{"course":{"productid":37210,"modality":1,"active":true,"language":"fr","title":"Master Class: Agentic Software Engineering using Claude Code","productcode":"ASECC","vendorcode":"MT","vendorname":"Master Class","fullproductcode":"MT-ASECC","courseware":{"has_ekit":false,"has_printkit":true,"language":""},"url":"https:\/\/portal.flane.ch\/course\/masterclass-asecc","essentials":"<p>The exercises will be conducted in Python, TypeScript, and C#. Basic knowledge of these programming languages is helpful but not required.<\/p>","audience":"<p>Software Architects, Developer (All)<\/p>","contents":"<h5>Module 1: Claude Code Fundamentals<\/h5><ul>\n<li>Get Started with Claude Code<\/li><li>Install and Configure Claude Code<\/li><li>Choose Your Editor<\/li><li>Write a CLAUDE.md Constitution<\/li><li>Master Prompting Techniques<\/li><li>Select the Right Model<\/li><li>Configure the Permission Model<\/li><li>Run Parallel Agents with Git Worktrees<\/li><\/ul><h5>Module 2: Claude Code Configure Harness<\/h5><ul>\n<li>Understand the Claude Code Harness<\/li><li>Build Custom Slash Commands<\/li><li>Automate Workflows with Hooks<\/li><li>Connect MCP Servers to the Harness<\/li><li>Create Reusable Skills<\/li><li>Package and Distribute Plugins<\/li><li>Persist Context with Memory<\/li><li>Checkpoint and Resume Long Sessions<\/li><li>Delegate Work to Sub-Agents<\/li><\/ul><h5>Module 3: Creating &amp; Managing Skills<\/h5><ul>\n<li>Understand Skills vs Slash Commands<\/li><li>Create a Skill from Scratch<\/li><li>Compose Skills into Workflows<\/li><li>Test and Publish Skills<\/li><li>Evolve Skills with Metrics<\/li><\/ul><h5>Module 4: Consuming &amp; Designing MCP Tools<\/h5><ul>\n<li>Master the Model Context Protocol<\/li><li>Build a Custom MCP Server in C#<\/li><li>Implement and Use MCP Applications<\/li><\/ul><h5>Module 5: Programmable Automation using the Claude Code CLI<\/h5><ul>\n<li>Run Claude Code in Headless Mode<\/li><li>Parallelize Work with Git Worktrees<\/li><li>Gate CI Pipelines with Sentinel Tokens<\/li><li>Enforce Policy Hooks Across Parallel Worktrees<\/li><li>Build Agents that Loop Until a Verifiable Goal is Met<\/li><\/ul><h5>Module 6: Plan and Decompose for Maximum Agentic Effectiveness<\/h5><ul>\n<li>Enter Plan Mode for Complex Tasks<\/li><li>Reason Deeply with Extended Thinking and Persist Decisions in STATE.md<\/li><li>Drive Specs with Spec Kit and BMAD<\/li><\/ul><h5>Module 7: Scale Task Execution with Sub-Agents<\/h5><ul>\n<li>Explore Sub-Agent Architecture and Context Isolation<\/li><li>Implement a Backend Sub-Agent for .NET<\/li><li>Configure a Frontend Sub-Agent for Angular<\/li><li>Configure a QA Agent for Browser Verification<\/li><li>Unit-Test Your Agent&#039;s Performance<\/li><li>Orchestrate Sub-Agents with Decomposition Patterns<\/li><\/ul><h5>Module 8: Optimizing the Agentic Harness &amp; Continuous Learning<\/h5><ul>\n<li>Optimize the Agentic Harness<\/li><li>Compress Context with the Caveman Technique<\/li><li>Build an Autoresearch Loop<\/li><li>Design Memory Architectures<\/li><li>Build a Second Brain with Obsidian<\/li><\/ul><h5>Module 9: Deploy Autonomous Action using Managed Agents<\/h5><ul>\n<li>Understand the Managed Agents Mental Model<\/li><li>Build Your First Managed Agent<\/li><li>Add Production Features to Managed Agents<\/li><li>Add Human-in-the-Loop Controls<\/li><\/ul><h5>Module 10: Security, Hardening &amp; Observability<\/h5><ul>\n<li>Map the Agent Threat Model<\/li><li>Apply Guardrails and Least Privilege<\/li><li>Secure Secrets and Credentials<\/li><li>Trace Agents and Diagnose Failures<\/li><\/ul><h5>Module 11: Build Multi-Agent Pipelines using the Agent SDK<\/h5><ul>\n<li>Understand the Claude Agent SDK<\/li><li>Call the Claude Agent SDK<\/li><li>Run Parallel Agents with the SDK<\/li><\/ul><h5>Module 12: Bundling &amp; Distributing Plugins<\/h5><ul>\n<li>Understand Why Plugins Exist<\/li><li>Inspect Plugin Anatomy<\/li><li>Convert a .claude\/ Config to a Plugin<\/li><li>Publish Plugins to Marketplaces<\/li><\/ul><h5>Module 13: Agentic DevOps &amp; Automation<\/h5><ul>\n<li>Deploy with the Azure GitHub DevOps Agent<\/li><li>Deploy to Azure with GitHub Actions<\/li><li>Automate Deployments with Azure Developer CLI<\/li><li>Provision Infrastructure with Bicep and Terraform<\/li><li>Drive the Azure CLI from Claude Code<\/li><li>Agentic Optimization: Web Vitals and SEO<\/li><\/ul>","summary":"<p>Great software no longer has to cost a fortune or consume every hour of your day. With Claude Code, you get an engineering partner that plans, builds, tests, and ships alongside you at a fraction of the time and cost. This isn&rsquo;t about prompting an AI. It&rsquo;s about designing systems that multiply what you can deliver. Welcome to the new standard.<\/p>\n<p>Agentic software engineering is a discipline shift, and once you experience it, there&rsquo;s no going back. Instead of spending days on tasks that take agents minutes, you orchestrate workflows that reduce cost, eliminate repetition, and scale your output without scaling your team. The developers who master this don&rsquo;t just move faster. They do more with less, and they do it consistently.<\/p>\n<p>Across 13 hands-on modules, you&rsquo;ll go from Claude Code fundamentals to production-grade multi-agent pipelines. You&rsquo;ll configure the agentic harness, design composable skills, build MCP tools that connect agents to real systems, architect parallel sub-agent workflows, and harden everything for real-world conditions. Every module is built around genuine engineering decisions, because the goal was never to write more code. It was always to build software that matters.<\/p>","essentials_plain":"The exercises will be conducted in Python, TypeScript, and C#. Basic knowledge of these programming languages is helpful but not required.","audience_plain":"Software Architects, Developer (All)","contents_plain":"Module 1: Claude Code Fundamentals\n\n\n- Get Started with Claude Code\n- Install and Configure Claude Code\n- Choose Your Editor\n- Write a CLAUDE.md Constitution\n- Master Prompting Techniques\n- Select the Right Model\n- Configure the Permission Model\n- Run Parallel Agents with Git Worktrees\nModule 2: Claude Code Configure Harness\n\n\n- Understand the Claude Code Harness\n- Build Custom Slash Commands\n- Automate Workflows with Hooks\n- Connect MCP Servers to the Harness\n- Create Reusable Skills\n- Package and Distribute Plugins\n- Persist Context with Memory\n- Checkpoint and Resume Long Sessions\n- Delegate Work to Sub-Agents\nModule 3: Creating & Managing Skills\n\n\n- Understand Skills vs Slash Commands\n- Create a Skill from Scratch\n- Compose Skills into Workflows\n- Test and Publish Skills\n- Evolve Skills with Metrics\nModule 4: Consuming & Designing MCP Tools\n\n\n- Master the Model Context Protocol\n- Build a Custom MCP Server in C#\n- Implement and Use MCP Applications\nModule 5: Programmable Automation using the Claude Code CLI\n\n\n- Run Claude Code in Headless Mode\n- Parallelize Work with Git Worktrees\n- Gate CI Pipelines with Sentinel Tokens\n- Enforce Policy Hooks Across Parallel Worktrees\n- Build Agents that Loop Until a Verifiable Goal is Met\nModule 6: Plan and Decompose for Maximum Agentic Effectiveness\n\n\n- Enter Plan Mode for Complex Tasks\n- Reason Deeply with Extended Thinking and Persist Decisions in STATE.md\n- Drive Specs with Spec Kit and BMAD\nModule 7: Scale Task Execution with Sub-Agents\n\n\n- Explore Sub-Agent Architecture and Context Isolation\n- Implement a Backend Sub-Agent for .NET\n- Configure a Frontend Sub-Agent for Angular\n- Configure a QA Agent for Browser Verification\n- Unit-Test Your Agent's Performance\n- Orchestrate Sub-Agents with Decomposition Patterns\nModule 8: Optimizing the Agentic Harness & Continuous Learning\n\n\n- Optimize the Agentic Harness\n- Compress Context with the Caveman Technique\n- Build an Autoresearch Loop\n- Design Memory Architectures\n- Build a Second Brain with Obsidian\nModule 9: Deploy Autonomous Action using Managed Agents\n\n\n- Understand the Managed Agents Mental Model\n- Build Your First Managed Agent\n- Add Production Features to Managed Agents\n- Add Human-in-the-Loop Controls\nModule 10: Security, Hardening & Observability\n\n\n- Map the Agent Threat Model\n- Apply Guardrails and Least Privilege\n- Secure Secrets and Credentials\n- Trace Agents and Diagnose Failures\nModule 11: Build Multi-Agent Pipelines using the Agent SDK\n\n\n- Understand the Claude Agent SDK\n- Call the Claude Agent SDK\n- Run Parallel Agents with the SDK\nModule 12: Bundling & Distributing Plugins\n\n\n- Understand Why Plugins Exist\n- Inspect Plugin Anatomy\n- Convert a .claude\/ Config to a Plugin\n- Publish Plugins to Marketplaces\nModule 13: Agentic DevOps & Automation\n\n\n- Deploy with the Azure GitHub DevOps Agent\n- Deploy to Azure with GitHub Actions\n- Automate Deployments with Azure Developer CLI\n- Provision Infrastructure with Bicep and Terraform\n- Drive the Azure CLI from Claude Code\n- Agentic Optimization: Web Vitals and SEO","summary_plain":"Great software no longer has to cost a fortune or consume every hour of your day. With Claude Code, you get an engineering partner that plans, builds, tests, and ships alongside you at a fraction of the time and cost. This isn\u2019t about prompting an AI. It\u2019s about designing systems that multiply what you can deliver. Welcome to the new standard.\n\nAgentic software engineering is a discipline shift, and once you experience it, there\u2019s no going back. Instead of spending days on tasks that take agents minutes, you orchestrate workflows that reduce cost, eliminate repetition, and scale your output without scaling your team. The developers who master this don\u2019t just move faster. They do more with less, and they do it consistently.\n\nAcross 13 hands-on modules, you\u2019ll go from Claude Code fundamentals to production-grade multi-agent pipelines. You\u2019ll configure the agentic harness, design composable skills, build MCP tools that connect agents to real systems, architect parallel sub-agent workflows, and harden everything for real-world conditions. Every module is built around genuine engineering decisions, because the goal was never to write more code. It was always to build software that matters.","version":"1.0","duration":{"unit":"d","value":4,"formatted":"4 jours"},"pricelist":{"List Price":{"DE":{"country":"DE","currency":"EUR","taxrate":19,"price":4890},"AT":{"country":"AT","currency":"EUR","taxrate":20,"price":4890},"CH":{"country":"CH","currency":"CHF","taxrate":8.1,"price":4890},"SE":{"country":"SE","currency":"EUR","taxrate":25,"price":4890},"SI":{"country":"SI","currency":"EUR","taxrate":20,"price":4890}}},"lastchanged":"2026-05-21T08:23:50+02:00","parenturl":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-courses","nexturl_course_schedule":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course-schedule\/37210","source_lang":"fr","source":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course\/masterclass-asecc"}}