Learn how to use AI
A structured path from "what is an LLM" through verifying output, using AI at work, and building with it. Work through it module by module — your progress is tracked as you go.
Your progress
89 guides across 4 tracks. Pick any module to begin — progress saves on this device.
Working with AI
0/59 done · 8 modules
Start here
The foundations that make every later guide easier. Read this pillar first if you are new to AI.
Verify and trust
What AI gets wrong, how to check its output, and what is safe to share at work.
How AI works
The mechanism under the hood — tokens, embeddings, transformers, context windows, agents. For the curious operator who wants to understand, not just use.
Use AI for work
Concrete task-based playbooks — email, meetings, research, weekly reports, second-brain capture.
Build with AI
Prompting your way to working software. Vibe coding, code review, working on existing codebases.
Ship and own your stack
Graduating from no-code to a real production deploy you control.
AI by role
Role-specific playbooks for sales, marketing, founders, HR, PM, engineering, design, ops.
Choose the right AI
Which model for which job, when a chat window is enough vs when to reach for a coding agent, and when the paid tier actually pays off.
Building & shipping
0/6 done · 3 modules
Prompt Engineering
0/12 done · 3 modules
Prompt fundamentals
The patterns that hold across every model — clarity, structure, examples, and the five moves that work every time.
Prompting techniques
Beyond the basics — chain-of-thought, prompt chaining, role assignment, and format control for predictable, repeatable results.
Building with prompts
For anyone embedding prompts in a product or workflow — system prompts, iteration discipline, injection defense, and cross-model porting.
Stacks & systems
0/9 done · 4 modules
Picking your stack
Build vs buy, what to roll yourself, what to outsource to a SaaS.
Integration patterns
Connecting tools without writing a backend. Webhooks, polling, native integrations.
Automation
Zapier vs Make vs n8n vs scripts. Personal automations worth the setup.
Running AI tools
Getting the tools actually running on your machine — installing CLI coding agents, what MCP is, and connecting AI to your own systems.
Sequenced routes through the library
Three multi-guide paths shaped by role and goal: operator, engineer, PM. An ordered reading list with notes — work through it at your own pace.
Recently updated
emergentintegrations.llm.chat: how the Python package works outside Emergent, plus JavaScript alternatives
What the emergentintegrations Python package does, how to keep it running on your own infrastructure with EMERGENT_LLM_KEY, why there is no JavaScript SDK, and how to replace it with direct OpenAI or Anthropic calls.
Migrate from Emergent: FastAPI→Railway, React→Vercel (2026)
Move your Emergent app off the platform and replace the emergentintegrations client and EMERGENT_LLM_KEY with a direct LLM connection. FastAPI moves to Railway, React to Vercel, MongoDB to Atlas, with exact commands and env wiring.
Chain-of-thought prompting: when reasoning out loud changes the output
Why telling a model to "think step by step" works, and when it does not. Zero-shot CoT vs few-shot CoT, what tasks benefit most, and the cases where it actively slows you down.
How to create an AI agent
The three honest ways to build one (no-code, a coding framework, or from scratch), with a first build for each, the failures to design for, and the resources worth your time. It starts with the question most people skip: do you even need an agent?