Episode 20 - Build Your Own CRM with AI
So in today's episode, I want to explore the idea of creating your own CRM or customer relationship management system. In addition to AI tools such as ChatGPT and specifically a custom GPT. And there may be other tools out there that could do similar. I know Claude has projects available. So the main point here is that with any software design, whether it's a CRM or some other sort of management system and a lot of software, not all, but a lot has to do with the management of either customer relationships or enterprise resources, financial management, time management, whatever it may be. Oftentimes, if you have an application or use case that has the word management in it, it is a good candidate to be able to be built in a generative AI system or as a custom GPT. Specifically, you think about software, and I've got a lot of experience on the Salesforce platform. When you think about it, it can be boiled down into four main categories or functions. And so the first would be I like to call a rule library or rules libraries. Think of these as the standard operating procedures that drive any business. Now a lot of businesses don't have clearly defined processes, and their processes could be defined as chaotic and haphazard or ad hoc and everyone doing things differently. In the oncoming age of AI, in the enterprise, those organizations that have clearly defined processes that are documented will benefit with AI, because that can be fed into AI can find improvements, gaps, and then also reinforce that behavior inside of the system that is being built, whether that's on the Salesforce platform, which readily is able to translate those requirements and those processes into reality on the platform, often with clicks instead of code or some other system. But the first primary building block of a system that does management in general would be what I like to call a rules library. And those are the rules that you live by as a business. Now, as with any rule in business, there are always exceptions. And this is where you will see that we always do things this way, except for these exceptions. And anytime there's an exception. Think of those as an exceptions library. And where I'm heading here, as we've briefly touched on, the first two of these four building blocks, is that these are basically libraries of information. Or consider them knowledge articles or knowledge libraries Or different pieces of content. You have your rules and then you have your exceptions to those rules. And that is when things are out of the ordinary, you have your primary use case. And then the exceptions handle those things that don't follow the main path, that most things go down to the default path. And then in the third library you would need are actions that the software needs to take. And this is where you go from static information to updating that information. Back in the early days of the internet, in the land of intranets and CGI programming. This is where you would be making calls to a server and doing updates there, or even relational databases. Whatever it may be, you need some sort of actions library or to account for the actions that need to happen, so that when this rule is triggered and these exceptions are accounted for, what is the action or actions that need to be done? And also are these immediate or time based actions, much like how workflow rules used to work in Salesforce? And so then the fourth and final piece is that database or dare I say, spreadsheets or even Google Sheets. Some way of connecting your roles, your exceptions, and the actions that then go out and update your database or your records, And so if you've ever built a custom GPT, you have your instructions And that's where you would specify your rules and your exceptions. You have your knowledge base. And those are additional documents that you can share for to train upon and to know and understand further. And then also you can connect to an external database through actions via custom GPT. You could use this, use case then in this scenario to build for example, a customer relationship management system as a custom GPT. And so that fourth and final piece is that database or the records in general, as far as the different accounts or contacts or opportunities. And then based on its knowledge base of its rules and its exceptions, then it can infer what actions need to be taken as well. So I encourage you to think about building your own CRM as a custom GPT. That would be great use case of exemplifying your understanding of building out applications with generative AI, and that would be great things to speak to as well in an interview, or to put on a resume or LinkedIn profile. The beauty of generative AI is it can help you on the front end of the planning of the software that you're building by helping you to create business requirements, documents, and user stories as well. And then on the other end of the spectrum, for the QA and testing, the user acceptance testing and the test scripts that need to be performed, testing for positive and negative outcomes and being thorough. It can also figure out unlike us because we don't know. What we don't know is it can help infer and figure out the gaps in our thinking or the things we have not thought about. The different dependencies. These are the things to be taken into account and ask questions in this back and forth, conversational coder type of mindset to help identify where exceptions are needed, where further rules are needed, and then also the prioritization of those roles, what order they need to be evaluated in. The main point is you don't need to know how something is done. You don't need to know the nitty gritty of how the code works. You just need to know what the end results you're looking for, and then being able to test and verify that it's giving you the desired results. If you have a thorough test case or set of test cases, you can verify that is performing as expected under a host of scenarios. With the embracing of generative AI, you can build your own systems as a solopreneur as well, and try to leverage that in your own home based business or your lifestyle management or home management techniques. And these be practical, hands on examples of things you could build using either Salesforce or ChatGPT or cloud or whatever AI tool you choose. And regardless if you want to go down the path of building something like this, just having the understanding that all management related software, especially Salesforce, can be boiled down to four key components. And that would be the rules library, the exceptions library, the actions library. And then finally the database of the records are stored and updated and can be transformed. So now with the exciting times that we find ourselves in, the ability to become a creator in a consumption world has been democratized. It is available to anyone that can form sentences and can communicate. And so this is an advantage to all of us, and not just the few. So all that's left in remains is to ask yourself, what will I build today?