Large Language Models (LLMs) have been the talk of the industry with promises of transforming organizations and the way we all work. Many of the most well-known models, such as ChatGPT, are cheap and easy to use. Yet they are limited to answering questions based upon the information contained within their initial training datasets. Fun to use, but not scalable or fine-tuned to work for your organization. Additionally, there are privacy concerns for businesses intending to share sensitive data with companies that have opaque terms and conditions.
So, how can you employ techniques to overcome these limitations and securely implement LLMs within your organization? That’s what I’d like to talk you through in this article. When implemented securely, LLMs can access an organization’s internal knowledge base – including documents, databases, or any relevant data source – to answer questions insightfully and in an effective tone of voice. This approach, known as “retrieval augmented generation” (RAG), unlocks the business potential of these models, enabling deeper interactions with customers or employees. This article will aim to give you an understanding of how to utilize LLMs for your business, how to enhance their performance to maximize potential benefits, and how data management experts like us at Amplifi can offer customized support and guidance, tailored to your specific needs.
I’ll guide you through several practical ideas that businesses can use with LLMs and provide detailed strategies on the best methods to initiate their implementation effectively. This will help ensure you’re well-equipped to start integrating these advanced technologies into your operations smoothly.
We’ve all watched e-commerce evolve at a breakneck pace. What once was a siloed channel is now an enterprise-wide challenge. In this new reality, PXM is as crucial to business success as CRM and ERP systems.
But PXM isn’t standing still either. It’s no longer just about presenting your products on the digital shelf; it’s about driving how companies scale and syndicate content across omnichannel experiences—globally and in an organized, automated way.
Unify the customer experience
More and more, businesses view product data through a PXM lens. It’s not just about data quality but about improving the lives of end customers. The question becomes, how can we leverage the foundations of good data to unify the customer experience while scaling across brands and channels?
This is a challenge, especially in industries like CPG, where businesses juggle multiple brands with unique properties like packaging dimensions and nutritional information. It’s normal to lack consistency from brand to brand. However, you don’t want customers to feel that pain, or drain your resources trying to overcome the issue.
During a recent webinar, we chatted with Salsify about the future of PXM and how businesses can leverage next-gen features to unify their data at scale. One example—part of Salsify Advance, their new PXM platform—is a capability called Universal Properties. It provides a flexible framework to establish common naming conventions and normalize data across the enterprise. This unification ensures that accurate, consistent data reaches the end customer without the need to create different properties for each brand.
Scale globally
Businesses are beginning to recognize that PXM requires bringing all regions and geographies under one roof. However, there are challenges to managing the nuances.
As new products are introduced, they require translation, enrichment, and syndication across channels. However, this process can vary significantly between regions like EMEA and North America due to differing approval pathways, digital asset requirements, and compliance standards.
Locale Awareness is another powerful PXM feature of Salsify Advance. It provides nuanced workflows and validation rules that allow you to tailor processes according to specific regional needs. With this functionality, you can create business logic that triggers and operates differently based on the region. This ensures that your product experience is both globally consistent and locally relevant—an essential aspect of PXM.
Leverage AI for automation
Imagine if you could treat every syndication endpoint with the same care and ensure your customer wins, no matter the channel. This is a hallmark of PXM, yet it often feels elusive. It’s simply too time-consuming to manually tackle enrichment for every product, on every endpoint. So, you settle for the top 10-20%.
This is where AI-driven automation makes a big impact. It’s not about reinventing the wheel, but about optimizing it. Salsify Advance, for example, allows you to integrate the AI services of your choice into your existing workflows.
This approach provides a significant advantage. We often hear concerns about how to leverage AI in a secure, safe, and governed way. By integrating AI into PXM workflows, you can test, learn, and scale improvements more efficiently and in a governed way.
Support new ideas and innovation
In the rapidly evolving world of PXM, it’s crucial to have a platform that not only grows with your business but also fosters new ideas and innovation. To stay ahead, companies need tools that accelerate progress and adapt to industry-specific needs.
One way to jumpstart PXM initiatives is through industry-specific accelerators. For instance, Salsify Advance offers accelerators tailored to sectors like Grocery, designed to streamline end-to-end processes with proven workflows, attribution rules, and mappings. These accelerators provide a valuable head start.
Another exciting development is the App Center within Salsify Advance—a growing marketplace where partners and customers can share and access transferable use cases. This ecosystem encourages collaboration, enabling users to tap into collective insights and knowledge. It’s an environment where you can implement solutions independently or with the support of partners like Amplifi, driving continuous growth and innovation.
Prepare your business for PXM
In the excitement around PXM, it’s important to pause and consider these key questions:
Is your data ready? Every initiative should start by prioritizing data quality, enrichment, and governance. Centralized, well-managed data makes syndication and PXM implementation much smoother.
Is your AI strategy clearly defined? AI won’t solve problems at the click of a button. Start by considering: Have we identified the right use cases for AI? Do we understand their practicality? Is my data accessible for AI? It’s not about having perfect data but setting clear parameters around how the data will be sourced and used.
Are you prepared to accelerate? Accelerators can provide a great jumpstart, but they also require a solid enablement plan and training. It’s crucial to understand what they do, how they can benefit your business, and what kind of change management might be needed for adoption.
Is your solution aligned with your business objectives? The most successful organizations can answer with a resounding “yes.” If technology drives your business decisions, you’re on the wrong path. Keep business needs and objectives in focus and ensure PXM upgrades support those goals.
Have you considered a Salsify Health Check?
If you’re unsure about the answers to these questions – whether you already have Salsify Advance or not – a Health Check can be incredibly valuable.
Amplifi’s Salsify Health Check is a collaborative, value-add assessment of your business and data objectives and deep dive into your Salsify solution to help you get the most out of the platform as it grows and evolves.
We help you answer critical questions like:
- Do you need to rethink your organizational structure around product data and Salsify, or address process bottlenecks?
- How can you build an incremental roadmap that leverages Salsify Advance and demonstrates value to your leadership?
- How can these insights translate into actionable projects with clear goals that align with your business objectives, using Salsify Advance as a key driver?
Through a short, targeted engagement, we’ll help you set a clear path forward, ensuring you’re ready to leverage Salsify Advance and evolve with it as your business needs change.
Setting up for success with LLMs
The application of AI in scenarios like developer tools and employee self-service scenarios vividly demonstrates how machine learning and natural language processing can transform workplace efficiency. By handling routine inquiries and providing rapid responses, AI allows for human talent to be allocated where it’s most needed—tackling creative challenges and strategic planning.
If you’d like to see a demo or have questions, reach out via our form below or download our guide.
Use Case: Enhancing employee self-service with AI-powered HR tools
AI has the potential to significantly transform the landscape of human resources by increasing the efficiency of recruitment processes, improving the onboarding experience, and effectively monitoring employee satisfaction. A typically laborious task recruiters must perform is to objectively assess, summarize and quantify the overall strengths and weaknesses of the applicant cohort for a job advert. In this use case, by providing the received CVs/resumes as context, an LLM would be able to determine what proportion of candidates meet certain criteria (ranging from soft skills to programming in a certain language).
Not only could this be used to power an insightful dashboard that visually demonstrates the status of a recruitment campaign, but also suggestions for altering a job description advert could be made dynamically, whenever it seems the applicants’ skills-mix is not as desired. Similarly, it could suggest interesting questions for individual candidates at interview if a particular skills gap is identified. This would empower the HR team to spend their time on higher-value tasks, such as relationship building. Furthermore, by optimizing prompts or fine-tuning the LLM, it could ensure there is consistency in assessing candidates across all members of the recruitment team.
Use Case: Streamlining developer queries with AI-enhanced documentation access
Developers frequently encounter the need to integrate various APIs into their projects, which requires precise knowledge of how these APIs function. A common question might be related to the type of HTTP method an API uses, such as, “What HTTP Method does the New Sale API use?”
Traditionally, this would involve a time-consuming search through extensive API documentation. However, the integration of LLMs could speed up this process. By providing the API documentation directly to an LLM, developers can receive instant, accurate answers. For example, when inquiring about the New Sale API, the LLM can quickly interpret the documentation and confirm that the API requires the PUT method for new sales as demonstrated by the use case graphic. This interaction not only saves valuable time but also allows developers to stay in the flow of their work, enhancing productivity.
Some top tips on how to get started on implementing LLMs
There are three main approaches in creating an AI for your business – Retrieval-Augmented Generation (RAG), fine-tuning existing models, and developing new models. RAG combines retrieval systems with generative models, offering quick and efficient solutions for many use cases. Fine-tuning enhances pre-trained models for specific tasks, while developing new models provides custom solutions but is resource-intensive. We will focus on RAG for the rest of this article, as it provides quick value across a wide range of use cases.
To give you a steer on how to approach implementing LLMs with your organization, a few of my initial suggestions would be:
- Understand embeddings: Learn how embeddings capture semantic meanings in text, facilitating tasks like semantic search and customer analysis. I provide a detailed explanation of embeddings below.
- Identify applications: Pinpoint areas for LLM use, such as AI-powered HR tools for quicker employee queries and AI-enhanced tools for developer efficiency.
- Prepare for integration: Ensure the right technical infrastructure and robust data management practices are in place, while adhering to ethical standards.
- Implement and monitor: Start with pilot programs, adjust based on feedback, and continuously update the models.
- Train your team: Educate employees on effectively using these new AI tools.
- Evaluate and iterate: Regularly assess the impact and refine solutions to improve outcomes
Mastering Embeddings and Prompt Engineering
A prompt is the question you ask the LLM (each model may have slight nuances in the optimal way to structure them). The current generation of models all have an upper limit to the length of prompt that can be supplied, and their performance may degrade the longer the prompt. Therefore, we must use an intelligent way to pre-filter our documents, to provide meaningful context to the LLM rather than blindly pasting all the text available from our document corpus. To perform this filtering, we utilize embeddings.
Embeddings are powerful tools for building AI systems with domain-specific knowledge. They are numerical ways of representing real-world text – similar to how geographical coordinates (latitude and longitude) map specific locations on Earth, embeddings provide a way to represent the meanings of words in a structured format. This allows us to measure and compare the meanings of different words within a high-dimensional space, making it easier to analyze and understand textual data.
By converting all our documents to embeddings in advance, when a user asks a question, we can rank the documents in terms of their similarity to the question. This allows us to filter out any documents that will not provide meaningful additional context for the prompt. The pipeline below demonstrates this principle.
Enhancing LLM Precision with Document Chunking
Our documents may be long and 99% of their content irrelevant to bring back errors, or vague information without answering the question at hand. For instance, a single clause within a long legal document may be all that is relevant. One effective technique to maximize the precision of our prompts is “document chunking”. As discussed, LLMs often struggle with long documents due to memory constraints and context dilution. Chunking—dividing a lengthy text into smaller parts—ensures more manageable processing and helps maintain contextual accuracy.
There are several approaches to chunking. The simplest is fixed-size chunking, where a document is uniformly divided into segments of a specific word or character count. However, this method can sometimes split important contextual information.
A more nuanced approach is semantic chunking, where texts are divided based on natural divisions like chapters or topics. This technique respects the document’s inherent structure, ensuring that each chunk retains a complete idea or concept. However, it requires more sophisticated processing to identify these natural divisions accurately.
In many cases, a hybrid approach proves most effective. It combines fixed-size and semantic chunking, balancing the ease of uniform segmentation with the need to preserve meaning.
Implementing chunking involves selecting the right tools. Many text processing libraries offer basic chunking functionalities, but for semantic chunking, more advanced natural language processing (NLP) tools may be necessary. Integrating chunking into your LLM workflow involves testing to find the optimal chunk size and approach for your specific needs.
While chunking greatly enhances the precision of LLM outputs, it’s not without challenges. One major issue is ensuring that the context is not lost across chunks. Overlapping text segments or incorporating summary sentences at the start or end of chunks can help maintain continuity but would need human editing and/or intervention to ensure the content flows as intended. In the example below, a prompt has been created using a chunking approach. The user’s question (in pink) is combined with specific and relevant quotations drawn from the company’s internal documents (in yellow), so the LLM can properly answer the question.
About the author
Vanessa Summitt is Consulting Director at Amplifi.
