Episode Categories:
Resources:
Join the discussion on LinkedIn: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Start Here Series in our Inner Circle Community: Join for free access
10 Essential Steps to Unlocking Business Value from Any AI Chatbot in 2026
The rapidly evolving field of AI chatbots has shifted the landscape for business productivity and decision-making. As of 2026, most major AI platforms—ChatGPT, Claude, Gemini, Copilot, and others—have converged in user experience and functionality, enabling the use of unified best practices to produce reliable, actionable outputs. Below, the key operational and strategic details are laid out, optimized for executives, decision-makers, and business owners aiming to extract measurable value from large language models (LLMs).
Understanding Large Language Model Capabilities for Business
Modern LLMs are no longer simple chatbots or advanced search engines. These models, trained on immense datasets, are generative systems that produce unique outputs based on the user’s context inputs. Businesses need to note: outputs from LLMs are non-deterministic—submitting the same prompt to different instances, even within the same model, will yield a range of responses. This means robust prompting and context management is essential to achieve reliable, economically viable business outputs, such as drafting contracts, generating market reports, or automating client communications.
Selecting the Right AI Operating System for Enterprise Scale
2026 has introduced the concept of AI “operating systems”: comprehensive platforms (like ChatGPT, Claude, Gemini, or Copilot) designed to integrate deeply with business data and workflows. For operational consistency and security, it is now practical and recommended to concentrate most business knowledge work within a single AI operating system, matched to existing IT ecosystems (for example, Gemini with Google Workspace, Copilot with Microsoft environments). This focus simplifies onboarding, context sharing, and compliance adherence.
Surface Selection: Deploying AI on Web vs. Desktop for Improved Workflow
The transition from web-based AI interactions to desktop applications is a significant evolution. Desktop surfaces now harness local computing resources, enabling faster processing, deeper integration with business data, and real-time actions (such as editing files, automating software tasks, or orchestrating local databases). For businesses that are privacy-sensitive, desktop applications offer more direct management over data access and retention while supporting advanced local automations that traditional web interfaces cannot match.
AI Chatbot Subscription: Why Paid Plans Are Mandatory for Business Reliability
Using free-tier AI models introduces substantial risks. Free versions often provide outdated AI models, limited outputs, and lack critical reasoning capabilities. This leads directly to substandard outputs unsuitable for any business-critical process. Enterprises leveraging LLMs must opt for paid, current-generation models—those which explicitly offer advanced “thinking” or “reasoning” modes—to ensure outputs meet enterprise-grade accuracy and compliance expectations.
Business Context Layer: Managing Inputs for Accurate AI Output
Today's LLMs accept layered context that profoundly affects output quality. The business context layer includes training data, up-to-date web content, and proprietary company data. Mismanagement or over-extension of the context window—akin to overflowing a hard drive—degrades outputs, producing irrelevant or outdated results. Effective AI use requires setting clear direction at the start of each interaction, prioritizing relevant context, and understanding that initial prompts are typically the most critical.
Context Engineering Techniques: Prime, Prompt, Polish for Actionable Results
Effective context engineering can be broken down into three foundational techniques:
Prime: Work with the model to establish roles, goals, and constraints before asking for deliverables.
Prompt: Feed precise instructions and business datasets to steer the model.
Polish: Iteratively refine AI-generated drafts, using feedback loops until the output aligns with company standards and specifics.
Modern AI platforms have integrated support for creating reusable “skills” or workflows that encapsulate these engineered prompts, making future iterations easier and more consistent.
Integrating Company Data: Secure File, App, and Data Handling with AI
Direct integration of CRMs, project management tools, and document systems into AI chatbots is now standard. These integrations support bidirectional workflows—AI can read, update, and create records across systems automatically. Businesses should design connector-based workflows that explicitly instruct when and how to utilize specific files or data sources, ensuring human knowledge work is focused on high-value decisions instead of routine data transfer or synthesis.
Privacy, Permissions, and Governance in Enterprise AI Deployment
Robust governance underpins all responsible AI adoption. Today’s enterprise-level AI platforms match or exceed cloud provider data security standards and allow configuration of permissions, model training toggles, and access control—all necessary to avoid shadow IT and unauthorized sharing of sensitive data. Enterprises must implement continuous, not one-off, compliance training and permission review as features and regulations evolve.
Transparency, Observability, and Reasoning Artifacts in AI Workflows
Business leaders now have access to detailed observability tools across AI platforms. These tools enable full tracking of every action, decision, and data access taken by an AI agent—including, for example, which external sources were consulted or how the context was managed. This ensures that if a deliverable or business process needs to be audited, every step is visible, supporting both regulatory needs and internal process improvement.
Verification, Iteration, and Workflow Automation: From Output to Scalable Business Value
Initial outputs from even the best LLMs generally require iterative refinement. Incorporating expert-driven feedback loops—rather than passive, unchecked automation—is the key to transforming generic AI drafts into customized, high-value deliverables. After verification, the refined process should be encapsulated as a reusable workflow or automated skill, allowing the business to scale up AI involvement with reliability and repeatability.
In 2026, extracting value from AI chatbots means embracing these pinpoint operational strategies. By mastering model selection, prompt engineering, context management, and integration with core business systems—while maintaining rigorous governance and observability—enterprises move beyond experimental automation toward consistently measurable business productivity gains.
Topics Covered in This Episode:
- LLM Landscape: Cookie Cutter Model Trends
- 10 Essential Steps for AI Chatbots
- Choosing the Right AI Operating System
- Selecting Optimal AI Chatbot Surfaces
- Importance of Paid AI Chatbot Plans
- Understanding LLM Context Window Layers
- Context Engineering and Prompt Best Practices
- Integrating Files, Apps, and Company Data
- AI Chatbot Privacy, Permissions, Governance
- Transparency, Observability, and Reasoning Artifacts
- Verification, Iteration, and Workflow Automation
Episode Transcript
Jordan Wilson [00:00:16]:
The saying of keeping up with AI is like trying to drink water from a fire hose, though it's tired and cliche is obviously a 100% true. I mean, with all the nonstop updates, your head is probably spinning trying to keep up. So you're thinking with all these new releases, how do I use ChatTBT, or is using Claude kind of the same as using Gemini on the desktop, or can I prompt Copilot kind of like I'd prompt codex? Or maybe you've had to start the race sprinting, and you've never really got the proper one zero one on how all of these AI chatbots work. Regardless, you definitely aren't alone in the fire hose updates drowning you out. That's the new struggle for every enterprise because it's not like there's a cheat code. Right? Because as the AI models are changing almost daily, so too does the input required to get the best output, and I get it. As someone that covers AI daily, I understand the struggle of trying to play a game, yet the field dimensions change without notice. And you were using a softball yesterday, but cricket gear today and tomorrow, you might kind of play it out like rugby.
Jordan Wilson [00:01:31]:
The input rules and the output capabilities are moving targets. But there's one thing I found out over the last three or four months. The big players have all just kind of started to copy each other, which is actually a good thing for you. So I think it's actually been over the last two months that we've finally stumbled on a set of best practices for getting the best outputs out of any large language model. So that means, well, there is a cheat code or at least a set of somewhat concrete rules that when followed will give you stellar outputs really no matter what model you're using. And that's exactly what we're gonna be giving you today on everyday AI. Welcome to the start here series. If you're new here, the start here series is your essential guide to getting caught up in getting ahead with AI.
Jordan Wilson [00:02:25]:
But first, let's talk about the big picture. So the capabilities of these models are very, very real, and it is hard to keep up. Right? So right now, you probably see examples all over the place. You see people sharing examples, whether it's online, whether it's media articles that are so poorly written, and you're like, well, these AI models are really bad. Look at all these mistakes. But then you also see these benchmarks and these tests and, you know, these big companies laying people off in lieu of spending billions of dollars on AI, and you're confused because you can't even know or don't even really understand what button to click or which model should I use. And up until recently, it's been too hard to follow because there's been too many different paths. And now I think, essentially, we have cookie cutters.
Jordan Wilson [00:03:17]:
Right? We have the McMansions of models because they're all kind of the same. Obviously, the capabilities and the harnessing of the tool is all completely different and unique. But I think for the first time, maybe ever, at least when it comes to, you know, the three to five handful of big AI players, we have a set of rules that can apply unilaterally to really any of them. So that's what we're gonna be going over on today's show. Stick with me. This one, trust me, is gonna be thirty minutes. Alright. I know sometimes I say twenty five to thirty, and then you're, like, forty five minutes in.
Jordan Wilson [00:03:55]:
But stick with me on today's show. Here's what you're gonna learn. You're gonna know why the cookie cutter nature of today's large language models is actually both a good and a bad thing. You're gonna know the up to date capabilities, features, pros, and cons of the big players, specifically focusing on ChatGPT, Claude, Gemini, technically applicable to Copilot, but we're not gonna go into that one as deep as well as, I mean, you can apply it to perplexity, GROC, open models, etcetera, because they are kind of all getting the same. And you're gonna leave today's show with the 10 essential steps to get the most out of any AI chatbot. Alright. This is the start here series. This is the essential podcast series to both learn the AI basics and to double down on your AI knowledge.
Jordan Wilson [00:04:38]:
Because after doing this for three and a half years, nearly almost 800 episodes now, I never had a good answer when people ask, Jordan, I'm new to the podcast. Where do I start? Well, you start here with the start here series, and you go to starthereseries.com. That is gonna give you free access to our inner circle community. It's exclusive. This is the only way you can actually get access in the start here series, space inside of our free community. You can go find every single start here series episode all in one easy to find place. A Spotify playlist that's updated, all the newsletters, go read it. It's awesome.
Jordan Wilson [00:05:14]:
Alright. So, if you missed our last start here series episode, we covered bill by partner or wait, the four layered AI stack decision framework for 2026. And today, we are giving you the LLM cheat code, 10 essential steps to get the most out of any AI chatbot. Alright. And I'm just gonna give you those steps now, and we're obviously going to break them down as we go along. But here they are, Kind of steps, best practices, rules to live by, whatever. But number one, you have to understand what a large language model is and what it is not. Number two, you have to choose your AI operating system like Chad GVT, Cloud Gemini, or Copilot, and really stick to those as much as you can for the majority of your day to day knowledge work.
Jordan Wilson [00:06:04]:
Number three, you have to choose the right surface. And the surfaces are unfortunately changing, but I think it's actually for the good. Number four, you have to choose the right account plan and model. I'm gonna break down those best practices as well. Number five, you have to understand the context layer. First, you have to understand it before you get to number six, context engineering basics. I'm gonna tell you prime, prop, polish, refine q, five five five, a lot of the secrets that I've kind of held close to the best throughout the years. Number seven, I'm gonna tell you how and why in risks on working with files, apps, and company data and why that matters.
Jordan Wilson [00:06:45]:
Number eight, we're gonna talk about privacy permissions and governance and how that actually plays out in these AI operating systems. Yeah. I call AI chatbots now AI operating system because that's what they are. Number nine, transparency, observability, and reasoning artifacts. I'm gonna show you how to use those things to your advantage to get better outputs. And last but not least, verification, iteration, and workflow design. There you go. You can stop here if you want.
Jordan Wilson [00:07:13]:
But trust me, this is like thousands of hours of conversations over the past three years, and I'm gonna do my dangest, to get them to you in thirty minutes or less. So, here's what I wanna talk about, why this is both a good and a bad thing. And I think this really became evident when Google at their IO conference, like last week. And I know. Right? So right now, it's the May 2026. I should put this out there because I know, you know, a lot of you might be listening to this in, you know, July or December. So, obviously, some of the things are gonna change here when I'm talking about certain surfaces, models, modes, etcetera. But, hopefully, these concrete ish, 10 steps will still hold.
Jordan Wilson [00:07:59]:
But I noticed at Google's IO conference when they announced their new anti gravity two point o desktop app. Right? And not gonna get into it, but I'm like, wait. This just looks like codex. It functions like codex. And then I'm like, wait. Cursor kind of does too. And that's when I started to notice that for the most part, especially compared to eighteen months ago, when all of the different whether we're talking about the web interfaces. Right? Gemini.google.com, claw.ai, chatgvt.com, grok.com, whatever you're using.
Jordan Wilson [00:08:32]:
Eighteen months ago, they all looked really different. It was almost like speaking different languages. Now it's all speaking the same language with slightly different dialects. Right? Like, anti gravity literally looks like it is codex light. Right? Color schemes, fonts, all of the same layouts. So it's good and bad. From a bad perspective, it might seem to you, the nontechnical user, that the front facing innovation is kind of slow. Right? As an example, go back to, you know, 2024.
Jordan Wilson [00:09:05]:
Front end innovation for, users and maybe early in 2025 was everywhere. Right? All of a sudden, we had artifacts from Claude, and then we had, you know, canvas mode. And, you know, we had these agents that worked inside, and all of a sudden, you know, large language models went from simple, you know, next token prediction transformers to models that could think and reason and call tools. Right? So I think there is this period of fast innovation in terms of what buttons you would click, all of these modes, deep research, etcetera. But if I'm being honest, in 2026, we haven't seen that same thing, and I think that's actually good. Because what happened is it I think it gave us, number one, now we can kind of apply these best practice rules. But more than, anything else, I think it allows enterprises to be able to modularly modularly, pivot as needed. Right? Because eighteen months ago, if you were a heavy ChatGPT Teams user, back what it was called before it turned into ChatGPT business, and then you try to go to, you know, Gemini.
Jordan Wilson [00:10:08]:
Right? There was no Gemini business at the time. It was just Gemini. You'd be confused. But now they've kind of all copied each other with certain features, projects, GPTs, gems. Right? They're all kind of just the same thing now. But the actual race is smarter, faster models with autonomous desktop harnesses. So the surface is changing a little bit. But ultimately, the thing that you have to keep in mind if you don't get anything else from today's show, AI models are smarter than that, all of us.
Jordan Wilson [00:10:36]:
If you're using them the right way, and that's a big if. And when I talk about jagged jagged capabilities, right, people will share something where it's like, oh, AI models are dumb. And then you have this false sense of security, like, oh, I don't have to worry about keeping up with these day to day. Yes. You do. Anyone that shares those things, that's a skill issue. You know? Send them this video, and then they'll be like, oh, I've been using everything wrong. But AI models by default, studies show this even judged blindly by experts.
Jordan Wilson [00:11:07]:
Today's AI models with all of this harnessing built around them, they can produce artifacts one shot. Right? You know, complete websites, complete apps, spreadsheets, PowerPoints, Word docs, PDFs, etcetera. Right. So they're no longer just a little chatbot to talk to, and we've covered that, in-depth in the start here series, so far. So let's dive in. We have some upgraded visuals, today, but let's get into our, kind of the 10 new rules of work, I'll say. So number one, what is a large language model, and what is it not? Well, if you're only using CHAD, GPT, or CLOD, or whatever as a version of Google, as a smarter, faster, better source version of Google, you're missing out. Right? If you're just treating it back and forth like talking to a smart friend, you're also missing out.
Jordan Wilson [00:12:06]:
So by default, large language models are generative. So that means they are nondeterministic, where a search engine like Google, aside from localization and personalization, is deterministic. Right? If we put in the exact same query, chances are aside from that personalization and localization but if we all did a an incognito Google search, right, five years ago before AI overviews in AI mode, we've, for the most part, all would have gotten the exact same outputs. Right? Even if there's, you know, 20,000 people listening to this episode and we all did it, we would, for the most part, get the exact same results. It's not the same with generative AI. It is generative. There is a an an element of, next token prediction, and, essentially, large language models have been trained on the entirety of the Internet. Copyrighted works, you you know, open source coding projects, videos, photos, everything, just terabytes of data.
Jordan Wilson [00:13:01]:
So the old quote unquote, I always say that there is a line in the sand that came with OpenAI with the first, widely available reasoning model. So previously, when you first started using chat g b t or maybe you're listening to this and it's been a while. Right? The older models were transformers, and that's really all they were is next token predictors. And but still, they're generative. So the whole point is if the 20,000 people listening to this show all put the same prompt in chat gbt or Claude or Copilot or whatever, you're probably gonna get very different results. Right? There might be 2,000 very different results. There might be 20,000 very different results. Right? It's it kind of goes through this next token prediction process, but, that is why you have to really understand how these work and build up a context and good practices to get the best output.
Jordan Wilson [00:13:54]:
So, there's also in this without going too deep, there's a lot of nuance to this. Right? Because now these models can think, very much like a human would, and we're gonna get to that a little bit later. But for the most part, a large language model is not a search engine. It is not a chatbot. It is a reasoning engine that combined with your data and your human knowledge can output economically viable work at a rate better and faster than humans. Alright. So that is number one, what a large language model is and what it isn't. So now that we know what it is, where do we use it? Alright.
Jordan Wilson [00:14:37]:
So, also in the start of here series, I had an entire, episode on this concept of an AI operating system, but I think that's important to talk about, because now they can all connect with your data. Alright? And depending on what you go and, you know, what route you go down, I do think it's best to to move most of your organization, most of your enterprise into one AI operating system. Right? So, personally, I'm using chat g b t via codecs more than anything. A lot of people are using Claude whether that's on the web or the desktop. We're gonna get to that in a minute. There's also Gemini for those, people who are, really ingrained, in the, kind of Google workspace, ecosphere. And then, obviously, with Copilot, it's a little more difficult to explain because there's so many hoops to jump through in terms of permissions, role based, access control, all these things. It's a little convoluted.
Jordan Wilson [00:15:36]:
But, I always tell you I I I tell companies, try to move the majority of your day to day operations inside one of these AI operating systems. Obviously, you should be building modularly. So when there are, you you know, new kind of frontier breakthroughs, or huge advantages, maybe a section of your team can take that context over to another one. Also, now every single big player makes it fairly easy to bring context over. So whether that's things like skills and plug ins, your context, memory, chat history, etcetera, There's easy ways to port this over. It is more or less just a very, in-depth and detailed prompt, FYI. Alright. So number two is you have to choose the operating system.
Jordan Wilson [00:16:21]:
Number three, you have to choose the right surface. And this, at least in 2026, is where we've seen the most movement on, not necessarily what we saw in, you know, mid twenty twenty four to mid twenty twenty five, which is the features and the modes, the deep researches. Right? The, you know, agentic capabilities with these reasoning models by default, the connectors, the apps. The surface is what's changing. So what do I mean by that? In 2022, with the advent of ChatGPT, it was the web. We went and chatted. Right? Then we started to bring our teams on board, and you could collaborate with others in kind of a shared workspace. You know, and now in, you know, late twenty twenty five with Claude Code, then Claude Cowork in early twenty twenty six, and now Codex and everyone else.
Jordan Wilson [00:17:08]:
Right? Google got on board with their Gemini desktop app with their anti gravity, which I don't think is that great, but hopefully, it'll get better. Right? Now everything is moving to the desktop. And one of the reasons is is, well, it can use, kind of your local machine to do a lot more, faster and access your data. It can read and write on the desktop surface, which is huge. And then, obviously, everything is agentic by default. So there's no easy answer to say, okay. Well, should I still use the web version? Should I use the desktop version? You you know, to get to that answer, you have to sit down and talk about what's important, in terms of access, in terms of automations, in terms of, you know, what you want in the cloud versus running locally. Actually, you know, although the the there's a lot of risk, reward trade off with a desktop version, in some instances, it might be better for some companies that are, you know, privacy first.
Jordan Wilson [00:18:04]:
So number three, you know, is understanding that that surface dictates access. Right? So, because it's important to know that the agent tools I mean, they can use your actual browsers. Right? And that's one of the biggest advantages, I think, to the desktop surface aside from being able to read and write to your local folders. Right? But to be able to use your actual browsers, I think codex's built in browser is so far ahead. Computer use technology where I can literally, you know, use your computer, launch different programs. I have mine, you know, can go through and read my iMessage on my computer and, you know, open up all these different desktop programs if there isn't a built in app or connector. Alright. Number four, choose the right model, people.
Jordan Wilson [00:18:51]:
Stop using a free plan, period. If your company is like, yeah. Use the free plan until we get this approved. Don't do that. The risks are too high. Alright. I don't care if you're using chat GPT, quad, Gemini. It it doesn't matter.
Jordan Wilson [00:19:06]:
For the most part, you might get, like, one or two quote, unquote prompts or outputs, you you know, with a decent enough, plan if you're on a a decent enough model. If you're on a free plan, don't do it. It's not worth it. If you want real outputs, you have to use a paid model. Right? All these people that are sharing things online, and you're like, oh, yeah. I'm so dumb. Right? They're usually using an old model, a free model, and they really just don't understand, kind of the underlying harness. So this is like, you know, you could have a convertible body, but, oh, the engine is actually, you know, a dude on a bike.
Jordan Wilson [00:19:46]:
Right? That's the equivalent of using a free model. You can't hide it in the fact that, like, oh, I'm using claw. No. If you're using the free model, right, for the most part, you probably don't even know because companies don't always tell you what version it is. Right? Like, did you know that there's a GPD 5.4 latest? I'm like, no. You don't. Because unless you're like me, you're not out there testing these things. Right? You just think, oh, I'm using the best in the world, and you probably aren't if you're on a free plan.
Jordan Wilson [00:20:14]:
And you also need to be using thinking models. Do not use these models that don't think, don't reason. Alright? You need to be using those always even if that means waiting an extra ten, twenty, thirty seconds. Alright. I'm gonna get to this later, but read the chain of thought. Do some exercise. Have multiple, you you know, prompts running at the same time and, you know, dictate, you you know, move between. I do think the the job of the future is agentic orchestration.
Jordan Wilson [00:20:40]:
Alright? So don't just, you know, go and chat with one, you know, free chatbot thread. At that point, you're wasting your time. And if you're making any business decisions based on using a free or a non thinking model, I'm sorry. As the kids say, n g m I not gonna make it. You, your department, your company, if you're doing that, if that's part of your actual strategy, don't. Right? Just just please don't. Unless you're just trying to learn, like, where all the buttons are, like, how do I work this thing? That's the only time you should be doing that. Alright.
Jordan Wilson [00:21:14]:
So number five, understanding the context layer. And this part is important before we even dive into the, you know, best practices of context engineering. But context is essentially everything that an AI model can see or not see. Right? The the way that I've, you know, we've taught, you you used to do, like, two live, you know, kind of prompt engineering courses a week for, like, two and a half years. And kind of the analogy I've always used if if if you think back to the Star Wars credits from the original Star Wars. Right? And it it comes in and the words come in slightly slanted, and it says in a galaxy far, far away. Right? And eventually, the words, they get smaller, smaller, smaller, and then they're off the screen. Think of that as a context window.
Jordan Wilson [00:22:02]:
Different models have different context windows. So, essentially, you might be using a large language model, or you might have a skill saved or a plug in or a workflow saved, and you're using it repeatedly. And all of a sudden, you know, started out great and all of a sudden it's like, wait. This stinks now. You know? Oh, you know, this company must have nerfed the model. Maybe, but probably not. Probably, you just ran over your context window. So that's essentially the amount of information like a computer's hard drive, that a large language model can retain.
Jordan Wilson [00:22:31]:
Alright? And a lot of times, the first prompts, the first pieces of information you give a model are oftentimes the most important. It's where you give it direction. So the difference between a context window or understanding how context works in a hard drive is if you try to save a, two gigabyte file on a full hard drive, it's just gonna say, nope. Can't do it. No room. Alright? A large language model is gonna do it, and this is gonna kick off something, and you have no clue. So working with relevant, accurate business context is one of the most important things to do when working with a large language model, because, essentially, large language models get data from one of three places. Number one, their internal training data, which for the most part is very, very old.
Jordan Wilson [00:23:14]:
Number two, any of your company data that you share that can be, you know, apps, connectors, your file memory, chat history. You know, there's essentially a layer of your, you know, personal context, company context, you know, your all your SaaS apps that you use. Right? And then there's the web. Alright. So you have to understand that there's now this context layer that didn't really exist before. Right? It used to just be the training data. And keep in mind, training data is usually really old. There's a knowledge cutoff date, but I would venture to guess the overwhelming majority, like, 99%, of the data that actually ends up in today's large language models is nowhere close to that date.
Jordan Wilson [00:23:55]:
So, you know, let's just say if there was a way to turn off web search and to turn off your company's context, and if you were to only rely, on a model's training data, it would be very bad. Right? It's actually crazy to think it took Infropix so long to add web search and which is why I was like, companies should never use it. Right? Because without web search, you know, you're probably playing with data at minimum that's probably on average fifteen to eighteen months old on the good side. And think of how quickly your company, your competitive landscape, your sector moves. And imagine if you only had access to data that was 15 to 18 months old. Yeah. Recipe for disaster. And that's why also you get these, you know, out outputs sometimes, especially, you know, pre, you know, twenty twenty four reasoning models that could agentically call the web and pull your data.
Jordan Wilson [00:24:45]:
Why you'd get these outputs that looks like they were absolutely terrible? Well, because they were. It was relying on old data, and large language models are trained to be helpful assistance. Alright. So make sure you go back and listen to the start here series going over the I think we called it the seven deadly sins of AI, where we kind of talked about some of these things. But that's why sometimes outputs from large language models seem generic. And you're like, is this actually truthful, or is it kind of lying to me? Well, the context helps steer that away from just giving you these general it sounds helpful, but is it true to being pinpoint specific and valuable for your company? Number six, context engineering. Alright. This obviously plays in line with the context layer, but this is where you insert, right, one of those three layers of data into the context window.
Jordan Wilson [00:25:33]:
So this can be things like your traditional prompt engineering, so you can share that context via your prompting. Right. But the important thing, really is knowing that it works in layers. So I'm gonna give you a couple hints. Right? So we taught prime prompt polish. Alright? The thirty second version of that is you should always prime a model, work with it a lot before you prompt it and ask it for an output. And then polish, we're actually gonna get to that technically in number nine and ten because the first output that a model gives you is usually garbage even if you do everything else correctly. Alright.
Jordan Wilson [00:26:10]:
Refine queue, that's where we talk about, you know, role, examples, fetch, insights, narration, explanation, and questions. Alright? If you wanna go more on the, you know, prime prompt polish, refine queue, five five five, this is like a decision tree on when you should use, a large language model versus when you should do it, quote, unquote, manually without AI. Actually, when you do go to starthereseries.com, and sign up for our community, you will also get access. Yeah. A lot of people don't know this. We recorded that. It's on demand. Right? I used to do it live.
Jordan Wilson [00:26:43]:
I can't do it live anymore, but I keep the videos pretty updated. So you can go take our updated prime prompt polish course. I think it was updated as of, like, GPT 5.4. So I'll probably update it once we get, like, five, six or something. But the, the basic, this is basic context engineering one zero one. Alright. So it can be as simple as, you know, doing the role, goal, sources, constraints, examples, whatever it is. But it's making sure that through your words that you're sharing, you are steering the model in the right direction and telling it what context to use, what output you need in working with it before you just expect it to give you amazing outputs.
Jordan Wilson [00:27:21]:
Alright. Number seven, working with files, apps, and company data. This one is huge. So files make AI far more specific to the actual task. Alright. And a lot of people think, oh, if I just dump all of my context into one one of these large language models and tell it, you know, okay. Now go, you know, right, you know, next quarter's press releases and update all our job descriptions based on the SOPs and right? All you're doing in this instance without getting too technical and accidentally turning this again into a ninety minute show, these think of them as books on the bookshelf. Right? You still have to tell the model when via whether that's through a a skill, a a plug in, a certain workflow, automation, etcetera.
Jordan Wilson [00:28:04]:
You still have to tell it when to use the book and sometimes direct it to look into what chapter. But, creating these, you know, app connections are huge because depending on if you're talking about, you know, Chad GPT, Claude, or Gemini, as an example, they all treat these connectors a little bit differently. As an example, some of them might index or cache some of your most important connectors like your Gmail. Right? So you don't even have to wait. It just knows, and it can actually, you know, proactively go out and find these things and surface them to you, which is actually huge. So, you know, whether we're talking about uploading files, you know, connecting, a connector or an app. Right? Like a Google Drive or a Microsoft, SharePoint, OneDrive, Box, etcetera. Your CRM.
Jordan Wilson [00:28:55]:
Right? Most of the big three, I don't know if Google does, but I think mostly everyone else has, like, HubSpot and some of the big names in CRMs. Right? All of these things now, for the most part, have read and write. And that is big, and that's much different than where we were at, you know, in the early days of connectors, like, nine months ago. Right? So now these can, well, run actions for you. So, you know, let's just say you get some information off of a Google Sheet, and you have to go, you know, update, something in a database, and then you have to go, you know, change some options on a CRM, and then you have to update your project management tool, ClickUp as an example. Right? These are all processes that normally I call the human duct tape that you would have to do. Now these connectors can talk to each other and carry that context over. We did a show called agentic context carry in the start here series.
Jordan Wilson [00:29:50]:
So go back and listen to that if you wanna know more about how that works. But, essentially, this is why these models with the context, you you know, layer in this an agent being able to carry that context and keep it in the context window is huge because this is the majority of what so many knowledge workers spend their time doing. You know, you have the five to 15 probably different SaaS applications that you spend your time in. You use your brain, your role, your requirements, your KPIs. You, grab all of that important context from all of these different, you know, apps. You, you know, personalize it, create some value out of it, and then you piece it together in all of these other apps. This is what agents do now. Right? So working with files, apps, connectors, and your company data is huge.
Jordan Wilson [00:30:37]:
Alright. Number eight, and this is important, especially following up. Maybe it should have been number seven. Right? Don't do the shadow IT. Right? Shadow IT is when you don't have permission or, you know, shadow AI or shadow agents, whatever you wanna call it. When you don't have permission to use your company data, you shouldn't be uploading it. Right? But the good thing is whether we're talking about cloud enterprise, Gemini enterprise, Chad GPT enterprise, they have the exact same data security and privacy, that you would have from your cloud provider. So if you upload, you know, your company's, data to a cloud is the exact same thing.
Jordan Wilson [00:31:20]:
It is the exact same thing as using these connectors in these apps. As long as you're going through, you know, turning off model training, doing the, you know, one zero one best practices, you're not running any additional risk. Again, that's a big if as long as you're, you know, using these models correctly, turning off, you know, training data, which most of the paid, business or enterprise versions do by default. You're not running any additional risk with your company's data. It's not like I'm gonna upload, you know, or connect my data, turn off model training, and my competitor is gonna be like, oh, what's everyday AI doing? That's not how it works. But people, smart people with brains still think that today. That's not how it works. Right? Governance is also extremely important.
Jordan Wilson [00:32:04]:
That is permission design. Right? This is not paperwork. This is not a one time twenty minute training because the systems are constantly changing. Alright. Also, personal accounts, those aren't like unofficial company AI systems. Like I said, you know, you should only be connecting your company's data. Number one, if you've gone through the guardrails, the governance, the privacy permissions, getting the sign off from everyone involved, but you should all also only be using it through the proper channels. Right? I can't tell you the number of companies when they're telling the truth.
Jordan Wilson [00:32:35]:
They're like, okay. Well, yeah, we we got our, you know, Copilot approved, but, you know, no one can get the right access to it. But, well, if we're using SharePoint and Copilot, we should just be able to use it in chat t b t. Right? Well, in theory, kind of, but also absolutely not. Right? That is going against governance one zero one. So, you know, expert driven loops are so important when we talk about, you know, properly setting up these guardrails, especially as these large language models, these quote unquote AI chatbots by default can now take actions for us, and we can schedule agents to go take actions, right, with right, w r I t e, right capabilities. Right? They can go off and email customers and update your CRM. And, you know, maybe if you're not, you you know, keeping an expert driven loop, it could potentially make a huge mistake that can cost your organization a lot of money.
Jordan Wilson [00:33:31]:
So there's obviously a downside to productivity and efficiency, if you skip over step number eight, which is proper privacy permissions and governance. Yeah. So after permissions though, leaders need visibility into what actually happened. And that's where we have to talk about the importance of transparency, observability, and reasoning artifacts. So this is where, people skip over showing your work, and being able to observe that as a team. Right? So I can't go into all the specifics because it's gonna take a while. But especially when you get up to enterprise accounts, not only can you see, you know, usage and things like that, you can see, right, I think Copilot actually leads in this. You know, I think with their, intra ID, you can see every action certain, you know, agents make.
Jordan Wilson [00:34:22]:
I think Chatt GPT's new workspace agents, for, business and enterprise, teams do a great job of doing that as well. But you have to be able to understand and show the work, especially when agents are, or sorry. AI chatbots are agentic by default. You have to be able to, observe them and understand the reasoning artifacts. What does that mean? You know, there's usually a little thing you can click, accept in Gemini. Gemini, can we get a little better at that, please? Right. I know there's a tiny step that we got, with three five flash and the, you know, updated version of Gemini, but we need complete transparency when it comes to seeing how models get from context engineering and great setups and great workflows to creating this great economically valuable work. And the reason being is because models change all the time.
Jordan Wilson [00:35:13]:
So if you can't properly see every single step in every tool call, in every website that a model or an agent went to in order to deliver that, you know, first draft deliverable for your team that you ultimately sent off to a client or the RFP or whatever it is, then you don't have the observability. Then you don't actually own that asset because you don't know what's happening. Right? So I like to talk about the steps in the middle are sometimes the most overlooked, but they're the most important. Because if you don't understand what's going on, you don't own it. Right? So what does that mean? If something happens in the harnessing or a model changes or, you know, there's a drastic switch up in how a model uses different tools. If you don't own and understand that observability, the the the reasoning, you know, artifacts, then you may not be able to replicate those same things. And if they if these things are running on loops scheduled, which is very easy to do, and one little thing changes, it can break your entire business if you become overly reliant on passive, lazy, human in the loop workflows versus expert driven loops. Expert driven loops means that you are looking at the transparency and observability.
Jordan Wilson [00:36:30]:
Alright. Last but not least is verification, iteration, and creating those workflows. Right? So what do I mean by this? Iteration is huge. So I talked about, you know, the prime prompt polish. This is the polish. You know, your first output, even if you do everything else, steps one through nine correctly, your first output for the most part from a large language model, even a great one, is at best case, it's gonna be generic garbage. Right? But it's not gonna be very well. It's not gonna sound like you.
Jordan Wilson [00:37:00]:
It's even when you give it the proper examples. Right? You have to really iterate on the output. You have to understand how it got to that output and then run it over and over and make it better. That is this iteration loop where you turn, you know, your first output. Right? My old journalism days, the first version of the story you turned in was never really good or the best. Right? You always had to go through the multiple editors and all the the the red all the red lines to make it better. And then once you get to that point, you need to then turn it into a workflow. And this looks a little bit different in chat g p t versus Claude versus Gemini.
Jordan Wilson [00:37:36]:
Right? But for the most part, we are getting these universally, applicable skills. Another thing, anthropic, led the way on this, and everyone else is adopting them. But skills are essentially ways that at the end of iterating, you can go through and, essentially, in more words than this, say, turn this into a skill. Right? And then once you turn it into a skill, then you can schedule it because, most of these systems have scheduling by default. So, it's all about verify that it works. You know, make sure you're using the right model, the right mode for the right tool. You're getting the right outputs. You're verifying it.
Jordan Wilson [00:38:12]:
You're going through the transparency, observability, the reasoning artifacts, but then you don't stop when you get that first, you know, hey. This draft is good enough. No. Keep working. That's where you Polish. You turn it into a skill, you turn it into a plugin and then you turn it to a, an automated workflow. And that's how we go from working with an AI chat bot to commanding AI agents. Alright.
Jordan Wilson [00:38:36]:
I hope this one was helpful, y'all. If so, let me know. If you're listening on the podcast, please do me a favor. Alright. This this one has been a long time in the waiting. So, you know, I hope more people can hear this because I wanna cut through the BS. I want to tell people exactly how these models work, and I wanna be able to do it for as for free as long as I can. Right? So that only happens if you're number one, sharing this with others.
Jordan Wilson [00:39:02]:
So if you are listening, you know, on LinkedIn as an example, please repost this if this is helpful. If you are listening on the podcast, please subscribe to the show. That would mean a lot. Leave us rating too if you can. So I hope this was helpful. Like I said, make sure to go to starthereseries.com to get exclusive access to all of the episodes in this series. Thank you for tuning in. I hope to see you back tomorrow and every day for more everyday AI.
Jordan Wilson [00:39:27]:
Thanks, y'all.