Course Outline
From autocomplete to agents: understanding agent failures
• Anatomy of a coding agent: model, harness, tool surface, context, permissions
• Tool positioning: Claude Code, GitHub Copilot, Cursor, Codex CLI, Gemini CLI
• A taxonomy of failure modes: incorrect context, inappropriate tools, lack of feedback, unbounded autonomy
Demonstration: Executing the same task successfully and unsuccessfully side by side
Context engineering
• The context window as a finite budget: determining what deserves space
• AGENTS.md, CLAUDE.md, .cursor/rules, copilot-instructions.md — a unified concept implemented via various filenames as the single source of truth
• Conventions, build and test commands, architectural boundaries
• Retrieval versus explicit context; task decomposition and sub-agents
Lab: Compose repository context for an unknown Python service, re-run a failing task, and compare outputs
Reusable workflows and Agent Skills
• Selecting the abstraction: instruction file, skill, custom command, or plain script
• Skill anatomy: triggering, instructions, bundled scripts, progressive disclosure
• Cross-tool portability and the onset of vendor lock-in
• Versioning, review processes, team distribution; common anti-patterns
Lab: Develop and test a reusable workflow that enforces house coding standards
MCP: linking agents to real-world systems
• Architecture: clients, servers, tools, resources, prompts; stdio and HTTP transports
• High-value servers: Git hosting, issue trackers, databases, browsers, internal APIs
• When a CLI or script outperforms an MCP server
• Tool-surface hygiene: why excessive tools compromise reliability
Lab: Configure MCP servers and process a ticket end-to-end — issue, branch, patch, tests, pull request
Feedback loops and evaluation
• Tests, types, and linters as the agent’s ground truth; employing test-first approaches for control
• CI as the outer loop, and review discipline for agent-authored diffs
• Golden-task evaluation sets: metrics to track and regression detection methods
• Cost and latency as primary metrics
Lab: Construct a small evaluation set and score two agent configurations against it
Security and guardrails
• Prompt injection vectors: issues, pull requests, READMEs, dependencies, fetched pages
• Permission models: allowlists, approvals, read-only tools, network egress control
• Secret hygiene and sandboxing: containers, ephemeral credentials, limiting blast radius
• Supply-chain risks associated with third-party MCP servers and shared skills
Lab: Observe an agent being hijacked by a poisoned repository, then harden the environment to prevent recurrence
Team rollout strategies
• A staged adoption path; balancing standardisation with individual flexibility
• Metrics that demonstrate tangible value versus those that do not
Requirements
• Proficiency in Python, Git, and command-line operations
• Previous experience with an AI coding assistant
• NobleProg will provision Dadesktop VMs for participants, pre-configured with Docker, VS Code, and Python 3.11 or a later version
• A functional AI coding assistant of your choice: Claude Code, GitHub Copilot, Cursor, Codex CLI, or Gemini CLI. The labs are tool-agnostic, and instructions are provided for each platform
Audience
• Software engineers, technical leads, and architects who utilise AI coding assistants but struggle to obtain consistent results
• Platform and developer-experience engineers implementing AI tooling across teams
• Engineering managers 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
