Claude Code – autonomous agent development & MCP integration (CLPRG1)
AI - Artificial Intelligence, AI for developers
This hands-on course helps experienced developers adopt Claude Code into real development workflows. You will operate controlled agents in both IDE and terminal, work with prepared code fragments and projects, and practice safe, repeatable AI-driven development.
Through practical exercises, code review and TDD you will build CLAUDE.md, manage memory, define guardrails and implement hooks, custom commands and skills. The course covers MCP integration and multi-agent pipelines for production use.
THIS TRAINING COURSE WILL HELP YOU:
- Understand LLM principles and agent architecture
- Set up and use Claude Code in IDE and terminal
- Create CLAUDE.md and manage project/user memory
- Design and enforce guardrails and security constraints
- Develop and test code with agents in a TDD workflow
WHO SHOULD ATTEND?
- Developers integrating AI into development workflows
- DevOps and platform engineers managing MCP servers
- Tech leads and architects designing agent solutions
- QA engineers and automation specialists
COURSE LOCATION AND AVAILABLE DATES
Praha + online (optional)
26–27 Nov 2026
632 €
CZECH
18–19 Feb 2027
632 €
CZECH
13–14 May 2027
632 €
CZECH
Need this course in English?
Public courses are usually delivered in Czech, but this course is also available in English. We can arrange private training for your team online, at your premises or in our classrooms, and tailor the content to your needs.
For groups of around 4 or more participants, private training can already be comparable in price to booking individual places on a public course. Send us your requirements and we’ll recommend the best format and provide an exact quote.
Request training in English
Course content:
Hide details
-
From chat to agents
-
History of LLMs
-
Inner workings of LLMs
-
What an agent is and its components
-
Claude Code in the IDE
-
Plugin installation (VS Code / JetBrains)
-
Inline edits vs side-panel conversations
-
Claude Code in the terminal
-
CLI workflow and when it's faster than an IDE
-
CLI-driven development without opening files
-
Context for the agent: CLAUDE.md and memory
-
Why context determines output quality
-
Structure of a good CLAUDE.md
-
Auto-memory; project vs. user memory
-
How to craft an effective prompt
-
What makes a prompt effective for an agent
-
Specificity, examples, constraints, verification asks
-
Iterating prompts during a task
-
Navigating unfamiliar code
-
Delegate "how does this work?" to the agent
-
When to trust synthesis and when to verify
-
Spot-checking architectural claims
-
Planning and limits for agents
-
Plan mode and agreeing on changes before implementation
-
Small steps and iterative changes
-
Scope control — stopping unrelated refactors
-
How to review code produced by an agent
-
Reading AI-generated diffs
-
Hallucinations and fabricated APIs
-
Review fatigue and mitigation strategies
-
Tests and test-driven development
-
Why tests are more crucial when shipping with AI
-
TDD workflow with an agent
-
Reviewing AI-generated tests with the same skepticism as code
-
Git workflow and gh CLI
-
Creating pull requests via gh CLI
-
AI-assisted diff review
-
Autonomy and guardrails
-
Spectrum of agent autonomy: default, acceptEdits, plan, auto, bypassPermissions
-
Auto mode and configuring autoMode.environment
-
dangerously-skip-permissions and managed team settings
-
Claude Code hooks
-
Pre/post-action hooks (formatter, linter, custom rules)
-
Hook events: PreToolUse, PostToolUse, Stop and others
-
Hooks to enforce project conventions: /loop, /schedule and built-ins
-
/loop and /schedule — repeated and scheduled tasks
-
Context management: /clear, /compact, /memory
-
Session configuration: /model, /config, /permissions
-
Creating custom commands
-
Anatomy of a custom command in .claude/commands/
-
$ARGUMENTS templating
-
Sharing commands across the team
-
Using skills
-
What a skill is and how it differs from a command
-
Discovery — how an agent detects available skills
-
Applying skills to real tasks
-
Building custom skills
-
Skill structure (metadata header, content, examples)
-
Description as a trigger
-
Packaging and team distribution
-
MCP servers — practical use
-
MCP mental model
-
Confluence MCP server
-
MCP vs plain CLI usage
-
Custom MCP server
-
MCP protocol in depth
-
Server structure and tool definitions
-
Multi-agent workflow and spec-driven development
-
Sub-agents: planner / executor / verifier
-
Superpowers plugin and get-shit-done (gsd)
-
When multi-agent pipelines make sense and when not
-
Remote control and Claude Code channels
-
Claude Code from anywhere (mobile, second machine, on-call)
-
Channel plugins (Telegram and others)
-
Building your own end-to-end application
-
Setting up a small project
-
Full workflow: context → plan → test → PR
-
Summary of pitfalls and enterprise deployment considerations
-
Prerequisites:
-
Experience in software development, routine use of Git and familiarity with an IDE (VS Code, JetBrains, etc.).
-
Schedule:
-
2 days (9:00-17:00)
-
Price per person:
-
632.00 € ( 764.72 € incl. 21% VAT)
Training and learning environment
What does the environment for in-person IT courses look like?We hold training courses in our own classrooms equipped with modern computer equipment for each participant and a large projection screen. Each workstation is fitted with a powerful computer for seamless practical exercises, and the environment supports a calm, friendly atmosphere during training.
Do I need to bring my own laptop to the classroom IT course?Our training rooms are fully equipped, so you do not need to bring your own laptop. A modern computer with all necessary hardware and software is ready for you at your workstation.
Will you receive an official certificate after completing an IT course?Yes, upon successful completion of the training course, you will receive an official ICT Pro certificate confirming your participation and acquired technical skills. You can use it to verify your qualifications or add it to your professional profile.
Where can you find our training center in Brno?The premises of the ICT Pro training center are located on the 1st floor of the COMGUARD building at Sochorova 38 in Brno. Positioned on the border of Žabovřesky and Komín, the location is easily accessible by both car and public transport.
Where can you find our training center in Prague?The premises of the ICT Pro training center are located on the 1st floor of the Opatov Park building at Líbalova 1, Prague 11 – Chodov. The location provides a comfortable environment for your education with convenient access.
What facilities and refreshments are available to you during training breaks?Our training centers feature a fully equipped kitchenette for a comfortable break during your courses. The facilities include a coffee machine, microwave, kettle, and a wide selection of drinks and snacks.
What beverage refreshments are available during your course?A beverage station with a coffee machine, teas, syrups, and water is at your disposal throughout the entire training session. You can enjoy a coffee or another drink of your choice anytime during breaks.
What light refreshments are provided for you during the courses?During course breaks, participants can enjoy light sweet snacks, pastries, and fruit syrups to mix their own drinks. Fresh water dispenser and plates are also available for your convenience.
Should I bring my own snacks to ICT Pro training?There is no need to. A wide selection of savory snacks, sweet biscuits, and snack bars is available for you during breaks. Boost your energy for all-day focus right inside the training center premises.
Can you spend training breaks in the fresh air?Yes, an outdoor terrace is available at our training center. During breaks between learning sessions, you can relax in the fresh air in a pleasant green environment.
Where can you relax during course breaks?Our training center features a spacious outdoor terrace with seating options. During breaks between learning sessions, you can step outside to relax and recharge in the fresh air.