David Gaynor and Patrick Coleman

Build an app with ChatGPT

Andela

Replit

PeopleGrove

David Gaynor

Engineer and exited founder, ex Andela and Twitter

Patrick Coleman

Former first business hire and early leader at Replit and PeopleGrove

Discover ways to use AI tools from ideation to coding to content

How we built our language learning startup Yaya

A hands-on demo of using the ChatGPT API to build an app

Working with the ChatGPT API

Talk to users early, iterate quickly, and don't overbuild

Mistakes to avoid

🟢 WHAT WILL I BE ABLE TO BUILD IN THIS COURSE?You’ll build a functional application powered by LLM agents to automate a workflow of your choice. Along the way, you'll learn to design agent workflows, and integrate required tools. By the end of the course, you'll have a working MVP ready to showcase in a public demo. You can see this playlist for examples of what previous students built: https://tinyurl.com/llm-agent-demos 🟢 HOW WILL YOU HELP ME BUILD APPS LIKE THESE IN JUST 7 WEEKS?This course is all about learning by doing. You do a real project, applying concepts you learn about AI agents with our expert guidance. Specifically:👨🏽‍🏫 1:1 sessions with the instructors to help you think through bigger picture questions👨‍🎓 Async and sync sessions with a dedicated TA for constant support, code reviews, and real-time feedback To help you prepare, we have also curated 70+ hours of content, a "Learning Path" covering everything from product design and coding fundamentals to advanced LLM engineering concepts that you can consume at your own pace, as soon as you sign up. (see the next question for details) 🟢 OK! THAT DOES SOUND FUN, BUT HOW DO I KNOW IF I HAVE THE RRE-REQUISITES AND I'M READY FOR BUILDING?That's the most common question we get! The "Learning Path" we have curated should also give you a good sense of what knowledge we assume as pre-reqs. You should get started on that and then sign up for the course as soon as you feel you are ready:https://maven.com/p/bafd83/llm-agents-learning-path 🟢 I SEE! SO, I'LL DO MY PREP BEFOREHAND, THEN WHAT SHOULD I EXPECT TO HAPPEN DURING?Think about it like this (since we're developing a product here, eh?): This is a 3-sprint product dev + 1 week of prep for the public demo.🖌️ SPRINT 1 - DESIGN (weeks 1 &amp; 2)🔨 SPRINT 2 - DEVELOP (weeks 3 &amp; 4)🚢 SPRINT 3 - DEPLOY (weeks 5 &amp; 6)🎭 PUBLIC DEMO (week 7)In each sprint, you communicate your progress or blockers on Slack, you collaborate on your designs / code on GitHub, you show up to provide weekly project updates and get feedback, and finally you do an end of sprint demo. 🟢 OK! HOW WOULD I KNOW IF I'M MOVING IN THE RIGHT DIRECTION?You will get feedback async via Slack and other platforms we use, and also you join weekly group office hours, and when you need you can book the teaching staff for a 20 min 1:1 call. In addition, each sprint will wrap up with a "sprint demo" where you can show what you've done up to that point, and your peers and the teaching staff will provide feedback. We also will invite guest experts for each of the demos to provide additional feedback:🖌️ SPRINT 1 - Sr. AI Product Experts🔨 SPRINT 2 - Sr. ML Engineers🚢 SPRINT 3 - Sr. MLOps Engineers🎭 PUBLIC DEMO - Investors, Experienced Founders, Corporate Directors 🟢 WHAT IF I DON'T HAVE A PROJECT IDEA?We will have a default project (most probably related to automating data science work) that you can participate in. If your goal is to better internalize the concepts rather than working on a specific idea, you can join that project. We commonly see that people re-take the course in the future to further develop specific ideas they have, and focus on building the foundations the first time they take the course. 🟢 COOL! I'M EXCITED TO GET STARTED, AND A DISCOUNT WOULD REALLY SWEETEN THE DEAL!Glad to hear that! There are a few options:🧑🏿‍🤝‍🧑🏼 You can find a buddy or colleague and sign up together. (20% off 2-9 seats&nbsp;|&nbsp;25% off 10+ seats)✴️ We often share discount codes with communities (including AISC members - reach out to community@ai.science if you're not part of our slack). So, check in with the communities you are part of.📆 We regularly hold events and info sessions where we share flash sales discounts valid for a day or two. Join the mailing list on this page to receive notifications about those.

Mentorship Program to Help You Build an Agent-based MVP

Provide a brief description for each module as a way to sell the value of what students will be learning throughout the course.

First Module

Second Module

Third Module

Course syllabus

We will have group discussions and guests lecturers on Thursdays, and project office hours on Sundays.

Thursdays & Sundays

Course will run for 7 weeks in January and February. You will have access to reading / watching material, instructor, and hands-on teaching assistants.

Jan. 13, 2025 - Mar. 1, 2025

There will be a project that you will do alongside the course material with weekly milestones.

Weekly projects

Course schedule

You want to build an agentic MVP to demonstrate your skills for career progression purposes.

You want to build an agentic MVP to test the feasibility of your startup idea.

You want to build an agentic MVP to explore the new feature you want to add to your existing product

This course is for you if...

At the end of this course you will ...

Grasp how multiple LLMs can collaborate with each other, get feedback from or assign tasks to humans, ad use tools to tackle complex problems

Understand the core principles of multi-agent LLM systems

Bridge the gap by crafting strategies to seamlessly integrate LLMs with existing products, boosting user experience, productivity, and business metrics.

Integrate LLMs with existing product offerings to enhance user and customer experience

Learn what it takes to build robust multi-agent LLMs. Understand security best practices and ensure system reliability.

Understand key considerations for securing, robust, and reliable LLM systems

Design, develop, deploy, and demo an LLM agent application in 7 weeks!

Amir Feizpour, PhD

10 yrs in NLP, Founder of AISC - Community of 5k AI devs and founders

Abhimanyu Anand

Cohort 2409

Cohort-2501

If you are :﻿✔️ An aspiring entrepreneur who wants to build a world class technology product✔️ An existing founder who wants to maximize their runway✔️ A startup founder who is building a tech startup but lacks technical background✔️ A startup founder who wants to explore outsourcing This is the single most valuable resource for you. In my career spanning 17+ years I have been fortunate to have played the role of a startup founder who wants to build his MVP as well as of a technology consultant who works with startup founders to help them bring their startup dream to fruition. I have used this unique mix of experience from both sides of the table to assist multiple startups successfully traverse their 0 to 10 startup journey. I have now distilled all of this experience in to a concise and actionable learnings in the form of this course. This course is specifically built keeping in mind the needs of a new startup founder who if bogged down with huge amount of content telling them the theory of building their startup and MVP but does not provide them the tools and actionable items which they can start using immediately. Once you have completed this course you would have learned how to : 🏆 Clearly define a truly lean and minimal MVP.🏆 Get feedback from your ideal customer profile without needing to write a single like of code.🏆 Take key technical decisions about your product which have the potential to make-or-break your startup.🏆 A framework to identify the correct partners for you, be it hires or outsourcing agencies.🏆 Avoid common mistakes/gotchas that could end up as a huge drain of your time, money and effort.🏆 Have complete ownership over your IP while working with multiple third parties🏆 Actionable checklists, frameworks, templates and references to jumpstart your startup journey. I want you to immediately get to work towards building your startup MVP as soon as you finish this course. That is the guiding principal of how this course has been designed.

Jumpstart your startup journey by building your MVP the right way. 

The course will be conducted over a span of 2 days with 4 hours sessions on both the days.

Thursday and Friday

The next cohort goes live on Oct 3rd 2024 and will start at 8:AM EST

Oct 3, 2024

We will practice all that we learn, as we learn, in the form of a do-along case study. In this we take existing popular, complex startup product and go through the complete journey of building the MVP together.

Do-Along Case Study

Aspiring entrepreneurs who want to build a technology product by do not know where to start.

Existing startup founders, bootstrapped or funded, who want to maximize their runway.

Non technical founders who want to build, manage and scale a successful technology product.

Dreamers who are planning to build their startup soon.

Who is this course for

What you’ll get out of this course

This course is much more than explanation of concepts and dos and donts. My goal is to equip you with tools that you can start using the very same day to start building your dream startup. I will provide you with actionable checklists, frameworks, legal templates and contacts.

Get actionable checklists, frameworks, legal templates and references to supercharge their startup product building journey

What used to take weeks can now be done in days (any many times hours) using the powers of GenAI. I will tell you how you can use AI tools to significantly speed up your MVP development without breaking the bank

Use GenAI to significantly speed up all aspects of MVP development

You will not have to wait for the final MVP to be built before you can get feedback from your target customers. I will teach you how you can build prototypes quickly so that you can collect valuable feedback quicker and course correct faster. Without writing a single line of code

Learn to get feedback on your idea without spending a single dollar on development

Converting ideas in your mind to actionable specs is an art that I have perfected over the last 17 years. I will teach how you too can build specs that are extremely cost and time efficient and will be loved by your designers, developers, contractors and you.

Convert ideas to actionable specs faster without ambiguity. Specs that your developers and partners will love.

A new founders journey is full of decisions, all of which can make or break the startup. I will teach you the framework using which you will maneuver decisions like which contractors to choose and how to hire your team making sure that you do not lose valuable resources and time.

Learn to Identify the correct partners to build your startup. Make informed decision on whether to hire devs or find agency.

Working with others is hard. Its even more challenging when you are a new fonder with not enough time and funding. I will simplify and codify the process for you so that you can ensure a smooth working relationship with partners while maintaining complete indemnity and onwership

Learn to avoid the common pitfalls when working with third parties, safeguard your IP and avoid unnecessary hiccups in your startup journey

MVP is just the beginning. You want to build a product that will scale with time as you grow. Something that will make prospective investors comfortable when choosing to invest.

Build a scalable and investable business.

I will teach you how you can maximize your capital efficiency by simply tweaking some product development decisions and significantly improve your runway. This is even more crucial if you are a bootstrapped founder.

Increase your runway significantly

Leverage GenAI to fulfil your startup dream by learning to validate your idea, translate idea to MVP & find right partners for your startup

Akhil Gupta

Cohort 2

Cohort 3

People who can code get farther in life by solving problems with software. It is even more rare and impactful if your role is not as a developer but you can also code, for example a product manager who can code, a marketer who can code, or a sales person who can code, etc. The ability to code is a super power. These developer combos don't need to go talk to another developer in order to get something done, they can just make the thing themselves. Benefits for people who code: 1) Save time and money by building tools that automate tasks for themselves or others.2) Get promotions at work for technical contributions OR grow a business as an entrepreneur. So, why aren't you building your own software? Because learning to code is hard, and even if you know how to code, coding takes a long time. But, what if you didn't have to be the one to actually write the code? What if you could tell someone else what code to write and they did whatever you said (really fast) and never slept? This is exactly what AI can do. AI is now so good that it not only can help you code, it can even code for you. It's like having your own engineer who will build anything you want, at any hour of the day, and they just cost $20/month. What would you build if you knew how to do this? Knowing how to tell an AI to build software is the most high value skill you can learn today. Most people don't know how to do it, simply by learning a little bit you will already be one of the most skilled in the world. This course will teach you everything you need to know in order to build anything simply by telling the AI what to code. WHAT YOU WILL LEARN: - All of the tips and strategies- How to overcome issues and roadblocks- How to setup your developer environment- What AI to work with- How to build user sign in, save and pull data from a database, and integrate with services like OpenAI and Stripe- How to deploy your app for others to use WHAT YOU WILL BE ABLE TO BUILD: - Internal tools- An entire social network- AI apps- iPhone apps- Literally anything, no matter how complex or ambitious YOU SHOULD TAKE THIS COURSE IF: - You are excited to be able to build things- You are ok with getting frustrated WHY LEARN FROM ME: I have been building software since 2007 when I moved to Silicon Valley at age 19. I learned product management from Josh Elman, one of the most successful product managers in tech (LinkedIn, Facebook, Twitter, Robinhood, Apple). I've been working with AI specifically since 2016 as CEO of Octane AI, an AI company where we power AI for millions of people. I was one of the first people to get access to OpenAI's technology, years before ChatGPT was released. And more specifically... Over the past 90 days I have used AI to build at least one new app a day. I do speedruns where I see how much of an app I can build in 30 min, 60 min, etc. Just like going to the gym, but for coding with AI. I’ve also watched hours and hours of videos of developers screen sharing themselves building with AI, I’ve watched interviews with the founders of these AI tools where they give insights into their own tips and tricks, I’ve looked through forums, and chatted directly with anyone and everyone who is building this skill. Over the past three months I have gone&nbsp;very&nbsp;deep on learning everything there is to know about coding with AI. And I want as many people in the world to be able to do this too. Creating is just so fun and rewarding, my brain craves to create and coding with AI is one of the most amazing creative experiences. I’m here to deliver one very clear message to you:&nbsp;You can now build anything you ever wanted simply by telling an AI to build it for you. Social networks, cooking apps, iPhone apps, games, anything. ANYTHING. How does coding with AI work? What have people used AI to build? How exactly can you use AI to code an app? How can you copy my strategy for learning to code with AI? What does the future of coding with AI look like? I’m going to answer all of these questions for you in this course. I’m going to show you how to build an entire app. Yes you. Let’s do this.

Learn to Solve Problems With Your Own Software

Learn step by step how to start a new project, how to tell the AI what to code, and all the tips and strategies you need to build anything.

5+ Hours of Coding Lessons

Two one hour sessions a week for 3 weeks dedicated to Q&amp;A + Hands on trainings where we will code with AI together and get updates from all students on how their apps are progressing.

2x Weekly Live Coding + Q&A

You will work on your app outside of class as you learn to code with AI.

Weekly exercises and projects

Non-technical founders &amp; entrepreneurs&nbsp;who want to build their own MVPs quickly without depending on developers. Perfect for those with idea

Product Managers, Designers, Marketers, &amp; Business folks&nbsp;who want to increase their technical capabilities and build their own tools and pro

Engineers &amp; technical professionals&nbsp;looking to 10x their productivity by mastering AI-powered development workflows and tools.

It might sound intimidating, but you will learn to do this in your sleep.

How to setup your AI development environment, even if you've never coded before

This is an emerging skill and you will know all of the most current tips and strategies.

Real world tips and strategies for getting AI to code exactly what you want

You will make an actual app with NextJS, Tailwind, Supabase, and OpenAI. It will have signup/login, a database, and even AI.

You will successfully code an app, and you will be surprised at how fast you will be able to do it

You will be so good at coding with AI that you will be able to create apps and tools for work and personal use, and it will be just as easy as writing an email.

You will be able to solve problems with software

Hands on class where you will build any app you want, simply by telling AI what to do. No coding experience needed.

Matt Schlicht

Cohort 1

You're going to create an "Insights Extraction AI App" ("Unstructured Text Data" to "Structured Insights") using a modern stack of tools and AI engineering patterns An end-to-end deployed (live on the web) application that converts unstructured data (podcast, meeting notes, customer feedback, essays, etc.) and outputs structured insights (tweets, product descriptions, summaries, etc.). The goal is to build &amp; learn a flexible application structure so you can extend to your use case. Example applications you'll be able to extend this course's code to: Meeting "Next Steps" extractor, Podcast Summarizer, Customer Survey Trends Extractor, Extract class lessons from lectures, Data stream classifier, Custom apps with your own data AI Engineering Patterns we'll cover:* Prompting - The basic 3 step pattern for writing development prompts + optimizers, structured outputs* Observability - To manage costs, tracing and debugging* Retrieval/Chains - Adding more context to your LLMs and connecting multiple LLM calls together for a unified outcome* Model Choice - Tribal knowledge about when to pick certain models over another (spoiler: it depends on your use case)* Evals - The new style of unit tests for your LLM apps* Mindset - You'll learn how to approach novel problems with AI We promise three outcomes with this course:* You’ll launch an AI-powered app&nbsp;designed to teach you the foundations to build your own tools* You’ll surround yourself with a new&nbsp;group of friends:&nbsp;other builders who are as passionate as you (and hold you accountable)* You’ll 2x your likelihood to ship by experiencing first-hand the greatest trait a builder can have:&nbsp;a bias for action You'll get experience building with a modern AI powered development stack:* Cursor - Write code, but with ChatGPT by your side* v0 - Build user interfaces with words, not code* LLMs - Outsource intelligence to Large Language Models APIs like OpenAI/Anthropic* LangChain/LangSmith - Orchestrate and observe your LLM calls, ensuring your costs don't run out of control* Railway/Vercel - Deploy your apps* Supabase - Simple postgres database* Zapier - Simple ways to quickly integrate your application with other tools* Anthropic Artifacts - For prototyping mini applications "The best way to get good at something is usually to just practice actually doing the thing in question. A lot of very capable people outsmart themselves with complex plans that involve working a lot on fake prerequisites." - Sam Altman 10/27/2024 It’s no longer skill level that's holding you back, it’s just your desire to take a step forward. Along the journey, you’ll have access to mentors, successful builders that have built apps, a network of like-minded people, creative workshops, and 1:1 sessions. This program is a fast-paced, highly engaging program, but you don’t need to take time off work to participate. We’ve designed the program to be as flexible as possible for those who work full-time or have busy schedules. With that said, we encourage you to commit to&nbsp;at least&nbsp;4-5 hours of your spare time each week, for deep work, feedback groups, and live sessions. In addition to the course material, this cohort includes:* Code Templates - All materials shown in class will be available for download so you can continue to quickly build after the class* Slack - A channel for you to ask questions, connect with other builders, and get support on your projects* Guests - Each week we'll feature an expert from the industry to talk about AI Engineering This course is not:* Learn to be a programmer from scratch* Learn the absolute basics* Learn how to fine tune LLMs On the traditional SWE side, we will build our backend with Python and Postgres, frontend with Next.js, and deployed on Railway. Though this course is taught in python, you have the flexibility to bring whatever tool stack you're comfortable with. Who you are* You have a intermediate level understanding of Python + Javascript (React is a plus)* You're not afraid to roll up your sleeves and learn new technology* You value shipping something quick* You want to build AI-powered products* You're ready to break a big problem down into shippable chunks

Explore AI engineering patterns while building real systems

If your events are recurring and at the same time, it might be easiest to use a single line item to communicate your course schedule to students

Saturdays

We'll kick off the course in the new year

Jan 6, 2024

Each week will consistent of live instruction, video overviews, and "homework" (the fun kind) through practicing to build.

Scrappy Developers. You're a hands-on builder ready to turn your skills into real AI applications, even if development isn't your day job

Technical Leaders. CTOs and technical managers who are struggling to elevate the AI conversations with their teams

Experienced Developers. Software Engineers who want to build AI products but haven't dove into an AI focused tool stack yet

Become proficient in prompting, observability, chaining, model choice, structured outputs and scaling apps

Playbook of best practices for 5 areas of LLM development

You'll build your own tool which will start saving you time from Day 1. We'll walk through the steps of deploying your application on a custom domain (Ex: YourCoolAppYouBuilt.com)

A deployed "Insight Extraction" app live on the web

You'll gain hands-on experience with Cursor, v0, LLMs (OpenAI, Anthropic, Google), LangChain &amp; LangSmith, Railway/Vercel, Supabase, Zapier, and Anthropic's Artifacts

A survey of modern AI tools that will speed boost your workflow

We will run through step by step instructions on how to reduce the cost and latency of your LLM apps while maintaining (or even increasing) performance. This is critical to keep your LLM costs under control

Instructions to scale your LLM apps

Learn the key AI engineering patterns by building an app that extracts insights from unstructured text. Practical AI insights for developers

Lightning Lessons

Build an app with ChatGPT