The Evolution of Development Practices Through Agentic Engineering
Development teams are already using generative AI in their day-to-day work, but typically as an individual exploration: each developer writes their own prompts, without shared standards or true integration into the development workflow.
This course is designed to take the next step: turning that exploration into a standardized team practice that delivers consistent results.
Through a hands-on approach, we will cover everything from the fundamentals of LLMs and agents to the advanced agentic design patterns we use in our own development teams today.
Course information
Format
Online
Duration
10 hours of theory and hands-on practice, split into 2 parts (Foundations and Advanced Patterns)
Private student group, tailored to your company
Objectives
- Understand how LLMs and AI code agents function, and determine when to use a consultative versus an agentic approach.
- Master prompt and context engineering techniques to achieve consistent, high-quality results.
- Configure the agent's context (AGENTS.md, rules files, and skills) so it aligns with your project's tech stack and development conventions.
- Integrate agentic workflows into the development process, including Research-Plan-Implement (RPI) cycles, sub-agents, and spec/plan/test-driven development.
- Establish team practices and agreements on what to delegate to the agent, what to keep human-driven, and how to conduct assisted code reviews.
- Work securely by managing permissions, utilizing sandboxing, handling secrets properly, and preventing destructive operations.
What You'll Learn
- A shared AI framework for the entire team, rather than just individual skills.Reusable prompts, configurations, and skills you can apply to your own codebase starting the very next day.
- Real, hands-on practice: every module features exercises based on concrete development use cases.
Content
Part 1 - Foundations
- LLMs and Agents: Model types, capabilities, and selection criteria. Consultative vs. agentic use.
- Prompt Engineering: Fundamental techniques and common anti-patterns.
- Context Engineering: Context architecture (AGENTS.md, rules files, project configurations) and context window mechanics.
- Tools and MCP: Agent capabilities and the protocol connecting them to external systems.
- Skills and Rules: Reusable team workflows and project-specific agent guardrails.
- Security: Permissions, sandboxing, secret management, and preventing destructive operations.
Part 2 — Advanced Patterns (5 hours)
- Team AI Practices: Shared conventions and onboarding to the team's agentic workflow.
- Requirements Management: Assisted refinement and rapid functional prototyping (v0, Claude Artifacts, and similar tools).
- Agentic Workflows: Research-Plan-Implement (RPI) and sub-agents for parallel execution.
- Spec / Plan / TDD: Spec- and test-driven agentic development with automated quality gates.
- Agentic Code Review: Determining what to delegate (and what not to) in assisted reviews.
Who Is This Course For?
Developers and software development teams who have already experimented with generative AI tools (ChatGPT, Claude, Copilot) and want to transition to a systematic, collaborative, and agentic workflow.
It also delivers significant value to tech leads and architects responsible for defining standards and adoption criteria for their teams.
