The Agentic Intention Framework

Improve the reliability and efficiency of your agentic system by starting with a framework that defines constraints and considerations.

Intermediate

5 lessons

Approx. 36 min

Instructors

Carlisia Campos

MCP Technical Strategist

Carlisia Campos is a senior software engineer specializing in Go, cloud-native systems, AI (LLM/MCP) integration, and open source.

Intermediate

5 lessons

Approx. 36 min

Start Course

What you’ll learn

This course sets you up for successful use of an MCP server. We will introduce a framework that will ensure you are clear about the purpose of your MCP server. You’ll design your MCP server based on what LLMs actually ‘see’, establish tight boundaries for server scope, and you’ll anticipate how your server will evolve with time. This course is about investing time upfront to save time and energy later.

Lessons

Lesson 1

The Agentic Intention Framework

Introduction: The paradox of building with AI in the loop As modern software engineers, we’re trained in the agile way: ship fast, iterate based on feedback, let design emerge. We start minimal and evolve based on what we learn from users. But architecting robust, performant, and useful MCP servers demands the opposite: with LLMs in …

Article

6 min read

Lesson 2

A Tale of Three MCP Servers

Let me tell you about Eduardo and Monica (😬 if you know, you know, lolz), and Bruno, three developers who learned this lesson very differently. Keep in mind: A tool (handler) can either contain all the code to be executed or simply call another function that serves as an entry point for the actual work. …

Article

10 min read

Lesson 3

Defining Tighter Boundaries Using Intention

The agentic intention framework can be used as a daily decision-making filter. If every choice we face flows through this framework, we will succeed in keeping our MCP servers focused and effective. Scope boundaries Before writing any code, our intention helps us define what belongs in our MCP server and what doesn’t. The Goldilocks test …

Article

3 min read

Lesson 4

Composition Patterns That Work

One of MCP’s most powerful features is enabling LLMs to combine tools into solutions. In this section I want to give you ideas for how to craft effective composition patterns. Three principles for composable tools 1. Predictable contracts Each tool has clear inputs and outputs. When AnalyzeDocumentationQuality returns a QualityReport, the LLM knows exactly what …

Article

6 min read

Lesson 5

The Agentic Intention Framework In Practice

Overview: Who, what and why WHO will use the framework: WHAT are the components of the framework: A structured framework that transforms vague AI agent ideas into precise, measurable workflow definitions by eliciting explicit answers to critical questions before development begins: Framework constraints WHY use the framework: Achieve higher adoption rates for agentic tools and …

Article

11 min read