The 7-day roadmap / day 4 of 7
Day 4: Context Engineering and MCP.
You'll learn how to give AI the right context at the right time via rules, skills, and MCP. Strong context engineering is what makes AI outputs consistent and production-ready.
- 8 topics
- 6 practice exercises
- 30 min of reading
- Free, no email
The 8 topics
- 01From Prompt Engineering to Context EngineeringWhy the craft has shifted from writing clever individual prompts to curating the full state an agent receives: tools, history, files, rules, and constraints. How that shift changes what good engineering looks like.Theory2 resources1 min
- 02Rules and Instructions: Persistent Context for Your AgentHow to use rules files, repository instructions, and AGENTS.md to give agents consistent, project-level context without repeating yourself in every prompt. The difference between global rules, project rules, and task-specific instructions.TheoryPractice4 resources3 min
- 03Skills and Commands: Reusable PatternsHow to package reusable capabilities as skills and reusable prompt workflows as commands, so agents can load exactly what they need for a task without bloating the default context.TheoryPractice5 resources4 min
- 04Custom Agents and PersonasWhen and how to define specialized agents configured for a specific role or task. How persona definitions, scoped instructions, and the AGENTS.md pattern let you build agents that stay focused and don't overstep.TheoryPractice3 resources3 min
- 05Rules, Skills, Commands, and Custom Agents: Knowing What to Use WhenA clear map of the four context management techniques available in modern AI coding tools, what each one is for, who triggers it, and how to combine them without creating a mess.TheoryPractice2 resources6 min
- 06Model Context Protocol (MCP): What It Is and Why It MattersWhat MCP is, why it emerged as a standard, and how the client-server architecture connects AI assistants to external data sources, tools, and APIs in a consistent and composable way.TheoryPractice3 resources4 min
- 07MCP Security: What Can Go WrongThe real security risks that come with connecting agents to external systems via MCP: prompt injection through tool outputs, data exfiltration, confused deputy attacks, and the practices that mitigate them.Theory1 resource5 min
- 08Harness Engineering: Everything Around the ModelWhy the systems wrapped around an LLM — the prompts, tools, sensors, and guardrails — matter as much as the model itself, and how to think about them as a discipline rather than a bag of tricks.TheoryPractice1 resource4 min
What you will watch and read
The roadmap is the shortest route to the ideas in AI-Native Software Engineering (O'Reilly Media). If you would rather work through them with your team, the canvas turns them into a workshop.