Course Outline
From Autocomplete to Agents: Understanding Agent Failures
• Deconstructing a coding agent: model, harness, tool interface, context, and permissions
• Positioning various tools: Claude Code, GitHub Copilot, Cursor, Codex CLI, and Gemini CLI
• A taxonomy of failure: incorrect context, inappropriate tools, lack of feedback, and uncontrolled autonomy
Demonstration: Executing the same task successfully versus unsuccessfully, side by side
Context Engineering
• Treating the context window as a budget: determining what deserves inclusion
• AGENTS.md, CLAUDE.md, .cursor/rules, copilot-instructions.md — one underlying concept applied across different filenames to create a single source of truth
• Establishing conventions, build and test commands, and defining architectural boundaries
• Distinguishing retrieval from explicit context; techniques for task decomposition and utilizing sub-agents
Lab: Create repository context for an unfamiliar Python service, then re-run a failing task to compare outputs
Reusable Workflows and Agent Skills
• Selecting the right abstraction: instruction files, skills, custom commands, or standard scripts
• Understanding skill anatomy: triggers, instructions, bundled scripts, and progressive disclosure
• Ensuring portability across tools while identifying where vendor lock-in may occur
• Managing versioning, reviews, and team distribution; recognizing common anti-patterns
Lab: Develop and test a reusable workflow that enforces organizational coding standards
MCP: Connecting Agents to Real-World Systems
• Architectural components: clients, servers, tools, resources, and prompts; supporting stdio and HTTP transports
• Identifying valuable servers: Git hosting platforms, issue trackers, databases, browsers, and internal APIs
• Determining when a CLI or script is more effective than an MCP server
• Maintaining tool-surface hygiene: understanding why excessive tools reduce reliability
Lab: Configure MCP servers to manage a ticket from start to finish – issue creation, branching, patching, testing, and pull request submission
Feedback Loops and Evaluation
• Leveraging tests, type checking, and linters as the agent's ground truth; using test-first approaches for control
• Integrating CI as an outer loop and maintaining review discipline for agent-generated diffs
• Utilizing golden-task evaluation sets: defining what to measure and how to detect regressions
• Treating cost and latency as primary metrics
Lab: Construct a small evaluation set and score two distinct agent configurations against it
Security and Guardrails
• Protecting against prompt injection via issues, pull requests, READMEs, dependencies, and fetched web pages
• Implementing permission models: allowlists, approval workflows, read-only tools, and network egress controls
• Adhering to secret hygiene and sandboxing practices: using containers, ephemeral credentials, and limiting blast radius
• Assessing supply-chain risks associated with third-party MCP servers and shared skills
Lab: Observe an agent being hijacked by a compromised repository, then reinforce the setup to prevent such incidents
Team-Wide Deployment Strategies
• A phased adoption path: determining what to standardize versus what to leave to individual discretion
• Identifying metrics that reflect genuine value and those that do not
Requirements
• Proficient knowledge of Python, Git, and the command line
• Prior experience with an AI coding assistant
• NobleProg will provision Dadesktop VMs for participants, pre-configured with Docker, VS Code, and Python 3.11 or later
• A functional AI coding assistant of the participant's choice: Claude Code, GitHub Copilot, Cursor, Codex CLI, or Gemini CLI. The labs are tool-agnostic, with instructions provided for each option
Audience
• Software engineers, tech leads, and architects who use AI coding assistants but struggle to achieve consistent results
• Platform and developer-experience engineers implementing AI tooling across multiple teams
• Engineering managers responsible for establishing standards, guardrails, and success metrics
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
