FF to Section 2 if you are already familiar with this!)

Identifying the Shortcomings

Generic Training Pitfalls: Commonly, LLMs are trained on vast, static datasets that don’t account for the latest market trends or sector-specific nuances. This limitation leads to responses that lack relevance to current industry-specific scenarios, your organization’s specific data sources and knowledge, or fail to incorporate the most recent data.

Lack of verified data source, expert contact points: Responses retrieved from standard LLMs lack explanation of verified data sources to double check the accuracy of information retrieved. This is important for authenticity reasons and for knowing where to request further information if needed. Or whom your team might reach out to if the customer comes back with additional information.

Customization: Reimagining LLM Utility in Sales

Industry-Specific Tailoring: Greg from AI Makerspace space highlights a paradigm shift from the one-size-fits-all:

ambition of general-purpose LLMs towards more industry, domain, and task-specific models. This shift emphasizes the need for a data-centric approach, where the focus is on leveraging our unique datasets to tailor AI responses to specific industry needs.

Our objective is to harness the potential of refined LLMs and transition from a broad-stroke to a focused, efficient, sales-specific assistant in the ever-competitive sales arena. We do this through major 3-axises:

Direct and Credible Responses: In sales, the need for quick, direct answers supported by credible sources is paramount. Sales professionals often don’t have the luxury of sifting through voluminous knowledge bases. They require efficient ways to access information that directly supports their immediate sales objectives.
Integrating with Sales Force Automation (CRM/SFA) and Account Planning: Sales people heavily rely on CRM/SFA tools and account planning documents. The integration of LLMs with these sources can make information retrieved, intuitive and relevant to realtime workflows.
Including multi-faceted assets of marketing: Including brand marketing, loyalty, public relations, and analyst relations information. These elements present unique opportunities if aligned to the overall sales conversations and strategy.

Section 2: Tailoring LLMS through Fine-Tuning

The first approach we are exploring in this post is Fine-tuning. Fine-tuning is the process of refining pre-trained models, like GPT-3.5 or GPT-4, to serve precise applications. It involves retraining these models on a targeted dataset that resonates with the particular task at hand, such as providing legal opinions based on an existing knowledge base. This process includes feeding the model with labeled examples relevant to the task, requiring meticulous data selection and data engineering techniques to steer the AI accurately.

Fine-tuning incurs additional overhead costs as explained below. However, it proves to be more cost-effective in the long run considering RAG inefficiencies and compared to training a model from scratch. It is particularly efficient for complex tasks, like building a domain-specific chatbot, by making the model more attuned to industry-specific jargon and scenarios.

The Fine-Tuning Process

Start with a Pre-Trained Model: Choose a robust model like GPT-3 as your foundation.
Curate Your Dataset: Collect a set of examples specific to your sales task. This dataset forms the backbone of your fine-tuning process.
Training and Feedback Loop: Introduce these examples to the model, assess its outputs, and iteratively adjust the model through what are called gradient descent and backpropagation techniques.
Deployment: Once the model converges, it’s ready for deployment in real-world sales scenarios.
Iterate with each data update

Advantages of Fine-Tuning

Precision and Relevance: By adjusting a model’s internal parameters, fine-tuning biases it towards new data while retaining its general capabilities. This makes the model adept at handling specialized skills required in sales contexts.
Adaptability: Fine-tuning allows for adaptation to new domains, improving performance on specific tasks, and customizing output characteristics, such as tone and level of detail. It’s especially useful when data distributions change over time, keeping the model relevant and updated.

Challenges in Fine-Tuning

Data Quality and Availability: The need for high-quality, relevant training data is paramount. Gathering and curating such data, especially for niche sales domains, can be daunting.
Risk of Overfitting: Over-specialization is a real threat, as it might limit the model’s effectiveness in slightly varied contexts or more general queries. Thus the need for data engineers to overview and review the retraining and feedback loop processes
Resource Constraints: The computational and time resources required for fine-tuning can be substantial, posing challenges for smaller teams or businesses.
Integration and Maintenance: Keeping the model aligned with evolving sales strategies and integrating it smoothly with existing sales tools and processes adds layers of complexity to its application.

Section 3: Retrieval Augmented Generation (RAG)

Second approach to customize LLMs to follow certain domain model is Retrieval Augmented Generation (RAG). In the quest for more efficient and accurate responses from Generative AI in sales, RAG not only addresses the limitations of traditional Large Language Models (LLMs) but also introduces a new dimension of flexibility and real-time adaptability.

Retrieval-augmented generation combines LLMs with embedding models and vector databases (nvidia.com)

The RAG Mechanism Explained

RAG combines the prowess of generative models and enriches LLMs with the latest, verifiable data without the constant need for model retraining. By integrating prompts with relevant information extracted from Vector databases – mathematical representations of data – RAG significantly enhances response accuracy.

RAG works by converting queries into numeric formats (embeddings or vectors), which are then matched with similar information in a vector database. This process augments the context of prompts before they are processed by the LLM, leading to more accurate and relevant responses.

Key Benefits of RAG in Sales

In sales, RAG can pull real-time market insights and data-driven responses, vital for crafting effective sales conversations. RAG can accelerates the sales process by providing immediate, data-driven responses. This rapid engagement tool helps reduce the time spent on information retrieval, allowing sales teams to focus more on customer interaction and less on searching for data. By providing sales teams with instant access to a wealth of data, sellers are empowered to address customer queries more effectively and confidently, translating into higher conversion rates, enhanced customer experience and potentially boosting return on investment (ROI).

RAG can enrich sales conversations with comprehensive, up-to-date, and competitive information, making each customer interaction more impactful and informative. RAG serves as a powerful AI sidekick for sales teams, offering access to technical knowledge and market insights. This support helps sales representatives better understand and address customer pain points, building trust more rapidly.

Retrieval-augmented generation combines LLMs with embedding models and vector databases (nividia.com)

RAG’s true power in sales lies in its ability to adapt and simply customized to different flows. RAG enables businesses to tailor AI responses to reflect their unique brand voice, tone, and align with the company’s identity and values.

Rapid Implementation: RAG systems can be set up quickly, allowing sales teams to get up and running in a short time, thereby streamlining the sales cycle and boosting engagement.
Current Information: RAG pulls from relevant, up-to-date sources, ensuring that the information provided is current and reliable.
Transparency and Trust: Users can access and verify the sources used by RAG, enhancing transparency and trust.
Reduced AI Hallucinations: Grounding LLMs to external data minimizes the chances of incorrect information.
Computational Efficiency: Organizations save on continuous model training, making RAG a cost-effective solution.

Mixed mode – Hybrid RAG / Fine-Tuning

While fine-tuning offers model specialization, RAG provides real-time adaptability and flexibility. RAG’s ability to pull from current, external sources reduces the computational and financial burdens associated with constant model retraining. RAG stands as a robust solution in the sales domain, offering a blend of accuracy, speed, and adaptability that is crucial for modern sales strategies. By leveraging RAG, sales teams can access a wealth of information, synthesize it effectively, and apply it in real-time interactions, greatly enhancing their effectiveness and efficiency.

Experts say that if you take RAG far enough, you are actually doing a sort of fine tuning, it is not either or, it is a state of the art of best of both. In Axcieve, we are building our own hybrid models. We found that for each type of client’s situation, there are specific needs, document formats, privacy, regulations, performance constraints, that all combined require configurable approach. Our strength lies in providing a flexible way to adapt to our clients needs, providing fast deployment and quick time to value, transforming our clients’ sales teams with fully equipped knowledge bots, elevating prospects experience and achieving organizations goals.

Sales Enablement with LLMs: Fine-Tuning and RAG