The context is everything the model sees along with that request: earlier messages, files, project instructions.

In depth: 00 · ABC: six words before you start → “5. Prompt and context”

Related: prompt · context window · memory

Appears in

• 01 · Introduction: Your experience with AI · Four shifts · Your first prompt
• 02 · Setup: Your first project
• 03 · Stack selection: Matrix of 4 stacks · Behind a censorship firewall: no VPN · Hermes + local stack
• 04 · Prompt Engineering: My worst prompt · The spec formula · The sins of prompting
• 05 · Context & Memory: When the agent didn't get you · Context vs Prompt · The memory system · Tune your memory
• 06 · Automation Pipeline: What to automate next?
• 07 · Tools & Extensions: MCP: superpowers through a protocol · Plug it in and test · Pendel: your agent audits your project
• 08 · Agent Engineering: Jagged Intelligence: What to Delegate
• 09 · AI Notebook: How it works
• 10 · Model Training: What's inside a model · Fine-tuning: when and how · Practice: fine-tune a small model
• 11 · Second Brain: Security: everything that comes from outside

The course is free — start on the site →

Write to the author: Telegram · LinkedIn

checked against the course: 2026-11-02 · 664b147