26 01732 759725 AI with a low-code data orchestration platform like Xefr, or opting for a fully customised private model. In our experience, to gain a true competitive advantage, businesses will need more than just standard models. However, this doesn’t have to be complex. Software engineers can build a wrapper that transforms an OpenAI model into something specific to their use case. For example, wrapping GPT-style models with prompts or guard rails can help configure them quickly and help overcome accuracy issues. OpenAI tools can also be made more traceable and formatted to show why an answer was given, with links to the source material so that humans can double check answers. Bias is another weakness in OpenAI systems that businesses will want to avoid, particularly if they are using the tool for something like screening a CV. Software consultants can build guard rails and prime an OpenAI system to minimise biases or train an AI tool on the business’ proprietary data, which is less likely to contain biases. Managing privacy concerns ChatGPT is fuelled by online data, and employees may inadvertently hand over sensitive data in their queries, with implications for privacy. It is possible to make small modifications that sit over the OpenAI API to prevent this, such as holding the data for a limited number of days and ensuring it is not used for training. Often, when engaging with a consultancy to develop bespoke solutions, businesses prefer to retain ownership of IP. In many cases, it’s not the tool (e.g. Xefr) or the AI model where IP resides, but the data + model + training process that gives rise to a trained system. This will be unique for each client and is something they can own. Where we do need to write custom software, we can do this in auxiliary projects that are separate to Xerini codebases and this, too, is something the customer (or partner) can retain IP ownership of. Finally, where there are privacy concerns, we can train and finetune open-source models that are bespoke to the client and can run on private hardware without leaking data to third-party services. Managing the process Any investment in technology is a risk. The largest barrier is ensuring that the benefits are tangible and properly understood. Taking an incremental approach and breaking things down into manageable phases, with each delivering identifiable value but carrying less risk can be a pragmatic solution. There is also the people element. With people-centric concerns, such as the fear of losing jobs or agency within current roles, it’s important that we convey a message of enhancement rather than replacement e.g. employees will be able to get more done in less time and this will make their lives easier rather than making their role redundant. Getting this message reduces the number of objectors and potentially turns them into champions. We believe all businesses, regardless of size or situation, are ready to start their AI journey whether that is through tools like ChatGPT, by integrating their systems and data via platforms such as Xefr or with fully bespoke model generation. Working with an experienced software consultancy can streamline the AI integration process greatly and help to avoid expensive platform migrations. https://xerini.co.uk Natural language processing: a practical guide While it’s exciting to type a quick query into ChatGPT the real value of AI will be realised when businesses can seamlessly integrate it with their internal systems to help solve business problems in a quick and costeffective way. One area in which AI can have most impact is data management and analysis. Both structured and unstructured data can be tagged and classified, making information more accessible and easier to find using natural language search. For example, a business may want to onboard thousands of legacy certificates to make that data available to staff or to enable them to ask the system a question raised by a client. Another example is automatically screening CVs to shortlist candidates for a job role. Many such tasks would previously have been too labour-intensive or too technically challenging to be worthwhile. Before AI, the cost vs. benefit didn’t stack up. Now it does. Choose wisely There are already hundreds of AI tools and models with varying use cases, which can make the market difficult to navigate, and no universal tool for every application, so choosing the right one is important. Before investing in a tool, a business needs clarity on its capabilities. This means achieving good visibility on the data it does – and doesn’t – collect, knowledge of where and how it is stored, a clear articulation of the problem that needs to be solved, and the expected benefits of solving it. After establishing this, businesses can explore various options, including using OpenAI in its current state, enhancing its functionality through integration Alex Luketa, CTO of artificial intelligence consultancy Xerini, explains how businesses can get the most out of generative AI Alex Luketa
RkJQdWJsaXNoZXIy NDUxNDM=