Maximize Productivity with AI Agents

This ad is not shown to multipass and full ticket holders
React Summit US
React Summit US 2025
November 18 - 21, 2025
New York, US & Online
The biggest React conference in the US
Learn More
In partnership with Focus Reactive
Upcoming event
React Summit US 2025
React Summit US 2025
November 18 - 21, 2025. New York, US & Online
Learn more
Bookmark
Rate this content

In this talk, we will explore how to offload work to large language models and automate away most "busy work" in order to maximize and enhance productivity on a daily basis. We will do so mainly by exploring how LLMs can callfunctions.

This talk has been presented at Productivity Conf for Devs and Tech Leaders, check out the latest edition of this Tech Conference.

FAQ

In AI, an agent acts on behalf of a user or a group, taking an active role or producing a specified effect, similar to the broader definition of an agent.

Agency in AI refers to the ability to choose tools and produce specific outcomes, similar to the concept of free will or freedom to choose.

Language models use tools by generating structured output, such as JSON, which is then processed by an orchestration layer or application.

MCP is a protocol that makes functions available to AI models over standard input/output or HTTP, allowing models to be extended with new capabilities.

The orchestration layer organizes and manages the interaction between language models and tools, enabling structured task execution.

Tejas Kumar is a web developer with over 20 years of experience, having worked at companies like Brasel, Spotify, and Zeta.

Developers can use AI agents to automate coding tasks, manage repositories, and integrate with development tools, enhancing their productivity and efficiency.

Langflow is an open-source diagramming tool that helps understand AI agent workflows by connecting models and tools using a visual interface.

AI agents can increase productivity by automating tasks, integrating with tools and services like Google Calendar, and providing intelligent assistance for scheduling and information retrieval.

AI agents are AI systems that act on behalf of a person or group, taking an active role or producing a specified effect. They can choose tools to achieve specific outcomes.

Tejas Kumar
Tejas Kumar
25 min
27 Mar, 2025

Comments

Sign in or register to post your comment.
Video Summary and Transcription
I'm Tejas Kumar, a software developer with over 20 years of experience. AI agents are defined as entities that act on behalf of users or groups to produce specific effects. Agents consist of an orchestration layer, a language model, and tools represented as JSON functions. Langflow is an open-source tool that allows users to build their own AI agents by connecting language models and tools. Composio is a tool that enhances agent capabilities by offering integrations and apps, such as Google Calendar integration. MCP (Model Context Protocol) is a way to share context with models and extend their capabilities. It allows functions to be made available to models over standard input/output or an HTTP endpoint. MCP can be used with GitHub to perform various tasks like searching and fixing code issues. The Talk covered the basics of AI agents, building agents with Langflow and enhancing them with Composio, and using MCP with GitHub. The speaker encouraged audience questions and exploration of these concepts.

1. Introduction to AI Agents

Short description:

I'm Tejas Kumar, and I've been building on the web for over 20 years at places like Brasel, Spotify, Zeta, and more. Let's just define what an agent even is. An agent is someone who acts. Let's take a look at another definition called agency. These words are important as we discuss agents, because that's fundamental to understanding AI agents. What is an AI agent? It's when an AI acts on behalf of you or a group or takes an active role or produces a specified effect. Large language models or neural networks simulate our brains, our neural networks. If a human brain has agency to choose tools, so does a language model or an LLM. What is agency? It's the ability to choose a tool to achieve an outcome or producing a particular effect. Now let's zero in on the agency definition in the context of language models.

I'm Tejas Kumar, and I've been building on the web for over 20 years at places like Brasel, Spotify, Zeta, and more. And a lot of this building has been enabled by AI agents. This was the big trending topic in 2025, AI agents. So in our time together today, let's talk about agents, and let's talk about it assuming zero knowledge, and go from there.

To begin with, let's just define what an agent even is. And to do that, we can just go on Google and type define agent, right? And so what we see is it's a person who acts on behalf of another person or group, a person or thing that takes an active role and or produces a specified effect. And so what we can see is an agent is someone who acts. That's literally the thing. Either here in the first definition, acts on behalf or takes an active role. Let's take a look at another definition while we're here called agency. And this is interesting because it's a noun, which is a business or organization providing a particular service on behalf of another person like a travel agent or something. Or the second one, action or intervention by producing a particular effect. And so these words are important as we discuss agents, because that's fundamental to understanding AI agents. So it notice it says a business or person previously. And when we take these definitions and apply them to AI, we get AI agents. So what is an AI agent? It's when an AI acts on behalf of you or a group or some or when an AI takes an active role or produces a specified effect.

Agency, if we look at that other definition, if we look at agency, it says a business or organization providing a particular service, or this one, action or intervention by producing a particular effect. Canals carved by the agency of the water. There's more definitions here, which we can get into the etymology and all of this. But one of the definitions of agency is also just free will or freedom to choose. For example, if you ask me to multiply two very large prime numbers, I could, using my agency, try to do it in my head, probably get it wrong, or using my agency, pick a tool to use like the calculator and get it right. So tool use and choosing the tool is a tenet of an agent, either human AI or otherwise or business. And so that's like agent 101. What does this mean for AI? Basically the same thing. Large language models or neural networks are algorithms that simulate our brains, our neural networks. They're literally the representation of a human brain. So if a human brain has agency to choose tools, so does a language model or an LLM, because it's ultimately just a neural network, a transformer based neural network, if you're interested. And so I hope that becomes clear. So what is agency? It's the ability to choose a tool to achieve an outcome or, in the case of this slide, producing a particular effect. Now let's zero in on the agency definition in the context of language models.

2. Agent Components and Tool Usage

Short description:

There's this great paper by Google published October of 2024, Agents, by Julia Wiesinger, Patrick Marlow and Vladimir Vuskovich. This ultimately is an agent. It is a runtime that contains three components, an orchestration layer, a model, usually a language model, and tools. Tools are nothing more than functions. Language models can generate structured output, which is JSON. Language models use tools by generating JSON output. For example, a language model can generate a tool called JSON object with arguments like the city. The application that consumes this output would then call the corresponding function in the orchestration layer.

There's this great paper by Google published October of 2024, Agents, by Julia Wiesinger, Patrick Marlow and Vladimir Vuskovich. And this paper goes on to outline, excuse me, it was September 2024. The paper goes on to outline what is an agent. And if we go to that section, there's some text and a diagram. This ultimately is an agent. It is a runtime that contains three components, an orchestration layer where things are, well, orchestrated or organized, a model, usually a language model and tools.

I think if we've had any exposure at all to something like chatGPT, we know what a language model is. We don't need to go into detail about that. But let's talk about tools and then the orchestration layer. Tools are nothing more than functions. That's how they're represented in the AI agent landscape. They're functions. And so some might think that a language model can call functions. That's not true. Language models can generate structured output. Because what is structured output? It's just language. It's JSON. And so how language models use tools is by generating JSON output.

Let me show you. So if we come to TL draw and just create our slides interactively, you can say, let's say the user is you and you say get the weather to the language model. A language model can then either say, I can't, right? If it can't. Or the language model will generate you a tool called JSON object. So it might generate you something like this. Tool name is get weather. And then args is complete. It's an array of arguments that's completely generated. And of course, args would be the city, for example. And then your application that consumes this output would read this. And then an application code or in the orchestration layer, you would do this. You would call get weather with Berlin, right? And then whatever the response is would go back to the LLM.

3. Building Your Own AI Agent with Langflow

Short description:

So LLM generates structured output connected to your orchestration layer or application. The agent runtime consists of a language model, tools represented as JSON functions, and the orchestration layer. If you want to build your own AI agent, Langflow is an open source diagramming tool that helps you understand the process. You start with an agent and choose a language model. Then provide an API key, instructions, and connect tools like URL browsing and a calculator. Finally, input and output are piped through the agent.

So LLM would say, you know, you got weather like 20 degrees, whatever. And then the LLM would turn that into a response to you. This is how tool calling works. They're just really good at generating structured output. And so that structured output is connected to your orchestration layer or your application here. This is how it works.

So as we can see, even here, that diagram comes to life. Let's open it in split view. And what we can see is this is the diagram where you have a language model. That's our language model. You have tools, which is nothing more than a JSON representing a function and an actual function, and the orchestration layer, which is our application that calls this. Fundamentally, this is how it works. And this here, what we have here is the agent runtime. That's really it.

But let's make it a little bit more practical. Say you wanted to build your own AI agent. How would you do that? Well, if you go to Langflow.new, this is something that I built at Datastacks. Langflow is an open source diagramming tool that helps you really understand things. So if we come here, and immediately, as soon as we log into Langflow.new, we see something like this, which is a basic agent. It's literally called a simple agent. And so how does this work?

Well, at the center of it is an agent, where you have a model provider to give us the language model, of course, and you choose the model you want. You then give it an API key and you give it some instructions and you connect tools. Okay, what tools are available to us? Well, we have a URL, so it can browse the web. It can literally just access things on the internet. And a calculator, just in case you want to do some math. So these are the two tools available to it. Finally, we take the chat input and pipe it in, and we take its response and pipe it to chat output. This is a really basic agent. So let's try and use it. And I'll give you a word of caution here, my API key may not be valid, but let's just do this together.

4. Converting Euros to Indian Rupees

Short description:

So convert 200 Euros to Indian Rupees and see what happens when the agent runs the code. By accessing URL fetch content and performing calculations, the agent determines that 200 Euros is approximately 18,280 Indian Rupees. However, without the necessary tools, such as the URL tool, the agent may not be able to provide accurate results. Removing the calculator tool further limits the agent's capability to perform conversions.

So convert 200 Euros to Indian Rupees. And so we'll see what happens when the agent runs the code. Okay, yeah, my API key doesn't work. But it's okay, we'll just put a new one in there. So it should be here. Let me just quickly get it. And again, this API key will be revoked, so no worries.

Okay, that's it. So now, let's go and try it again. Convert 200 Euros to Indian Rupees. And so look, it's accessing URL fetch content. It did a bunch of stuff. Look at this. It said, it got the exchange rate using the URL tool, and got it again, and then did some math. And says, finally, therefore 200 Euros is approximately 18,280 Indian Rupees. Of course this is important, because the exchange rate changes regularly. And if you don't have the tools, it's not gonna work.

For example, let's use maybe a cheaper model. And let's get rid of the URL tool. I just cut that line. Let's open a new chat and do it again. 200 Euros to Indian Rupees. And it's probably going to say, I don't know how to do that. So it has the calculator. But notice it's wrong. 17,700, because it just has a calculator tool, and it just came up, it hallucinated an exchange rate. What if we remove the calculator tool? Try it again in a new chat. Convert 200 Indian Rupees to, or excuse me, 200 Euros to Indian Rupees. And now it's just gonna probably fail. It gets the date.

5. Enhancing AI Agent Productivity with Composio

Short description:

To convert 200 Euros to Rupees, you need to provide the agent with more tools. The agent consists of a language model, an orchestration layer like Langflow, and various tools. Batok promised to increase productivity using AI agents. One way to achieve this is by making the agent more personalized for both developers and regular users. Composio is a great tool that offers integrations and apps to enhance agent capabilities, such as Google Calendar integration.

The current date and time in Europe is this. To convert 200 Euros to Rupees, you need, yeah, so they get more capable when you give them more tools. And this is how an agent works. And again, we see that diagram, right? You have a language model. You've got the orchestration layer, in this case, which is Langflow. And you've got tools. And Langflow is the thing that's getting the structured JSON output and binding it together.

Okay, this is cool. But Batok promised using AI agents to increase your productivity. And how might you do that? How might we make this personal? Like, this is cool for like a URL and so on. But how might we make this personal? And I want to answer this question really in two ways. One, how to make it more productive for you as a developer. And two, how to make it more productive for you just as a regular human being. We'll start with as a regular human being, which developers are also regular human beings. Don't come for me.

There's a great product and tool called Composio. I have no financial relationship at all to Composio, but I think they're doing great stuff. They're making tools for agents. Let's go check it out. So if I go to composio.dev and sign in, what I get is my dashboard. And there's a bunch of things here, but what's really cool is they have integrations and apps. So I'm going to go here to all apps, and it's going to get a bunch of tools. And these are the things that I can use agentically. Google Drive, and Slack, Perplexity. There's lots of things that I can use, or my LLM can use as an agent. And it just goes on and on. Let's go and use Google Calendar agentically because I want a calendar agent. So I'll come here, and I'm going to set up the Google Calendar integration. And how I'm going to set that up is by logging in to my Google account. So I'm going to connect default Google Calendar.

6. Setting up Composio with Langflow

Short description:

To enhance agent productivity, you can set up Composio to use your Google Calendar in Langflow. By getting an API key from Composio and pasting it into Langflow, you can authenticate and access various actions for your agent, such as quick add, finding events, finding free spots, creating events, and listing calendars.

That's my default user ID. That's my user in Composio. And I'm going to sign in to my DataStax calendar. And of course, I'm going to give it permission. So that's it. It has permission. So now, my Composio application is set up to use my Google Calendar. I can go use this in Langflow. So I'm going to get an API key from Composio, just like this, and I'm going to come to Langflow. The same Langflow.new. And I'm going to go to Composio here on the left side. Composio Tools. Grab this. I'm going to paste in my API key, and refresh. And this is now going to go to Composio and be like, hey, what apps does he have? So I have a bunch of apps. I want the Google Calendar one. This here. And now it's going to check, am I authenticated? Am I not? Once it knows that I'm authenticated, I just refresh this. Once it knows that I'm authenticated, it will give me actions that my agent can perform. For example, do I want to be able to delete events with my agent? Probably not. I want a quick add. I want to get the current date and time. Sure. I want to update events. I want to, actually, I don't want to update events. It's a bit mutative. I want to find events. I want to find free spots. And I want to create events. And I want to list calendars.

7. Using Tools and Checking Schedule

Short description:

I want to do all these things, so I'm going to plug them into my tools. By connecting the tool to my Google Calendar, I can check my schedule for today and this week. It's using Composio and it shows that I have no meetings scheduled for today. I'm also able to find all my events for this week and inspect them. Although it mistakenly shows an all hands event in 2023, there's a tool called Current date that can be used to fix this. Let's try again and see what my meetings are for today.

So I want to do all these things. So now I'm going to plug this in here to my tools. And let's maybe use a smarter model.

That's it. I've added this tool, and it's connected to my Google Calendar. So if I go back here, and I'm like, what are my meetings for today? It may or may not. So it's using Composio. Look at that. You have no meeting schedule for today. Awesome.

And now I'm going to say, how many hours am I spending in meetings this week? And this is quite basic, of course. But it gets even better. And I can't wait to show you. So it's finding all my events this week. And you can actually inspect. There you go. So these are all my, I do have an all hands. But that's 2023. So it doesn't know the current date, for some reason. But I think there's a tool here. Current date. Look at that. Does this have tool? It has tool mode. So I'm going to turn it into tool mode. Plug it in. And let's try again. Why not? So let's go and say, what are my meetings for today? In a new chat. I love live coding with you here. And again, it may not work. Okay.

8. Conducting Experiments and Finding Free Slots

Short description:

So in March 2025, I conducted an experiment with a dummy date to test the tool. It successfully found all my meetings for that date, including one with my manager, Carter. But we can do even better. By getting the current date and time, we can find free slots and perform more actions. There's a lot happening behind the scenes.

So it is March. I don't know. Let's just do a dummy date, for example. March 4th, 2025. Just because I know it's in the past, and stuff happened. And we'll try this again.

And again, we can just add a tool here. But I want to show you something really awesome.

So it's finding events for March 4th, 2025. A date in the past where I know for sure what meetings happen. And these are all my meetings. That's absolutely true. Every one of these meetings is totally valid. And this is me and my manager, Carter. And it's great. So it totally works. But we can do even better. Right?

We can say, it's, again, we'll go back and use our fake date, 2025. We'll have it do this. And so, yeah, now we can see it's finding events. It's getting the current date and time. Finding free slots. And you can also just see the output here. Whoa. There's a lot of stuff. And so there you go. Executed, create. It's doing a lot. So I'm just going to go and collapse this chat here. There you go.

9. Meeting with Melissa Herrera

Short description:

I had a meeting with Melissa Herrera scheduled for March 11th at 935 PST. Although the location was not provided, I was able to view the event on Google Calendar. Upon checking my work calendar, I found that the meeting had been completely booked by my AI assistant. It was a great experience and a testament to the power of creating your own agent using Langflow.

Meeting with Melissa Herrera. I said it's March 4th. So next week is March 11th. 935 PST, her time. Location, unfortunately, isn't an actual location. But you can view the event on Google Calendar here. Let's go check.

I'm going to click on it. And it says busy. But that's my personal calendar. Let's go look at it in my work calendar. March. It's supposed to be here. Wait, let's take a look. Wait, what did it say? This was for March 11th. Let's check. March 11th. Meeting with Melissa Herrera. Boom. This was completely booked by my AI assistant. A decent location in SF. Absolutely bananas. Absolutely bananas. That is the coolest thing. That's how you can create. Yes, I'm going to delete this. That's how you can create an agent for yourself. Absolutely bananas. And it's Langflow. And we just did it here.

10. Langflow and Model Context Protocol

Short description:

Langflow is an open-source tool that allows you to host it yourself. It provides a web API that can be accessed from any front end or client. Additionally, I want to introduce you to MCP, or Model Context Protocol, which is a way of sharing context with your models. MCP allows functions to be made available to models over standard input/output or an HTTP endpoint. It's a powerful tool that extends the capabilities of any model. Let's dive into coding to see how it works. And don't worry, we'll address the concerns about job security as well.

Langflow is open source. You can host it yourself. Do not share your API keys in Langflow.new. It's just for prototyping, kind of like we're doing.

Let's wrap up Langflow. And then I want to show you some more stuff. So if you click on API, this entire flow, using your tools, using all of it, becomes accessible over a web API, over HTTP. And then you can call it from any front end, any client. React Native, whatever you want. You can just use your assistant as yourself, as your agent. Very cool.

Finally, I want to spend some time talking to you about something called MCP. That's called Model Context Protocol, MCP. Let's go over here and change the slide. MCP, Model Context Protocol. Now, if this was in person, I would ask you, like, hey, has anyone heard of this? Is anyone using this? I can't do that. But maybe you can react on the video or something. What is this? It's a way of sharing context with your models. Remember we said function calls are like this, right? MCP is a protocol that makes functions available to models over either standard input output or over an HTTP endpoint. Any model can be extended using Model Context Protocol. It is so cool. And I'd love to show you this as well. But the way I'm going to show you this is through coding. Some of you are, you keep asking the question, like, hey, am I going to still have a job? Is the machine is going to take my job and whatever?

Let's find out. So Model Context, there are many, many, many MCP servers by many, many, many vendors. There's like GitHub and Slack and basically anything that has an API can be exposed over MCP. And so what we're going to do is using the GitHub MCP server, just find an open source issue as me, solve it and open a PR, just fully autonomously with an agent. To do that, first, we need a GitHub personal access token. So come with me to GitHub and let's make one. I will revoke this after this session.

11. Using Model Context Protocol with GitHub

Short description:

To work with Model Context Protocol, you can use NPX to open the MCP server in the terminal. Additionally, you need a client like cursor, which is an IDE client that uses MCP. By adding the GitHub MCP server to cursor and providing the GitHub personal access token, you can communicate with the server and perform various tasks.

So you're not going to be able to pretend to be me on GitHub and we'll, yeah, let's delete this one. And I'll make a new one, a new token with, yeah, okay. With repo scopes, so repo, and I'll call it my agent. Well, pretend you didn't see that. My agent and we'll save the token. And now I'm going to get it.

Great, please don't copy this. And now, where do I plug it in? Well, there is, how you work with Model Context protocol is really just over NPX. It all works locally. And so you could just, whoa, you could just NPX-Y like this. NPX-Y Model Context Protocol slash server GitHub. Just run that and it'll open MCP server just like that in the terminal. Absolutely bananas. But what is this actually doing?

Well, you need a client for this. And so let's go use a client cursor. Some of you may have heard of this IDE cursor. It's a really great client that uses MCP. So let's open cursor and let's just like close the side, but let's close everything and go to cursor settings. We come here to the full settings. And what we're going to do is go to features and here we have MCP servers. There's no MCP servers, but I can add one. And there's SSE or command as I mentioned, we choose command and we'll say this is the GitHub one. So what I'm going to do is env GitHub personal a access token equals, and I'm just going to copy my token from here. And again, you can't use this. And then we'll say that NPX command. And we're just going to run this inside of cursor as we add a new MCP server. That's kind of annoying that it dismissed the modal, but server name GitHub, is it going to dismiss the modal again if I go get my, okay, cool. And we'll say env GitHub personal access token equals this and run NPX, that's it. And so now it's calling it and look, it knows, it speaks MCP. And so it can do all these things.

12. Exploring MCP Server Capabilities

Short description:

Using the MCP server, you can perform various tasks like finding open issues and contributing to popular repositories. If the conversation becomes too long, try creating a new one or shortening the messages. Let's explore the SolidJS repository.

It has all these tools now, create or update file search repositories, create repository, et cetera. So cool. So now using this MCP server, I can go to the agent composer, the cursor composer here, is going to create a new chat, right? And I can do literally anything. I can be like find a trivial open issue in Facebook slash react and open a PR fixing it. I can literally do this and I can choose agent mode. But let's maybe find a smaller repository that I maybe haven't contributed to react, but let's go on GitHub and just like find even better. Let's just find a trivial issue open in a trending popular GitHub TypeScript. Actually not even TypeScript repository. Let's go bananas here, repository, right? And so it's going to even find the thing. This is full agentic flow. And so I submit and it's just gonna look at this, calling MCP tool search repositories. And it's searched some repositories. Now let's look for an open issue in one of these popular repositories. I'll check the pretty repository.

Cool. I'd love to contribute to prettier. What happened? Your conversation is too long. Please try creating or shortening your messages. Okay. Let's make a new conversation. It apparently found like big messages or something, but I can just do it again. It's doing prettier again, but maybe this again becomes too big. So list issues maybe gets too many issues, you know? Yeah, okay. That's the problem. So let's do another one. Let's do in a, let's give it a repository. SolidJS slash solid or something. There we go. It even knows in the solid JS repository, that's wild. And let's see what happens.

13. Exploring Different Models and Fixing Issues

Short description:

Let's choose a different model with a different token length. The SolidJS repository has some open issues, including one that shows a string undefined. We can proceed to fix this issue by checking for undefined. The process involves forking the repo, cloning it, and running the necessary commands to search and grep the code base.

Even here, my conversation is too long. Let's just choose a different model with a different token length.

Great. Plod 3.5 is so much better than 3.7, isn't it? So it's listing issues. Conversations again, too long. Let's go use OpenAI maybe. GPD 4 mini. I guess you could use unsupported model. You could use Gemini that has a larger context window, and there's also cursor settings that, it's a beta feature, but it allows large context.

Okay, look at this. So some open issues in SolidJS. Issue 1041. Shows string undefined. Past previous node, whatever. The first issue seems like a straightforward bug that could be addressed by checking for undefined. Would you like to proceed? Proceed. And now it's gonna just fix the issue. Absolutely. It might fork the repo, because it has my personal, look at this, it's forking the repo. As me, wild. There, I successfully forked it. Now you're gonna clone the, whoa, whoa, whoa, just like cloning stuff. And now it's CDing, and it's literally just running these, my hands are free, yeah? It's just like running this. It's grepping the code base, it's searching the code base. Wild. So it's just full agent mode. That's crazy. And so we can just watch this code and take my job. I might fast forward this, but we'll see. That is wild.

14. Using MCP to Search and Fix Code Issues on GitHub

Short description:

I can use MCP on GitHub to search and fix code issues. I recently found and fixed a TypeScript issue in the lengthflow.ai/lengthflow repository. The process involved searching the repository, forking it, retrieving file contents, and creating a pull request. The pull request, which mentioned issue 6263, was fully agentic, and it was a feature request by Rigo Lepe.

I can even say, just like stop, don't work with this locally, but do it all on GitHub. I can say that, because I don't wanna, look at this. It's amazing. So I can just have this use MCP all the way, and it's searching the code. Again, this is just a GitHub tool. It just keeps searching the code, so.

So cool. Let's read the section of the file where this is defined to understand how it works. All of this is just happening. This is just a GitHub. So anyway, let's go to a previous one. So I did this some time ago. And if we look at this, this is what happened. I said, go find a TypeScript issue in lengthflow.ai.slashlengthflow, and fix it. It searched the repository. It's forked the repository. It got the file contents multiple times. Searched issues. Found an issue and continued all the way using this MCP until it created a pull request. Wild.

And this pull request here has a pull request ID, so I can even go on this, which is lengthflow.ai.slashlengthflow at 6914, so I can go to github.com. I can even just come here and look at my recent activity. It's this one. And this whole PR, I did nothing. This was fully agentic. Just all of, I didn't do any of this. And then it even said, it mentioned the issue here, 6263. And this was a feature request by Rigo Lepe. I don't even know him. All of this was just as me.

15. Concluding Remarks and Next Steps

Short description:

We covered model context protocol, the agent runtime, and what an agent actually is. We also explored how to use it with Composio, Lengthflow, and Cursor. You just need an agent runtime, an orchestration layer, a model, and tools. Looking forward to answering your questions and seeing what you build!

It was fully agentically. And so it's absolutely wild. Okay, so here it's still working. And the talk has a time bound, unfortunately, but at the end of this, I'm going to have a SolidJS pull request that just exists. Absolutely wild.

Let's wrap up. So what did we cover? We covered a bunch of things. We covered model context protocol, which is available in Cursor and other agents. We've covered the actual agent runtime that is here, that is agent's paper. Yeah, it's this one. We covered what an agent actually is, provided we didn't know that before.

So there's a really cool diagram here. And we explored how we might use it with Composio and Lengthflow or in Cursor. Either way, you just need an agent runtime, an orchestration layer, a model and tools. Thanks so much for listening. I can't wait to answer your questions and see what you build with all this knowledge. Take care.

Check out more articles and videos

We constantly think of articles and videos that might spark Git people interest / skill us up or help building a stellar career

AI and Web Development: Hype or Reality
JSNation 2023JSNation 2023
24 min
AI and Web Development: Hype or Reality
Top Content
This talk explores the use of AI in web development, including tools like GitHub Copilot and Fig for CLI commands. AI can generate boilerplate code, provide context-aware solutions, and generate dummy data. It can also assist with CSS selectors and regexes, and be integrated into applications. AI is used to enhance the podcast experience by transcribing episodes and providing JSON data. The talk also discusses formatting AI output, crafting requests, and analyzing embeddings for similarity.
Atomic Deployment for JS Hipsters
DevOps.js Conf 2024DevOps.js Conf 2024
25 min
Atomic Deployment for JS Hipsters
This Talk discusses atomic deployment for JavaScript and TypeScript, focusing on automated deployment processes, Git hooks, and using hard links to copy changes. The speaker demonstrates setting up a bare repository, configuring deployment variables, and using the post-receive hook to push changes to production. They also cover environment setup, branch configuration, and the build process. The Talk concludes with tips on real use cases, webhooks, and wrapping the deployment process.
Effective Performance Testing to your Server with Autocannon
TestJS Summit 2021TestJS Summit 2021
36 min
Effective Performance Testing to your Server with Autocannon
Top Content
Tamar is an experienced code writer and architect with expertise in Node.js. Performance testing can be confusing, but understanding terms like throughput and the 99th percentile is crucial. The 99th percentile is important for making commitments and ensuring customer satisfaction. AutoCanon is a powerful tool for simulating requests and analyzing server performance. It can be installed globally or used as a library in Node.js. Autocannon is preferred over Gatling for performance testing and can be integrated with end-to-end tests in Cypress.
Forget Bad Code, Focus on the System
React Summit US 2023React Summit US 2023
27 min
Forget Bad Code, Focus on the System
Top ContentPremium
Watch video: Forget Bad Code, Focus on the System
Setting up the system and separating concerns are important in software development. Modular construction and prefab units are a new trend that makes construction quicker and easier. Architectural complexity can lead to a drop in productivity and an increase in defects. Measuring architectural complexity can help identify natural modules in the code. Best practices for avoiding architectural complexity include organizing code by business domain and using prop drilling. Atomic design and organizing a monorepo are recommended approaches for managing architectural complexity.
Delightful Integration Tests With Testcontainers
TestJS Summit 2022TestJS Summit 2022
21 min
Delightful Integration Tests With Testcontainers
Top Content
Testing is crucial for development and production, with integration tests becoming more popular. Test containers is a library that integrates with Docker to create reliable test environments. It is flexible and can be used with various frameworks and test libraries. The IDE setup involves configuring the container and connecting it to the application. Test containers can be used for complex operations and allows running tests with real dependencies.
Confessions from an Impostor
JSNation 2022JSNation 2022
46 min
Confessions from an Impostor
Top Content
The Talk discusses imposter syndrome and reframes it as being a professional imposter. It emphasizes the importance of sharing and starting, embracing imposterism, and building inclusively for the web. The speaker shares personal experiences of being an imposter in various technical disciplines and highlights the significance of accessibility. The Talk concludes with the idea of building a collective RPG game to remove excuses for not making things accessible.

Workshops on related topic

Automated accessibility testing with jest-axe and Lighthouse CI
TestJS Summit 2021TestJS Summit 2021
85 min
Automated accessibility testing with jest-axe and Lighthouse CI
Workshop
Bonnie Schulkin
Bonnie Schulkin
Do your automated tests include a11y checks? This workshop will cover how to get started with jest-axe to detect code-based accessibility violations, and Lighthouse CI to validate the accessibility of fully rendered pages. No amount of automated tests can replace manual accessibility testing, but these checks will make sure that your manual testers aren't doing more work than they need to.
Utilising Zapier's Built-in AI Capabilities and AI Tool Integrations
Productivity Conf - Practical AI in MarketingProductivity Conf - Practical AI in Marketing
57 min
Utilising Zapier's Built-in AI Capabilities and AI Tool Integrations
WorkshopFree
Kelly Goss
Kelly Goss
How to supercharge your no-code automation building and reduce build time with Zapier's latest AI features and functionality. I'll also cover AI tools that natively integrate with Zapier to bring a whole new level to productivity.
Automated Testing Using WebdriverIO
TestJS Summit 2022TestJS Summit 2022
163 min
Automated Testing Using WebdriverIO
Workshop
Kevin Lamping
Kevin Lamping
In this workshop, I cover not only what WebdriverIO can do, but also how you'll be using it day-to-day. I've built the exercises around real-world scenarios that demonstrate how you would actually set things up. It's not just "what to do," but specifically "how to get there." We'll cover the fundamentals of Automated UI testing so you can write maintainable, useful tests for your website and/or web app.
How to Create a Web Application in an (Almost) Autonomous Way Using Clean Coder
Productivity Conf for Devs and Tech LeadersProductivity Conf for Devs and Tech Leaders
95 min
How to Create a Web Application in an (Almost) Autonomous Way Using Clean Coder
Workshop
Grigorij Dudnik
Grigorij Dudnik
Imagine replacing yourself with a multi-agent AI programmer to develop your production web application. That's exactly what we did at my startup takzyli.pl. To achieve this, we designed and used the Clean Coder - AI agent framework for autonomous code writing (https://github.com/GregorD1A1/Clean-Coder-AI), which is hopefully open-source project. If it worked for us, why shouldn't it work for you?In this workshop, I'll show you how to create an entire web application in an (almost) autonomous way and drastically reduce the time you or your employees spend on writing code.
Test, Code, Repeat: Mastering AI-Assisted Development
Productivity Conf for Devs and Tech LeadersProductivity Conf for Devs and Tech Leaders
53 min
Test, Code, Repeat: Mastering AI-Assisted Development
Workshop
Marco Pierobon
Marco Pierobon
"Test, Code, Repeat: Master AI-Assisted Development" introduces developers to a transformative way of coding with AI as a collaborative partner. This workshop focuses on how iterative workflows, such as the ping pong pairing technique, enable an enhanced interaction between human creativity and AI efficiency. 
JS Security Testing Automation for Developers on Every Build
TestJS Summit 2021TestJS Summit 2021
111 min
JS Security Testing Automation for Developers on Every Build
Workshop
Oliver Moradov
Bar Hofesh
2 authors
As a developer, you need to deliver fast, and you simply don't have the time to constantly think about security. Still, if something goes wrong it's your job to fix it, but security testing blocks your automation, creates bottlenecks and just delays releases...but it doesn't have to...

NeuraLegion's developer-first Dynamic Application Security Testing (DAST) scanner enables developers to detect, prioritise and remediate security issues EARLY, on every commit, with NO false positives/alerts, without slowing you down.

Join this workshop to learn different ways developers can access Nexploit & start scanning without leaving the terminal!

We will be going through the set up end-to-end, whilst setting up a pipeline, running security tests and looking at the results.

Table of contents:
- What developer-first DAST (Dynamic Application Security Testing) actually is and how it works
- See where and how a modern, accurate dev-first DAST fits in the CI/CD
- Integrate NeuraLegion's Nexploit scanner with GitHub Actions
- Understand how modern applications, APIs and authentication mechanisms can be tested
- Fork a repo, set up a pipeline, run security tests and look at the results