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
Scheduled Agentic Context Carry: The Next Step for Enhanced AI Workflow Automation
The AI landscape has evolved swiftly in recent months, revealing nuanced business value beneath the swarm of technical upgrades. While most business leaders remain focused on jumping from chatbot to chatbot, a less visible pattern has emerged following major launches from OpenAI, Google, Anthropic, Microsoft, and Perplexity: scheduled agentic context carry (SACC). This model is redefining how companies orchestrate routine tasks, cross-system workflows, and persistent memory within AI-powered environments.
AI Agents: Moving Past Chatbots to Persistent Scheduling and Automation
In the spring, major AI providers rolled out scheduled agents capable of running contextually-aware tasks both on fixed cadences and triggered by events. This transition shifts enterprise AI from reactive chatbot interactions to proactive, automated routines. Instead of repeatedly re-explaining the same requirements or manually bridging tasks between applications, orchestrated agents carry forward operational context—eliminating repetitive steps and dramatically reducing human intervention.
Key providers like Anthropic, OpenAI, and Microsoft have launched agents that schedule and execute operations across connected tools, maintaining memory of previous runs. For instance, OpenAI’s recent agent features support creating a workflow once, scaling it across teams, and running it on a schedule for recurring work. These agents’ capacity to interface across diverse business apps (Slack, Gmail, Drive, calendars, CRMs, etc.) marks a concrete step-change: routine digital labor can now be automated with persisted, cross-app intelligence.
Context Windows: The Technical Backbone Enabling Cross-App Intelligence
Modern agentic workflows depend on AI models’ expanded context windows—the effective working memory of an AI system. Providers have quietly increased these context windows from a prior baseline of around 8,000 tokens to 258,000 or even 1,000,000 tokens in enterprise-grade models. For business operations, this means an agent can track conversation history, instructions, company data, and dozens of contextual signals over weeks or months of operation, instead of losing critical context after a few exchanges.
This technical shift allows agents to not just process individual tasks, but to retain preferences, notice patterns, and follow ongoing business objectives. A scheduled agent can, for example, ingest updated industry reports each week, flag new market entrants, and tailor recommendations—all while referencing months of prior company goals and conversation history, without manual curation of information or context handoffs by a human employee.
Eliminating Manual Context Carry: Addressing Hidden Bottlenecks in Knowledge Work
Recent discourse has misunderstood the true value of agentic workflows, focusing myopically on the speed of single-app task automation. The actual business benefit emerges not from automating a task like sending a single email, but from offloading the invisible labor of connecting disparate systems and continuously carrying context between them.
For example, consider a multi-step process requiring email analysis, referencing drive files, cross-checking calendar events, and syncing with communication threads in Slack or Notion. Traditional workflows demand a knowledge worker to shuttle between these apps, manually retrieving and reattaching context to each new step. Scheduled agentic context carry dissolves these handoffs—enabling the AI agent to track, act, and remember across the entire stack, removing error-prone and time-consuming duct tape solutions.
Implementing Scheduled Agentic Context Carry: Three Actionable Steps
The operationalization of SACC inside an organization boils down to three disciplined steps:
1. Connect Live Data Sources and Preferences
Securely authorize AI agents to access approved business systems—email, calendars, CRM, drives, and chat tools. Ensure tools comply with organizational security and compliance requirements, and configure persistent memory and custom instructions reflecting business priorities.
2. Context Stuffing in a Dedicated Memory Thread
Aggregate contextual information—company docs, standard operating procedures, recurring goals—within a dedicated agent memory thread. Advanced context windows now retain weeks’ worth of operational memory, allowing for consistent automation of tasks like morning triage or weekly research, with reliable recall and progressive learning over time.
3. Iterate with Chain-of-Thought Reasoning
Before production deployment, routinely review and refine the agent’s multi-step workflows. Most platforms provide observability into executed steps, enabling inspection and adjustment of decision chains. Consistency and edge-case handling improve only through repeated trial, review, and adjustment.
Scheduled Agentic Context Carry as a Stepping Stone
SACC is not full autonomy, nor will it deliver unchecked automation across undefined business goals. However, it is the critical bridge between today’s narrow chatbot tasks and future AI agents capable of reliably executing complex, multi-system objectives. It eliminates the hidden productivity tax of manual context carry and lays the technical foundation for the next round of enterprise AI-driven efficiency.
Leaders currently integrating these automated, context-aware schedulers are streamlining operations, eradicating error-prone manual work, and freeing human talent to focus on judgment and innovation instead of repetitive digital legwork. The compounding value of such workflows will accrue swiftly for those who invest in understanding and deploying scheduled agentic context carry today.
Topics Covered in This Episode:
- Scheduled Agentic Context Carry (SACC) Explained
- AI Agents: Features vs. Benefits Paradigm
- Co-Working and Scheduled AI Workflow Shift
- Persistent Context and Memory in AI Agents
- Large Language Models’ 1,000,000 Token Context Windows
- Workflow Automation: Eliminating Human-AI Duct Tape
- Multi-App Integration and Cross-Platform Context
- Three Steps to Deploy Scheduled Agentic Context Carry
- Chain of Thought Iteration with Scheduled Agents
- Autonomous Agent Limitations and Future Bridge
Episode Transcript
Jordan Wilson [00:00:16]:
In the past twenty four hours, two of the biggest players in the AI space, OpenAI and Google, both launched updated versions of their simple drag and drop agents that work for you with your context around the clock. And that got me thinking of the common features versus benefits methodology when it comes to marketing. If you've never heard of it, it's pretty simple. Features describe the technical facts or the specs of what a product does, and well, the benefits explain the personal value the human gets from using said products. And in AI, we've seen a similar features versus benefits narrative take shape over the past few years. The feature, large language models are smarter and faster than humans when used correctly. The benefit, humans can be more productive, but the feature side has completely exploded over the past two months, and the benefit side is still being written. Stick with me here.
Jordan Wilson [00:01:14]:
So as large language models have become overly agentic by default overnight and as capable as humans, there's a new benefits paradigm for AI agents that has flown completely under the radar. And I know that this is the next big trend coming. It doesn't have a name, but I'm gonna go ahead and name it now, and explain the concepts. I'm calling this scheduled agentic context carried or SACC, s a c c. And I think the company's taking the time to understand and iterate on this new concept now are going to be the ones crushing their year end goals and KPIs in quarter four. So let's unwind this kind of new concept together because I think understanding this now is one of the most important investments you can make on your AI journey this year. So let's start there with our start here series. If you're new here, welcome to everyday AI, and this is our this is our here series.
Jordan Wilson [00:02:14]:
But let's first start with the big picture of what's going on. Anthropic, OpenAI, Microsoft, and Perplexity have all shipped scheduled agents just this spring. And most business leaders are still using AI just like a chatbot. I'm gonna go in and I'm going to technically, reactively ask an AI chatbot for something and probably have to reexplain a lot to waste a lot of time. But there's been a quiet workflow pattern, merging beneath every one of these recent product launches. And that's why we're talking about this new concept of scheduled agentic context period. So on today's show, that's exactly what we're gonna over kinda go over, and here's what you're gonna learn. You're gonna learn what agentic context query actually means and why you've never heard of it and but why it absolutely matters.
Jordan Wilson [00:03:06]:
You're gonna know how this hidden workflow bridges, chatbots, and the fully autonomous AI future. You're gonna understand the timing of all these things coming together and specifically these now huge 1 million token context windows that have quietly changed everything at this spring, and you're gonna know the exact three steps to deploy this pattern inside of your business today. Alright. Let's get started. Welcome to Everyday AI. My name is Jordan Wilson, and this is the start here series. So after 750 plus podcasts, I never had an answer when someone was like, I'm new. Where do I start? Well, you start here.
Jordan Wilson [00:03:43]:
Our start here series is an ongoing effort to help business leaders both better understand trending and emerging concepts, but also for those who are brand new to get caught up. So I'd recommend you start with episode one of the Start Here series and listen in order, but go ahead and listen to this one, and then you can go backtrack. But make sure you go to starthereseries.com because, well, it's gonna make it much easier to do that. That's gonna give you free access to our inner circle community. Right now, there's no other way for the general public to sign up except starthereseries.com. And then inside the starthere series space, there will be an updated Spotify playlist where you can go listen to all of the start here series very easily in order in a dedicated playlist. Alright. And if you miss our last start here series episode, we, in volume 20, so this is volume 21, we talked about AI change managements that works five moves the top 5% make.
Jordan Wilson [00:04:39]:
Alright. But let's get into this concept of agentic context carry. And y'all, every single major AI lab and the big third party players launched something. So from Mike was the big four. Right? So that's Anthropic, Microsoft, Google, OpenAI, and then even perplexity and, you know, OpenCLAW technically fall under this category. But literally, everyone launched something, and it's all very timely. So I did mention just the past twenty four hours with big announcements, from Google Gemini at their Cloud Next conference, and then with OpenAI's new agents that we're gonna talk about here in a minute. But also, quad code routines, right, that can bring, automated scheduled agent runs to your desktop.
Jordan Wilson [00:05:31]:
So it is kind of like the, maybe this open qual movement that happened, you know, really in February and March year, actually kind of forced the hand of all of the big companies to say, okay. It seems like we essentially to oversimplify it, we need a an an AI agent that can run on a cron. Right? Run on a schedule where someone can go in and they say, hey, AI agent. At this time, every single day, I want this to happen. So we had the quad code routines, which I absolutely love that runs on your desktop. Similarly, OpenAI in their codex platform just added schedule work and a persistent memory two days after that quad code routines announcement in mid April. And then we also just got wind that Copilot CoWork, officially launched in Frontier. So you have essentially all these scheduled, agent platforms slash coworking platforms.
Jordan Wilson [00:06:26]:
Right? So, like, Claude Cowork, is the big one. Microsoft Copilot uses essentially the Claude Cowork technology because they are an investor in Entropic. So you have those kind of two places coming together. You have these co working, kind of elements that allow for scheduling and it brings all your context, and then you have these scheduled agents. And it's all literally exploded out of nowhere. And although, you know, this may technically be a more timely, episode with all of these things happening now, the reason why I'm doing it in the start here series, whether you are listening to this in April or you're listening to it, I don't know, in the year 2027 is because I think that this is going to be a noticeable pivot in how the enterprise starts to interface with AI agents. Because here's the reality. Right? We've been hearing since probably late twenty twenty four that, oh, it's the year of AI agents and it didn't happen.
Jordan Wilson [00:07:23]:
And in 2025, it didn't happen. But I think we've now come to that realization in 2026 in a certain way. Because we've noticed that the fully autonomous, AI agents where you just give them a goal and then they go off and run on their own, not as reliable as we'd like, mainly because of safety concerns, guardrails, etcetera. So I think that this new kind of co working scheduled agents, is the stepping stone to where we will ultimately be when we have, you know, more of like, oh my gosh. This is artificial general intelligence. We have AGI because I give, an agent a goal and it doesn't need me for anything. Right? We're not there yet. So we are in this in between phase.
Jordan Wilson [00:08:04]:
I don't know if this phase is gonna last for a couple of quarters, couple of years. I'm not sure. But it is definitely taken shape so quickly over the last few weeks. And that's led to kind of, again, this feature benefit. Because when I think of traditional large language models, right, essentially, once once companies understood their utility, right, the immediate benefit was, oh, more time, productivity. Right? We can do more. You know, do do more or save time. But what about for the actual agents? Right? I think when we thought about AI in the feature versus benefits kind of paradox, we thought about the benefit on the human.
Jordan Wilson [00:08:46]:
But what about the benefit on the AI system? Because as they start to get agentic and more human like and how they could work, well, they start to benefit as well. And that benefit is the agentic context query that we're talking about today, and this is huge. And then like I said, just in the past twenty four hours, right, we had Google launch their Gemini enterprise agent platform and OpenAI launched their workspace agents inside of Cheggi Boutique. So we're gonna be going over that a little bit more on tomorrow's, show. And FYI, we did kind of go over some good examples of this context, Carrie, on yesterday's show on codex. Alright. So, if you missed that one, yeah, I'm unplugged both of these shows. So make sure to go listen to the codex, kind of super app preview seven sixty two, and then make sure to join us tomorrow more on these two recent launches.
Jordan Wilson [00:09:35]:
But here's a little bit on what the chat g v t scheduled agents can do just so we can kind of set the stage for why this context, Carrie, is extremely important. Alright. So how OpenAI says it in their recently released blog post, they say build once, scale across your team. Right? Create an agent once, share it with your team. Work that runs itself so you can run agents on schedules to handle recurring tasks, and then keep the work moving across tools. Right? So you can, the agents use your tools to gather information, take action, without needing step by step guidance. So now yeah. I had to do a little little wind up here, because I wanted everyone to really understand how big this is and how quickly it's happening before I really unwrapped this kind of concept that I coined, right, of agentic con agentic, context carry.
Jordan Wilson [00:10:39]:
Yeah. It's it's so new even even, you know, I don't just wanna say sack. Right? But scheduled agentic context carry. So this means, right, I wanna break down each of the four words and how they work together. So scheduled, obviously, means that the agent wakes up or runs on a cadence not only when prompted. So that can be both a time cadence, like we just talked about in the chattyPT agents, or as an example, in clogged routines, it can be a trigger. Right? When you get a certain type of email, then an agent is going to run. Alright.
Jordan Wilson [00:11:11]:
That's what scheduled means. Next, context query. That means your memory, either your personal memory and preferences, your company's data, all of those things, dynamic data pipelines, tool access, all those things that persist between runs. Alright? And that is the big piece there. That is the context and the carry. And, obviously, these agentic models all by default are able to do this. Right? So the models themselves, they can call tools. Right? They can, you know, call on, you know, these connected apps on these MCP servers that you can bring in, you know, thousands of different apps that you use.
Jordan Wilson [00:11:55]:
But the actual carry, that's what's important because as we've gotten these new context windows, which I'm gonna get into a little bit more, that's what makes this all possible. And the ability now for an agent to go out and learn something, right, about you or your company without you having to teach it. So let's just say you have a scheduled agent. Right? You give it information about your company, your company's goals. Maybe you're looking to acquire, you know, a new client or a new customer. But the industry whatever industry you're working in is moving fast. Let's say you have an agent that goes out, you know, every Sunday night, it pulls up the in the industry's most recent white papers, industry news, etcetera. And, oh, all of a sudden, when you didn't know it, it found out that you have a, you know, a huge new potential, you know, buyer moving in into your state that wasn't there before.
Jordan Wilson [00:12:50]:
Right? And the reason that this can happen is because it's able to carry the context with you. All of those documents that you share, preferences, the memory of your, you know, recent chats, but also that can run-in essentially the same context window over and over. So not only can it carry in the context that you give it, according to your information, but also the persistent memory of that actual conversation. So it's going to know. Right? If you have a a run that goes every single day, it is gonna carry that trend line with it. So it does start to turn into, oh, you know, it's like when you hire a junior employee, after a couple, you know, days on the job, they kinda start to get it. After a couple of weeks on the job, you're like, okay. It's picking up momentum.
Jordan Wilson [00:13:36]:
The same thing. That's, I think why this is a very exciting time in AI. And this, I think, is that bridge between, you know, the simple chatbots to the fully autonomous agent. Because as much as every, you know, OpenClaw aficionado wants you to believe, we are not yet at the point where, we have true autonomy in agents. Right? Where you give them a goal and they can safely go execute that goal without constant human intervention. Is it possible? Sure. Right? If you have a very well defined goal, if you have strict guard rails, and if you're using it in a narrow capacity. I don't think we have autonomous general agents.
Jordan Wilson [00:14:22]:
I think we have autonomous narrow agents that can do one very very simple, task if you give it or a goal if it's very, very specific. Right? But what happens if the guardrails are changed? What happens if the industry's changed? What happens if your data is corrupted? Right? An autonomous agent would, in theory, be able to, figure those things out. We don't have that right now. And I think that this, agentic context theory is that stepping stone that's gonna help us get there. I've I've also, you know, talked about this a little bit before. Previously, I'd call that kind of like, you know, the human AI duct tape. It's all those intermediate steps in between that a human had to do. Right? If you run something in, you know, deep research, inside ChattGPT, well, now I have to copy that.
Jordan Wilson [00:15:08]:
I have to go put it in a doc, and then I have to upload it to this project folder as an example. That is where this context carry and the larger context windows starts to erase, all of that manual, you know, human AI duct tape that, you know, those steps that us humans working with multiple AI systems would have to continually make. Because now these agents also have right ability. Right? Whereas before, you know, three to six months ago, they didn't have the ability to write to your Google Docs. They didn't have the ability to send Gmails. Right? Now they do. Right? If you give them the permissions and if you're feeling, you know, spicy and you wanna roll the dice. But that agentic context carry layers the schedule and the memory over that, but no one is really talking about this.
Jordan Wilson [00:15:56]:
I don't know. Maybe maybe I'm too dorky and excited about where we are. But the reality is, I think that there's been this AI moves too fast to follow, but you're expected to keep up. Otherwise, your career or company might lag behind while AI native competitors leap ahead. But you don't have ten hours a day to understand it all. That's what I do for you. But after seven hundred plus episodes of Everyday AI, the most common questions I get is, where do I start? That's why we created the start here series, an ongoing podcast series of more than a dozen episodes you can listen to in order. It covers the AI basics for beginners and sharpens the skills of AI champions pushing their companies forward.
Jordan Wilson [00:16:47]:
In the ongoing series, we explain complex trends in simple language that you can turn into action. There's three ways to jump in. Number one, go scroll back to the first one in episode six ninety one. Number two, tap the link in your show notes at any time for the start here series, or you can just go to starthereseries.com, which also gives you free access to our inner circle community where you can connect with other business leaders doing the same. The start here series will slow down the pace of AI so you can get ahead. Narrative right now. And, I'm actually gonna call out a recent, tweet, I saw or an x. What do you call what do you call a tweet on x anymore? I don't know.
Jordan Wilson [00:17:33]:
This is why I call it Twitter. You can't verb x. But there's a recent viral, tweet out on Twitter. Right? So ChatJBT had a recent integration with Starbucks. Right? Someone said, oh, you you know, why are all of these apps right? Why do they exist? It doesn't make sense. Right? Because it's gonna take me, you know, two minutes at the absolute fastest to make an order on this chat GBT Starbucks app integration. I'm just using this as an example. Throw in any, you you know, business app that you're using inside or, you know, connector that you're using inside Gemini Copilot, Claude or Chat GPT.
Jordan Wilson [00:18:12]:
But this kind of viral incident with Starbucks. Right? It's like, okay. Well, it takes two minutes to order it via the the the the app and if, the Chat GPT app. But if I go into the actual Starbucks app, I can do it twenty seconds. Right? So this is done. Right? But I think people are missing the points because it's not just about one app. It's not just about ChatGPT interfacing with one app. Because in the new agent builder, right, as an example, the brand new, agent builder, you can go to create an agent all by hand.
Jordan Wilson [00:18:48]:
I'm literally clicking around as I do this now. You can connect 20 apps. Right? Your your Gmail, your Slack, your Notion, your Teams, your Outlook email, your Google Calendar, Google Drive, whatever. Right? MCP servers. You can do all those things. You can connect agent skills. You can upload files. You can manage the memory.
Jordan Wilson [00:19:12]:
Right? So it's not just about, oh my gosh. You know, using a single app to do a task is so much slower, than it is to just do it individually in that platform or on that website. That's not what it is. It's about eliminating that human AI duct tape. It's about, you know, the the the 30 small human steps in between that are required. That is the context carry. Us humans have been the one carrying the context because AI agents didn't have the ability. They didn't have the, the tools to do that.
Jordan Wilson [00:19:43]:
Now they do. That's the thing. Yes. I can much more quickly go open my Gmail, read an email, and respond to it, than a connection in Gemini, etcetera. Right? But what about when there's a a Google Doc that goes with it? I have to look at my calendar. Oh, there's actually three or four different emails. Right. Oh, there's that file in my drive.
Jordan Wilson [00:20:13]:
There's a Slack conversation about that. Right? Now all of a sudden, yes, it might be quicker to do all of those small tasks individually in those apps or on those websites. But when you have to carry the context yourself manually as the human, that's where you can start. Right? This is essentially been the, mundane nature of knowledge work in front of a computer over the past twenty years, you know, as SaaS and applications have exploded. But that's what we do, and that is where the true benefit of now agentic context carry because us humans no longer have to do the duct tape and have to remember and have to bring that context from app a to app b to app c to storage d to messaging platform e and f. The agent does it all for us in one swoop. So, yes, it might take you five times as long to accomplish a goal inside of an AI agent, but that's not counting the human error, the human lookup, the human retrieval that has to happen every single step of the way in between. That's the big unlock here, y'all.
Jordan Wilson [00:21:23]:
But also, I don't know. I start to forget things fairly quickly. Maybe it's just me. Like, I literally use, you know, this concept of agentic context, Carrie, all the time. Right? I was actually walking, I was actually walking to, my office. Right? Sometimes I record, you know, from my kind of home office. Sometimes I, you know, record from my actual office. And, you know, I'm working on a cool partnership here, with the group Sage.
Jordan Wilson [00:21:49]:
And I had a couple different email threads with with travel. There was Google Docs. There was all these things, and I'm like, which, you know and I have multiple emails. Right? I have multiple email accounts. Certain forms go different places, and I'm like, my gosh. Like, this is gonna take me a long time. Instead, right, just use in this instance, use Claude. It went and carried that context.
Jordan Wilson [00:22:12]:
But what about when you can schedule those things? Right? And to say, hey. Every day at, you know, 2AM, I want you to go through my my my email, my calendar, Notion, Slack, all of these things. Yeah. It might take the agent longer to do that if than if you were to, but it's gonna do it on its own schedule, and it's gonna carry the context from app to app. So that's where the new breakthrough comes. It's the capabilities that have made the cross app technology possible. So here's where the unlock and the timing all comes into play. Right? I love Venn diagrams.
Jordan Wilson [00:22:52]:
Right? This is where it's kind of the the capabilities and the technology and the need have all overlapped with this perfect timing. So this is, you know, if you think of, like, co work or agentic scheduling, the features and then the context window all coming together and exploding at the same time. Right? So Claude, Anthropic has really led the way of this. So now they have that 1,000,000 token context window by default. Right? Codecs a little bit, you know, behind, although there is an experiment experimental, 1,000,000 token context window, in the command line interface. But on the app, I believe it's 258,000 tokens. So what does that mean? Right? If you're not too technical, that just means right? The free version of ChatGPT, last time I checked, I I haven't checked the free version in a while. But let's just say in 2025, it was about 8,000 token context window.
Jordan Wilson [00:23:46]:
Right? So now you're looking at 1,000,000. So do the math there. Or, you you know, or, you know, going to 258,000. Essentially, now AI models and AI agents can remember things over a very longer period of time. Right? Whereas before, they essentially had very short term memory. You would, you know, especially if you were on a free plan or, you know, early in 2024, 2025, AI models forgot things very quickly. So especially when it came to handling your data. So if you upload a file, you're working with it.
Jordan Wilson [00:24:18]:
Right? Maybe updating a job description and doing some research on recent law changes to make sure that your, you know, job description reflects those or something like that. Right? And it's going well, and all of a sudden it's, oh, wait. It's done. Right? That's because it ran over the context, but it context what is used to be very small. But now as they become bigger and bigger and bigger, right, it's essentially you're working with an AI model that has a bigger brain that's able to carry the conversation for longer. So now you know this kind of trending concept that's happening. It's not just going in and working with one app or one connector. Right? It's bringing in all of the different tech stack that you have to use on a daily basis, that your company has to use on a daily basis, eliminating all of those manual steps in between because the reality is just like a large language model, us humans, we have a context window as well.
Jordan Wilson [00:25:12]:
How much time do you spend? Right? Even pre AI, it was obviously way worse. But sometimes you spend just as much time trying to either track, remember, or find certain information where it lives within your kind of SaaS database as it actually takes to create that new business value once you do find it or reply to a certain email or to finish a certain deck or a project or fill out a spreadsheet. Right? Sometimes you spend as much time just trying to retrieve that information. So that's where the multiple apps is a big context window and the new agent capabilities, those three things coming together come to play. So now that you know it's here and you know that this, I think, is the intermediate step stepping stone until we have those fully autonomous agents. You need to take advantage of this scheduled agentic context carry sack. Right? Here's how. Step one.
Jordan Wilson [00:26:05]:
Three steps. Ready? I'm gonna go quick. Connect your live data sources and your preferences first. Make sure to do this. You know, I do have to, you you know, put up a normal disclaimer. Right? The, responsible AI person I am. Right. I'm a business owner.
Jordan Wilson [00:26:21]:
I decide if this is safe for my organization, but you need to do the same. Right? You shouldn't be doing this with shadow AI tools. You you could be doing this with approved tools, so make sure you go through the proper channels. But let's just say you have, you know, Claude approved or you have Chattopty b t approved, whatever it is. Right? And you have these connectors or apps approved as well. Alright. So you need to authorize those live connectors to your, as an example, your email, your calendar, your Slack, your drive, all of those important things, your CRM. Right? It's huge.
Jordan Wilson [00:26:52]:
Then you need to understand how each system's computer use and access works, and then ensure your custom instructions and memory are updated accordingly. So first, you have to get your data sources, your preferences, and your memory in line because when you talk about context, Terry, well, context is the base. Right? We did a an earlier show in the start here series on the importance of context engineering, so make sure you go back and listen to that one as well. And then also, all these platforms, they support MCPs. So even if you're, you know, your app of choice, whatever you're using, doesn't, have any of, you know, oh, it doesn't have a app connection to ChatChiquiti or doesn't have an app connection to Claude. Well, chances are you can just use a an MCP server and get that cooked up right away. So that's step one. Step two, you need to context stuff in a dedicated memory thread.
Jordan Wilson [00:27:43]:
Here's a little I wouldn't necessarily call this a cheat code per se, and this is much different. Right? I've I've I've obviously talk taught, you know, this concept of of prime prompt polish, you know, the basics of prompt engineering one zero one. With the context window, it doesn't throw away those best practices, but it does kind of change what can get done. So here's a little, little cheat sheet one for you for listening to this, episode now for twenty six minutes running. These systems now, the context windows are enormous. You can work on it in theory for a bare depends on what tools you're calling. But, you know, in quad code as an example, you know, running your routines all in the same thread of daily schedule, it's gonna hold. Right? I have some that run every single day that started, when it first came out, you know, two ish weeks ago, and they're not even close to hitting, the context window.
Jordan Wilson [00:28:42]:
Right? So at a million tokens, the agent can hold just weeks of regular usage working memory at once. So here's what I like to do. Connect everything to one threat. Right? They these all work a little differently. Right? You you know, codex works a little bit differently than cloud code, works a little bit differently than these brand new, you know, ancient builders essentially that we got from, from Chativity and from Google Gemini. But essentially, if you do connect things on a thread by thread or a folder by folder basis, have one where you just contact stuff. Right? Put all your contacts in there at once, and then that can be your daily drive. Because the good thing is is then also if you need to take it into a different direction, you can just fork that thread at that point.
Jordan Wilson [00:29:27]:
Right? So you at least have this unified base where you can every single day, right, have it be the one that brings you your your morning triage, the one for your, you know, most common day to day tasks, but aren't necessarily specifically project based that require a lot of different, directional feedback, etcetera. Right? So from that, you can iterate on the reasoning until it matches your standard. That's the big thing. You need to context step two is technically context stuff and and iterate as well. Well, iterate will actually get a little bit more into step three. Sorry. I I jumped ahead of myself. So step two, context stuff and, context stuff in a dedicated memory thread.
Jordan Wilson [00:30:05]:
And then step three, iterate with chain of thought. If you listen to the show at all, you know how important this is. You saw this in my little demo, that I did yesterday on codex. Right? You need to understand, how these models work because they are generative. They are not deterministic. They're gonna work slightly different each time. So you can't just run something once. Right? Especially as these, the the capabilities become, greater and greater.
Jordan Wilson [00:30:34]:
Right? A lot I I I see a common mistake a lot. People will run something once, and they're like, oh, yeah. This is great. Let's put it out in production. Okay. Well, that's could be dangerous, especially if you're doing something, public facing or client facing. You probably wouldn't wanna do that just yet. Right? Because there's always gonna be edge cases.
Jordan Wilson [00:30:51]:
You can run the same schedule run every single day for seven days, and it might two of the days, it might call the tool that you didn't want it to or, maybe it's, not calling a tool that you are telling it to. So you really do have to review the chain of thought and iterate. So what that means most systems, you can kind of have some level of observability traceability, as they go by looking at the system. So if they're scheduled, you can go, you know, usually, you might click on, you know, might say, oh, thought for one hour. You can click that and then see every single tool, every single step, and kind of get how the, that schedule would run or that co work session, how it works. And you can kind of trace it the same way. Right? When you think of, like, bath, right, where you had to show your work. I don't understand, like, the new common core bath stuff.
Jordan Wilson [00:31:39]:
Right? But back in my day, right, we just I don't know. Wrote down the the the the numbers in a column. Right? But yet to show your work. So you should always be checking the work of your, you know, co working run of your scheduled agents task and then iterating it. You need to, refine the prompts, make it better, and then once it is kind of quote unquote ready for production and you've built those guardrails in place, that's when you can save it as a routine or a schedule of automation. Then once refined, that is that hidden workflow. So it is those three steps that really allow that agentic context theory. Again, faster, step one, connect your live data sources and preferences first.
Jordan Wilson [00:32:18]:
Step two, context stuff in a dedicated memory thread. And then step three, iterate with chain of thought reasoning before you put it out into production. But then schedule that thing and take advantage of this stepping stone that I think is going to be huge, and the time is now. So like I said before, this is not the final destination. I think that truly autonomous agents with persistent memory are the next big deal, but we that could be far off. Who knows? I mean, maybe we'll have that, you know, next month, but it could still be another year, two years, or more until we actually see autonomous agents that you can give them a goal and they don't really require much else. This is the now or the next. So understand, and really push this agentic context carry.
Jordan Wilson [00:33:08]:
The leaders pulling ahead this quarter are building scheduled context on autopilot, not just, you know, better one off prompts, not just, you you know, sharing skills within your organization. That's no longer enough, right, to really be pushing in your space. So pick one recurring task this week, take it through those three steps, and then deploy your first kind of hidden workflow inside of it that's taking advantage of scheduled agentic context, Carrie. I hope this was helpful y'all. If it was, please go to starthereseries.com. That's gonna take you straight to a sign up form to get access to our community for free, the everyday AI inner circle. And then in the start here series space, you can go find every single start here series podcast, read every single start here series newsletter all in one space, Connect and network with others who are doing the same. Alright.
Jordan Wilson [00:34:07]:
I hope this is helpful. Thanks for tuning in. Hope to see you back tomorrow and every day for more everyday AI. Thanks, y'all.