Building with LLM APIs
Call language models from your own code: requests, streaming, tools and costs.
30tutors
6teachers
3free to start
$3 to $12per paid lesson
Building with LLM APIs tutors
30 tutors
System Prompts for Real Applications
System Prompts for Real Applications
Write system prompts that make an app behave consistently, handle edge cases and survive real users.68 lessonsSampleGabriela Sousa$5Your First LLM API RequestYour First LLM API Request
Send your first request to a language model API from code, read the reply and understand every field.66 lessonsSampleGabriela SousaFreeLogging and Tracing LLM CallsLogging and Tracing LLM Calls
Record every model call and pipeline step so you can explain cost, slowness and bad answers.65 lessonsSampleFarid Haddad$8Choosing the Right Model for a TaskChoosing the Right Model for a Task
Pick a model by testing it on your own task, weighing quality, speed, cost, context and data handling.60 lessonsSampleGabriela Sousa$5Fallbacks for Provider Outages and ErrorsFallbacks for Provider Outages and Errors
Keep LLM features working through outages, overloads and slowdowns with deadlines, breakers and fallbacks.60 lessonsSampleFarid Haddad$11Tool Calling: Let the Model Use Your CodeTool Calling: Let the Model Use Your Code
Define tools, run the call and result loop safely, and get a model to use your functions correctly.59 lessonsSampleGreta Lindqvist$8Your First RAG Pipeline, End to EndYour First RAG Pipeline, End to End
Build a small retrieval augmented chatbot over your own documents, step by step, and see where it fails.59 lessonsSampleEmeka NwosuFreeToken Counting and Cost ControlToken Counting and Cost Control
Count tokens, predict what a feature will cost and cut spending without hurting answer quality.57 lessonsSampleFarid Haddad$4Rate Limits, Retries and BackoffRate Limits, Retries and Backoff
Handle 429s and overloads gracefully with backoff, jitter, client side pacing and retries that never cause storms.53 lessonsSampleFarid Haddad$7Cost and Latency Budgets for LLM FeaturesCost and Latency Budgets for LLM Features
Set cost and speed targets for an LLM feature, measure them honestly and trade them against quality.52 lessonsSampleFarid Haddad$8Moderation, Refusals and Safe ResponsesModeration, Refusals and Safe Responses
Design how your LLM app handles harmful requests, refusals and sensitive topics, without blocking normal users.49 lessonsSampleGreta Lindqvist$5Prompt Injection Defences for LLM AppsPrompt Injection Defences for LLM Apps
Design LLM apps that stay safe when users, documents, web pages or tool results contain hostile instructions.49 lessonsSampleGreta Lindqvist$12Teachers who teach Building with LLM APIs
They wrote the lesson plans these tutors follow.
Emeka Nwosu
Search engineer teaching embeddings, chunking, vector and keyword search, and reranking from first principlesembeddings, chunking, vector databases9 tutorsSampleFelix Brandt
Numerical Python and code quality for data and AI projects that have outgrown a single notebookNumPy, pandas, plotting9 tutorsSampleFarid Haddad
Keeps LLM features fast, affordable and available as traffic grows: cost, caching, retries and observabilitytoken counting, cost control, prompt caching9 tutorsSampleGabriela Sousa
Teaches developers and product teams to make their first LLM API calls and design simple apps around themfirst API requests, messages and roles, system prompts9 tutorsSampleGreta Lindqvist
Structured output, tool calling and safe input handling for LLM applications that must behave predictablystructured output and JSON schemas, tool and function calling, image and document input9 tutorsSampleYohannes Tesfaye
Machine learning engineer who runs portfolio reviews and mock interviews for technical AI rolesML engineering interviews, data science interviews, AI product manager interviews9 tutorsSampleMore in Building with AI
- Python for AI The Python you need for AI work: data, notebooks, libraries and small scripts. 21 tutors
- RAG and search Connect a model to your own documents with embeddings, search and retrieval. 21 tutors
- Evaluation and testing Measure whether an AI feature works, with test sets, metrics and reviews. 21 tutors
- AI agents Models that plan, use tools and act in steps, and how to keep them on track. 31 tutors
- AI automation Hand repetitive work to AI with workflows, triggers and simple integrations. 25 tutors
- AI coding assistants Write, read and debug code faster with an AI pair programmer. 30 tutors