Build AI Products with LLMs

There's a lot of magic surrounding LLMs, but it all starts with a prompt. This lesson will show you how to "talk" to a model correctly to solve business problems — not just chat for fun.

In this lesson:
→ What makes a good prompt and why it's not just text
→ How to improve your prompt accuracy: Few-shot Learning
→ What LLM temperature is and how to control it effectively
→ Case study: classifying customer support requests by topic

What it looks like in practice:
→ Learning to write, test, and refine prompts for specific tasks
→ Case study: replacing manual support request labeling with AI

LLMs can do more than hold a conversation — they can also return structured data that machines can understand. In this lesson, we learn how to turn natural language requests into valid JSON to automate actions within a product.

In this lesson:
→ Why models need structure and why JSON has become the standard
→ How to write a prompt that consistently produces the correct structure
→ What to choose: few-shots or explicit instructions?

What it looks like in practice:
→ Learning to use JSON schema to switch the model into developer mode
→ Case study: structuring a user's search query to match filters in the system

Many models are available on the market, and new ones appear every month. This lesson will help you understand how models differ from one another and how to choose the one that will deliver the best results for your product.

In this lesson:
→ How GPT-4o, GPT-o3, Claude, open-source models differ and why it matters
→ What to look for when choosing a model: quality, price, speed
→ What affects quality, price, and speed: model size, training approach, reasoning capability

What it looks like in practice:
→ Comparing how different models perform and learning to measure it
→ Case studies: calculating tokens and costs, comparing two models on a real-world task

Sometimes one LLM task is actually three. In this lesson, we learn how to design a pipeline: breaking a task into stages, testing each one separately, and assembling a stable system from simple components.

In this lesson:
→ Why using a single prompt for everything is a bad idea
→ What an LLM pipeline is and why you need one
→ How to build request routing when you have multiple scenarios

What it looks like in practice:
→ Learning to connect and combine LLM components like LEGO to build a product
→ Case study: combining two scenarios — support requests and search

When an AI assistant doesn't return a deterministic answer but instead holds a dialogue, a simple right / wrong check is no longer enough. In this lesson, we learn how to build an eval process: defining clear quality criteria and automating the labeling.

In this lesson:
→ What eval is and how to use it in complex LLM products
→ How to formulate quality criteria that can be assessed by both humans and LLMs
→ How the "LLM as a judge" process works and when it outperforms manual labeling
→ How to collect and manage datasets for testing and account for data drift

What it looks like in practice:
→ Learning to evaluate the evaluators — setting up a quality assurance pipeline
→ Case study: building a benchmark and writing eval prompts for an AI math assistant, starting with a single criterion and then evaluating comprehensively

An LLM product needs to be not only smart, but safe. In this lesson, we explore how to prevent harmful outputs: learning to identify unsafe topics, formulate clear restrictions, handle grey areas, and build evals that keep the product within appropriate boundaries.

In this lesson:
→ How to formalize the topic of safety in LLM products
→ How a safety eval is structured and how it differs from quality evals
→ How to monitor safety in production

What it looks like in practice:
→ Learning to add safety checks to the pipeline: from keyword filtering to post-processing → Case study: building a safety eval for a children's AI math assistant

Highlight business impact: Explain how AI-prototyping knowledge will help you build smarter products that solve real customer problems and drive growth.
Emphasize upskilling ROI: Show that investing in your skills now means faster delivery, better decisions, and fewer costly mistakes down the road.
Connect to company goals: Align the course benefits with your company’s strategy, whether it’s innovation, efficiency, or entering new markets.
Stress team advantage: Point out how your new AI-prototyping skills will uplift your whole team’s expertise and collaboration.
Assure minimal downtime: Reassure your employer the course is hands-on, flexible, and won’t disrupt your current workload.
Simplify payment: Let them know we can issue an invoice if needed, making the process easy for company reimbursement.

Contact Sales

The cases are really real and reflect the diversity of products in the industry: not everyone has a "website" or a "store". In the "Fundamentals" course, we cover the clothes rental start-up; in the "Tech for PM" simulator, we will look at a taxi ordering app (like Uber), a music service (like Spotify), and a food delivery app. In the simulator "A/B testing" we will dive into experiments on the Meditation service, and in "Product Discovery" we will analyze the business of renting clothes.

The more cases you solve (and not just read/watch), the more experienced a product manager you become. There is no other way.

One of the distinctive features of ProductDo is that all our courses are packaged in a simulator format. We can say that this is an important element of our product vision. The simulator as a learning tool has many wonderful properties:
- it requires constant active participation of the student. In order to move forward, you need to choose some action or answer a question every time.
- it allows you to give detailed feedback on any action: You can justify the preferred option with links and examples
- it allows you to move at your own pace and does not burden those who do not really like to work in a group with unnecessary communication.

Usually, they teach like this: theory → practice. If you have mastered the theory well, then you do the practice 100% or so. We have a completely different methodology. We start with a practical task that needs to be solved (and if the course suits you, then you don't know how to do it yet). Only when you have tried to solve the problem, we bring up some theory behind it. We believe that the cycle: trying to think independently → making a decision → feedback on a decision is a very effective way to master new material, especially for those who have already reached some professional level.

If you want to try the simulator format, take a free lesson. It contains questions from different areas of product management. At the same time, you can evaluate which skills you already have enough pumped, and which can be further enhanced.

We help by giving you a bunch of practical tasks and sharing our mistakes and experiences. We have already built so many products that with our examples we can help you formulate your area (more technical or more payment, related to ML / AI, or sales, etc.). We believe that a good PM chooses their favorite product themselves and does not need to be led by the hand.

The entire history of the simulator with comments and answers is saved. Access to the materials remains forever.

Yes, students who have successfully passed the course may generate a certificate and proudly add it to their LinkedIn profile to Licenses & Certifications, or upload it to Facebook in the Schools section.

Yet do keep in mind that upon applying to a product company, certificates do not really increase the chances of being hired, at least in our practice. If a resume mentions a certain course, then this may raise questions about what the candidate really knows right now. Therefore, you need to solve problems and develop skills, and not chase certificates. Fortunately, our courses have enough practice.

You can be sure of the materials' quality and our mentors' experience. We've been teaching for many years, and we have thousands of happy PMs. Feel free to take a look at the student reviews for verification.

If you passed less than 30% of tasks of the simulator you could refund your money in full.