Skip to Content
View all events

Think Like an AI Pro

Published by O'Reilly Media, Inc.

Hands-on with LLMs, prompts, APIs, and tools like OpenAI and Claude

What you’ll learn and how you can apply it

  • Build AI-powered apps responsibly, with awareness of ethical risks like hallucinations and prompt injection
  • Design and optimize prompts to guide LLMs toward accurate, structured, and cost-efficient outputs
  • Integrate LLM APIs into real-world projects using tools like OpenAI, Claude, and open source models from Hugging Face
  • Leverage advanced AI capabilities such as agent workflows, retrieval-augmented generation (RAG), and multimodal inputs
  • Learn how to craft smarter prompts and understand API usage

Course description

As AI rapidly becomes embedded in every aspect of software development and business operations, understanding how to work with LLMs isn’t just valuable; it’s now essential. This live course with frontend engineer Aashima Ahuja is a fast-paced, hands-on introduction to the world of large language models (LLMs) and modern AI applications. Designed for developers, product teams, and tech-savvy professionals, it blends foundational AI theory with practical skills in prompt engineering, API usage, and advanced capabilities like agents and multimodal models.

You’ll learn how LLMs work, how to interact with them effectively through prompts, and how to build intelligent applications using cutting-edge tools like OpenAI, Claude, Hugging Face, and more. You’ll leave with the knowledge to build, optimize, and deploy AI-driven features responsibly and cost-effectively. Whether you’re prototyping a chatbot, integrating smart suggestions into a product, or exploring research workflows, this course equips you with the technical fluency to meet an AI-powered future.

This live event is for you because...

  • You’re a developer, data scientist, or product manager who wants to work hands-on with real AI tools.
  • You want to understand how LLMs work, including tokens, temperature, and prompting.
  • You’re ready to build real applications using APIs like OpenAI, Claude, or Hugging Face.
  • You’re a beginner or intermediate learner who wants practical, responsible AI skills you can use right away.

Prerequisites

  • Python installed on your computer
  • Any terminal (Iterm recommended)
  • No prior AI or machine learning experience required
  • Basic programming knowledge in Python or JavaScript (enough to read and write simple scripts)
  • Familiarity with using APIs or developer tools (e.g., Postman, REST calls, or browser-based playgrounds)

Recommended preparation:

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

The theory behind AI and LLMs (50 minutes)

  • Presentation: What is an LLM?; how LLMs work (tokens, self-supervised learning); determinism versus nondeterminism (temperature, randomness); token-based pricing (input versus output tokens); compute considerations (model size versus data size); common pitfalls (hallucinations, reproducibility)
  • Break

Crafting smarter interactions (55 minutes)

  • Presentation: Prompt engineering principles; in-context learning, zero-shot, few-shot, and chain-of-thought prompting; prompting tricks (temperature, max tokens, structuring); generating structured outputs (JSON, tables, markdown)
  • Hands-on exercise: Explore ChatGPT, Claude, or other LLM APIs
  • Break

APIs, inference, and cost tricks (55 minutes)

  • Presentation: Accessing LLMs via APIs; parameters overview (temperature, max_tokens, top_p); batching for cost optimization; overview of aggregators and open-weight models (Hugging Face, Ollama)
  • Demonstration: Python/Node.js
  • Hands-on exercise: Send your first batched request
  • Break

Exploring modalities and agents (45 minutes)

  • Presentation: Multimodal models (vision/audio inputs and outputs); reasoning and CoT in advanced models (Gemini Flash, DeepSeekR1); what agents are and how they work (Operator, AutoGPT, Deep Research); overview of RAG, CAG, and VectorDB integration
  • Demonstration: Using tools like Cursor AI, Perplexity AI, and NotebookLM
  • Break

Ethics, hallucinations, and guardrails (25 minutes)

  • Presentation: Prompt injection and jailbreaks; avoiding hallucinations; reproducibility and auditability in LLM output; final tools and best practices roundup

Wrap-up and Q&A (10 minutes)

Your Instructor

  • Aashima Ahuja

    Aashima Ahuja is a front-end engineer and a content creator. She has a passion for teaching front end. She has taken several trainings all over the world and is an active conference speaker. She has a bachelor's degree in Computer Science and has experience working in Big Tech companies.

    linkedinXsearch

Skills covered

  • Generative AI
  • MLOps
  • Web APIs
  • Application Programming Interface (API)