Nate B Jones explains four practical AI agents for non-technical users
A solo presentation by Nate B Jones on how to understand and use AI agents without a technical background.
Summary
Nate B Jones of AI News & Strategy Daily opens by cutting through the industry's overuse of the word "agent," offering a simple working definition: an agent is an AI that does things, not just talks. He introduces his "little guy theory" as a mental model for understanding agents — each agent is a competent helper hired for a specific job, not a replacement for human judgment. He then presents four agents he considers the most practical for non-technical users today — Manus, Notion AI, Lovable, and Zapier — explaining what each one does, what it costs, and how to get started with a concrete first task. The episode closes with a framework for building reliability before adding complexity.
Key Takeaways
FULL TRANSCRIPT
Defining what an AI agent actually is
Nate B Jones: The AI industry has a big terminology problem with agents. Everything's an agent now — chatbots, assistants, co-pilots, automations. The word has stretched so thin it means almost nothing. So let me give you a definition that is really, really simple, but actually holds up.
An agent is an AI that can do things, not just talk. If you ask it a question and it answers, it's a chatbot. If you assign it a task and it goes away, executes work, and comes back with a deliverable — like a spreadsheet, a document, or a working application — that counts as an agent. That distinction matters because it changes your relationship with the AI. If you are not having conversations and instead you're delegating outcomes, you are working with an agent.
The technical architecture behind this is simpler than the industry probably wants you to believe. Every agent consists of three components: a language model that reasons and makes decisions; tools that let it take actions in the world — browsing websites, editing files, calling APIs; and guidance that constrains what it should and should not do. That's it. LLM plus tools plus guidance equals agent.
The magic is not in any one of those pieces. It's in the combination. The sum is greater than the parts. A language model without tools can only talk. Tools without language models require you to operate them manually. Guidance without both is just a document nobody's going to read. But if you combine all three, you get something that can receive a goal, figure out how to accomplish it, execute the steps, and report back the results. Now you have an agent.
The little guy theory
Nate B Jones: I want to suggest a way of thinking about agents that will make them much easier to understand if you're not a technical person. I call it the little guy theory, and I think it corresponds to how a lot of us think of agents anyway, which is kind of handy.
Every agent is a little guy that you hire to do a particular job. The little guy is not a genius. The little guy is not a replacement for human judgment — just a competent helper with particular skills and particular limitations. This framing matters because it sets the right expectations. You wouldn't want a new hire to have your company credit card on day one and say, "Figure it out." You'd give them a very clear assignment. You'd give them limited permissions. You'd check their work before trusting them with more. Agents work the same way.
The little guy framing also clarifies what you're optimizing for. You're not trying to build artificial general intelligence in your Notion workspace. You're trying to get tasks done without doing them yourself. That means reliability beats capability every single time. I would rather have an agent that correctly researches 20 companies than one that attempts to research 100 and hallucinates half the data. I'd rather have an automation that handles 80% of cases perfectly than one that tries to handle 100% and fails unpredictably so I have to manually check every single one.
The goal is not to be impressed by what agents can do. The goal is not to put AI agents on your website — I know that's a surprise to some of you. The goal is to trust what the agent can deliver so you can delegate outcomes.
One small note on agents and pricing. If you are thinking about a hiring frame for your little guy, it helps you understand pricing, because in most cases with these agents you're paying by the hour the way we would pay a little guy to do work. These agents work by the token, and so it's a very similar mindset — you're paying for the tokens that this agent will use to do the task, just as you would pay someone to help you do a task by the hour. You're hiring the agent for this job.
This also sets the reliability conversation right at the forefront of your mind. If you're hiring someone to do the work, you expect them to be reliable. You need to be able to expect the agent to be reliable too, which is something that doesn't get talked about enough. I think we spend a lot more time talking about whiz-bang top-1% AI agent implementations and a lot less about very basic AI implementations that we can execute reliably, that save us a ton of time and make a real difference. And that's what this video is about.
The four knobs of agent reliability
Nate B Jones: This leads to what I call the four knobs of agent reliability.
The first knob you can turn is the habitat. Where does the agent operate? Where does your little guy live? Some live on the open web, browsing websites, extracting information. Others live inside your workspace, organizing and transforming content you already have. Others build software. Others connect applications and move data between them. Pick one habitat to start. Mixing them together is totally possible, but if you're just getting started, it can also create a lot more complexity than you need.
Second, agents need hands. What can the agent touch — what tools does it have? Read-only access is probably the safest. That means the agent essentially has a pair of glasses and eyes — it can read stuff, but it can't write. The ability to click buttons and take actions is more powerful but riskier. The ability to spend money or make irreversible changes — I would keep that off until you deeply trust the system.
The third knob is what you would call the constraints, the guidance, or even the leash for the agent. How much freedom does this agent have? A tightly leashed agent follows explicit step-by-step instructions every time. A loosely leashed agent gets goals and figures out its own approach. If you're just getting started, you want to define it as carefully as you can to avoid confusion and avoid unhappy outcomes.
The fourth knob is proof. Can the agent show it did the job correctly? Can you specify what good looks like — what a successful outcome looks like that the agent needs to demonstrate? Things like providing source links, screenshots, logs of the work, or before-and-after comparisons. If an agent cannot show you its work, it's really hard for you to verify its work, which means it's hard for you to trust its work.
The four agents non-technical people actually need
Nate B Jones: With that introduction to agents, I want to give you what I would say are the best four agents that fit this little guy mental model and that will help you get started if you're trying to get agents that do reliable work. These four agents cover most of what a non-technical person needs to accomplish. I've tested a lot — there are a dime a dozen. These are the ones you can actually use.
Agent one: Manus
Nate B Jones: Manus is your internet researcher. It lives in the cloud. It spins up a browser you can watch in real time. It can navigate websites the way a human would. It compiles findings into structured deliverables — think spreadsheets, documents, or slide decks.
The experience can be a little eerie the first time. You assign a task like "compare pricing and features for these top ten competitors," and you will literally watch as it opens tabs, scrolls through pages, copies data into a table, and delivers a CSV twenty minutes later. You don't have to watch, but you can. And there's some proof of work there. What would have taken you three hours of clicking, copying, pasting, and building a deck happens while you do other things.
The free tier gives you around 300 credits daily right now, which is enough to test it out. Paid plans get more expensive — they run from $19 to $199 a month depending on how much complexity and how much concurrency you need.
The key to using Manus well is specificity. Tell it what columns you want. Tell it what sources are acceptable and what format you need the output in. Vague instructions produce vague results — and that's kind of a hint for most LLM work, actually.
I am not just recommending Manus because it's good for beginners. I am recommending Manus because it is a very powerful computer-use agent for people who want to get real work done and who don't want to be in the code all the time. There are a lot of folks in what I would call the professional class who use Manus as their secret weapon, because Manus lets them get comprehensive deep research and organization tasks done in a way they could not get any other way.
This is true even if you use something like ChatGPT deep research. You might think there's a lot of overlap with Gemini deep research or ChatGPT deep research, but it turns out that Manus is generally speaking more complete at the kinds of deep research, thinking, and organization tasks, and it can output in multiple formats, which is handy.
For example, if you want to find a list of emails to reach out to about a potential fundraise — say you need to reach everybody in a Y Combinator class or everybody at a particular series of funds — that is a complex task that would take a junior associate several hours. It takes Manus a few minutes, and unlike ChatGPT deep research, it actually finds them all. It actually gets the whole job done, then comes back and gives you a spreadsheet. It can even help start to craft the email.
People who want work completely finished are often using Manus. And I hear back when I recommend Manus: "This is expensive." I come back to that little agent hiring paradigm. You're hiring this agent to do reliable work just as you'd hire someone to do reliable work. If you can get in a few minutes all of the emails you need for a major fundraise, it's probably worth the money. Think about the value of the work you're assigning the agent and budget accordingly.
Agent two: Notion AI
Nate B Jones: Notion AI is another great agent. Think of it as a workspace brain. Unlike Manus, which goes out into the world to find information, Notion AI works with the content you already have. And I will just not hide the ball here — it works in Notion. So if you are not in Notion, this is not going to be as useful for you. If you are in Notion, it is tremendously useful.
It works across your notes, your databases, your meeting transcripts, your project documentation. The September 2025 update introduces truly agentic work where you don't just answer questions about your workspace, but you execute multi-step tasks across it. You can update a pipeline and sales estimate within Notion based on a meeting transcript automatically. You can instruct it to extract every action item from your meeting notes, group them by owner, create a task database — and it will just do that.
The limitation is that Notion AI comes with the Business or Enterprise plans, because that's where they think you're going to use it. So if you're on the free plan or the Plus plan on Notion, you're going to have to upgrade to get access.
If your knowledge already lives in Notion, this is probably the fastest way to organize, search, and transform it. The key to using Notion AI is feeding it all of your rich context. That's why it works best with a rich existing database in Notion.
Agent three: Lovable
Nate B Jones: Lovable is your app builder. I've talked about it before. You describe a piece of software in plain English — "I want a personal CRM to track my professional network with a form for adding contacts and a searchable card grid," or "I want to make a travel website for my family" — whatever it is. It generates a working application. It generates front end, back end, and a database. It gives you a live URL. It lets you iterate through conversation. It helps you set up payments.
This is not a toy. The applications Lovable produces use real code — usually React and Tailwind — and you can export to GitHub and continue developing yourself or hand off to a developer later. What used to require hiring someone or learning to code yourself now requires describing what you want clearly enough to build something simple.
I have been using Lovable since the beginning, and I have seen it become easier to describe what you want and get a reliable build. Paid plans will increase your message limits. Kind of like Manus, you hire what you get — if you want an assistant to build you a working web application, it's vastly cheaper than a developer.
The key to using Lovable well is starting with a very clear mental picture of what you want and describing it precisely. The AI cannot read your mind, but it's really good at interpreting detailed instructions, and Lovable keeps investing in features like visual editing that help you more precisely realize your vision. So if you're looking to build a small application to start a business or to demonstrate a proof of concept, Lovable is great.
Agent four: Zapier
Nate B Jones: The last little agent I want to call out is Zapier. Zapier is your logistics manager. It connects applications and automates workflows. When something happens in app A, do something in app B. When something happens in Salesforce, put this into Slack.
We've had Zapier for a while, so why am I bringing it up now? Zapier has added agents which add AI reasoning to these traditional workflows. So instead of rigid if-then rules, agents can analyze your incoming data, make decisions based on context, and choose appropriate actions dynamically.
I would recommend starting with basic Zaps until you've built a few and understand how this works. If you've never used Zapier before, once you understand how they work, then start to add AI features where it makes sense. There's no point in adding an AI reasoning agent to a system that has very simple if-then rules and works better without it.
The key to using Zapier well is starting with one trigger, one action, getting that working, and adding the complexity of the agent when you really need it. For example, if you're trying to classify your incoming leads, that might take reasoning with a prompt from an agent — maybe it works better to have an agent do that. But you might start by just seeing if you can get your leads into a spreadsheet, and then add the classification column later with an LLM agent and see if that helps. That's an example of how I would progress through.
Concrete first tasks for each agent
Nate B Jones: Theory is easy to talk about, but let's try some specific examples that you could actually do with each of these agents so you can see what I mean. Each of these does not take very long. They're designed for this agent, and I hope they give you a sense of how easy and concrete it is to go out and get work done with agents. I don't want agents to feel inaccessible — that's what this entire video is about.
Try Manus. Open Manus and say: "Compare these top five email marketing tools for small creators in 2025. Please output a CSV with columns for tool name, starting price, free plan limits, a one-sentence best-for description, and a source URL. Please visit the official pricing page. Please do not guess prices." And then, by the way, you can say, "I don't know what the top five tools are — please research and determine the top five tools." Then just watch it work. When it delivers a spreadsheet, open the source links and verify that it got them right. Basically, it gives you a small research exercise that helps you see how Manus works.
With Notion, find the messiest page in your Notion workspace — whatever is a brain dump in there or copied text from elsewhere. Then ask Notion AI: "Please read this page. Extract every action item into a checkbox list. Group it by person responsible. If no deadline is specified, please mark it as TBD. If no owner is clear, mark it as unassigned."
This sounds really boring, but one of the most critical pieces that AI agents can help us with is our own hygiene in meetings as humans. Humans like to talk in meetings and then we don't follow up and nothing changes. Little things like this — making the AI a passive, always-on feature — are really helpful. Notion AI lets us do that. We can just define the action items, label the owners, label the due dates, and move on with our lives.
Lovable. Go to Lovable and say: "Build me a personal CRM app. It needs a form to add a person with fields for name, company, the last time I met them, and any notes. Please display people in a card grid. Add a search bar at the top to filter by company. Please use a modern, clean design. Right now I don't need authentication." You can add authentication, by the way, but we're just keeping it simple. Watch it build, click the preview, play around with it. You can even hit publish. You don't need to code. You don't need to hire someone. You just need to articulate what you want.
Lastly, with Zapier, create a new Zap. Set Schedule by Zapier to every day at 9:00 a.m. The action is to send yourself a Slack message that says: "Daily check — what's the one thing you must complete today?" Integrate it with Slack and see if at 9:00 a.m. every day you get that little message. The most reliable workflows are just ones that are deterministic — when X happens, do Y.
Now, this is not truly LLM-powered yet, but you can see how it could be. You can see how you could then say: "Read my last day's worth of work in Slack, turn it into a digest, and give it to me at 9:00 a.m." Now that's an LLM job. And so you can easily add that complexity over the top when you're ready.
How to build from here
Nate B Jones: I want you to understand the core loop here. You are assigning work. You're verifying the output. You're iterating on the instructions. Everything else is refinement.
Start with just one agent. Run a couple of missions in Manus or in Notion until you develop an intuition about what works. Once you have something reliable, make sure you do that use case well before you add another one. So many people try to do all of the things at once — "Let me have a Claude Code instance and let me set up all of my files so Claude Code can grab them and work with them." I love that. I've done whole videos on Claude Code. It's an amazing tool. But the people who thrive with AI agents don't have to have technical backgrounds. It's just being able to articulate what done looks like, and to understand where you have unclear instructions so you can clarify them for the agent.
I will be happy to do a follow-up on non-technical use for technical tools — I think that's a whole separate video. But for today, let's just focus on our team of little guys that handle work that used to eat our days. If we can get that far, that is already a huge win.
The future is not learning to code. It's learning to delegate — and having enough technical understanding of what those agents are doing, using LLM and tools and guidance, that you can troubleshoot. You have everything you need to set up your little guy and do your first agent mission.