{"course":{"productid":36408,"modality":1,"active":true,"language":"fr","title":"Responsible AI in agentic software development","productcode":"RAIASD","vendorcode":"CY","vendorname":"Cydrill","fullproductcode":"CY-RAIASD","courseware":{"has_ekit":false,"has_printkit":true,"language":""},"url":"https:\/\/portal.flane.ch\/course\/cydrill-raiasd","objective":"<ul>\n<li>Understand various aspects of responsible AI<\/li><li>How to use generative AI responsibly in software development<\/li><li>Prompt engineering for optimal outcomes<\/li><li>How to apply generative AI throughout the SDLC<\/li><li>The challenges in using agentic GenaI<\/li><\/ul>","essentials":"<p>General development<\/p>","audience":"<p>All people involved in using agentic AI tools in software development<\/p>","contents":"<h4>A brief history of Artificial Intelligence<\/h4><ul>\n<li>The origins of AI<\/li><li>Neural networks and &ldquo;probability engines&rdquo;<\/li><li>Early ML coding tools<\/li><li>The AI coding revolution of the 2020s<\/li><\/ul><h4>Responsible AI<\/h4><ul>\n<li>What is responsible AI?<\/li><li>Accountability and transparency<\/li><li>Mitigation of harmful bias<\/li><li>Validity and reliability<\/li><li>Demonstration &ndash; Experimenting with validity and reliability in Copilot<\/li><li>Explainability and interpretability<\/li><li>Safety, security, privacy and resilience<\/li><li>Security and responsible AI in software development<\/li><\/ul><h4>Using GenAI responsibly in software development<\/h4><ul>\n<li>LLM code generation basics<\/li><li>Basic building blocks and concepts<\/li><li>Prompt templating<\/li><li>System prompts in AI-driven coding<\/li><li>Can AI&hellip; boost your productivity?<\/li><li>Can AI&hellip; take care of the &lsquo;boring parts&rsquo;?<\/li><li>Can AI&hellip; be more thorough?<\/li><li>Reviewing generated code &ndash; the black box blues<\/li><li>The danger of hallucinations<\/li><li>The effect of GenAI on programming skills<\/li><li>Some further long-term effects of using GenAI<\/li><li>Where AI code generation doesn&rsquo;t do well<\/li><li>Prompt engineering\n<ul>\n<li>Why is a good prompt so important?<\/li><li>Establishing the context for generative AI<\/li><li>Zero-shot, one-shot, and few-shot prompting<\/li><li>Reasoning-based prompt engineering, chain-of-thought<\/li><li>Demonstration &ndash; Experimenting with prompts in Copilot<\/li><li>Enforcing and following token limits<\/li><li>Prompt patterns\n<ul>\n<li>Prompt patterns and prompt priming<\/li><li>The 6 categories of prompt patterns<\/li><\/ul><\/li><li>Some further prompting approaches\n<ul>\n<li>Least-to-Most and Self-Planning: decomposition of complex tasks<\/li><li>Demonstration &ndash; Task decomposition with Copilot<\/li><li>Unit tests, TDD and GenAI<\/li><li>Demonstration &ndash; Test-based code generation with Copilot<\/li><\/ul><\/li><\/ul><\/li><li>Integrating generative AI into the SDLC\n<ul>\n<li>Using GenAI beyond code generation<\/li><li>Using AI during requirements specification<\/li><li>Prompt patterns for requirements capturing<\/li><li>Prompt patterns for software design<\/li><li>Demonstration &ndash; Requirements capturing and API design with Copilot<\/li><li>Using AI during implementation<\/li><li>Prompt patterns for implementation<\/li><li>Demonstration &ndash; Finding hidden assumptions with Copilot<\/li><li>Using AI during testing and QA<\/li><\/ul><\/li><li>Agentic software development\n<ul>\n<li>Intelligent agents and GenAI\n<ul>\n<li>How is agentic coding different?<\/li><li>The Model Context Protocol (MCP)<\/li><li>Capabilities of MCP agents<\/li><li>Agentic integration in IDEs<\/li><\/ul><\/li><li>Agentic development workflow\n<ul>\n<li>Code-to-spec and spec-to-code with GenAI<\/li><li>Automated scaffolding<\/li><li>Demonstration &ndash; Agentic scaffolding with Copilot<\/li><li>Setting up the runtime environment<\/li><li>Demonstration &ndash; Environment setup with Copilot<\/li><li>Incremental development<\/li><li>Demonstration &ndash; Incremental development with Copilot<\/li><li>The role of MCP in Dev(Sec)Ops<\/li><li>Demonstration &ndash; Using MCP in DevOps with Copilot<\/li><\/ul><\/li><li>Pitfalls and best practices\n<ul>\n<li>&ldquo;Vibe coding&rdquo; and its implications<\/li><li>Engineering concerns with MCP<\/li><li>Security concerns of agentic development<\/li><li>MCP&rsquo;s effect on the attack surface<\/li><li>MCP-specific attack vectors<\/li><li>Demonstration &ndash; Attacking agentic Copilot<\/li><li>Case study &ndash; Database leakage via Supabase MCP<\/li><li>Hallucinations and &lsquo;agentic death spirals&rsquo;<\/li><li>Token limits and context<\/li><li>Context degradation with very large token counts<\/li><li>Prompt engineering vs context engineering<\/li><li>Context engineering from a developer&rsquo;s perspective<\/li><li>Context document examples<\/li><\/ul><\/li><\/ul><\/li><\/ul><h4>Summary and takeaways<\/h4><ul>\n<li>Responsible AI principles in software development<\/li><li>Generative AI &ndash; Resources and additional guidance<\/li><\/ul>","outline":"<ul>\n<li>A brief history of Artificial Intelligence<\/li><li>Responsible AI<\/li><li>Using GenAI responsibly in software development<\/li><li>Summary and takeaways<\/li><\/ul><p>A must-have primer for those looking to understand and responsibly adopt agentic GenAI in their software development projects. Building on these foundations, and depending on the technology stack, we suggest continuing with one of the Generative AI courses - see Agentic software development with generative AI in C++\/Java\/C#\/Python. For those working on machine learning solutions, the comprehensive 4-day Machine Learning Security course offers a natural next step.<\/p>","summary":"<p>Generative AI is reshaping the software industry, moving beyond code suggestions into autonomous, agent-driven development. Tools like GitHub Copilot and MCP-enabled agents can now participate in requirements gathering, design, testing, and deployment &ndash; not just code generation. This evolution sparks both excitement and caution: while productivity gains are clear, new risks around reliability, security, and bias demand responsible use.<\/p>\n<p>This course first introduces participants to the foundations of Generative AI and Responsible AI and then explores how agentic GenAI is changing the software development lifecycle. Participants will study prompting techniques, context engineering, and the integration of AI into requirements specification, design, and testing. A major emphasis is placed on agentic workflows, including automated scaffolding, code-to-spec and spec-to-code transformations, and Dev(Sec)Ops integration via the Model Context Protocol.<\/p>\n<p>Through numerous demonstrations and hands-on labs, participants will gain practical experience with opportunities and pitfalls: from improved productivity and testing support, to challenges such as hallucinations, dangers of &ldquo;vibe coding&rdquo;, and the expanded attack surfaces in agentic systems.<\/p>\n<p>By the end of the course, software engineers and managers will understand both the capabilities and the limitations of Generative AI and especially agentic GenAI, and will be equipped with skills to integrate these tools responsibly into modern software engineering practices.<\/p>","objective_plain":"- Understand various aspects of responsible AI\n- How to use generative AI responsibly in software development\n- Prompt engineering for optimal outcomes\n- How to apply generative AI throughout the SDLC\n- The challenges in using agentic GenaI","essentials_plain":"General development","audience_plain":"All people involved in using agentic AI tools in software development","contents_plain":"A brief history of Artificial Intelligence\n\n\n- The origins of AI\n- Neural networks and \u201cprobability engines\u201d\n- Early ML coding tools\n- The AI coding revolution of the 2020s\nResponsible AI\n\n\n- What is responsible AI?\n- Accountability and transparency\n- Mitigation of harmful bias\n- Validity and reliability\n- Demonstration \u2013 Experimenting with validity and reliability in Copilot\n- Explainability and interpretability\n- Safety, security, privacy and resilience\n- Security and responsible AI in software development\nUsing GenAI responsibly in software development\n\n\n- LLM code generation basics\n- Basic building blocks and concepts\n- Prompt templating\n- System prompts in AI-driven coding\n- Can AI\u2026 boost your productivity?\n- Can AI\u2026 take care of the \u2018boring parts\u2019?\n- Can AI\u2026 be more thorough?\n- Reviewing generated code \u2013 the black box blues\n- The danger of hallucinations\n- The effect of GenAI on programming skills\n- Some further long-term effects of using GenAI\n- Where AI code generation doesn\u2019t do well\n- Prompt engineering\n\n- Why is a good prompt so important?\n- Establishing the context for generative AI\n- Zero-shot, one-shot, and few-shot prompting\n- Reasoning-based prompt engineering, chain-of-thought\n- Demonstration \u2013 Experimenting with prompts in Copilot\n- Enforcing and following token limits\n- Prompt patterns\n\n- Prompt patterns and prompt priming\n- The 6 categories of prompt patterns\n- Some further prompting approaches\n\n- Least-to-Most and Self-Planning: decomposition of complex tasks\n- Demonstration \u2013 Task decomposition with Copilot\n- Unit tests, TDD and GenAI\n- Demonstration \u2013 Test-based code generation with Copilot\n- Integrating generative AI into the SDLC\n\n- Using GenAI beyond code generation\n- Using AI during requirements specification\n- Prompt patterns for requirements capturing\n- Prompt patterns for software design\n- Demonstration \u2013 Requirements capturing and API design with Copilot\n- Using AI during implementation\n- Prompt patterns for implementation\n- Demonstration \u2013 Finding hidden assumptions with Copilot\n- Using AI during testing and QA\n- Agentic software development\n\n- Intelligent agents and GenAI\n\n- How is agentic coding different?\n- The Model Context Protocol (MCP)\n- Capabilities of MCP agents\n- Agentic integration in IDEs\n- Agentic development workflow\n\n- Code-to-spec and spec-to-code with GenAI\n- Automated scaffolding\n- Demonstration \u2013 Agentic scaffolding with Copilot\n- Setting up the runtime environment\n- Demonstration \u2013 Environment setup with Copilot\n- Incremental development\n- Demonstration \u2013 Incremental development with Copilot\n- The role of MCP in Dev(Sec)Ops\n- Demonstration \u2013 Using MCP in DevOps with Copilot\n- Pitfalls and best practices\n\n- \u201cVibe coding\u201d and its implications\n- Engineering concerns with MCP\n- Security concerns of agentic development\n- MCP\u2019s effect on the attack surface\n- MCP-specific attack vectors\n- Demonstration \u2013 Attacking agentic Copilot\n- Case study \u2013 Database leakage via Supabase MCP\n- Hallucinations and \u2018agentic death spirals\u2019\n- Token limits and context\n- Context degradation with very large token counts\n- Prompt engineering vs context engineering\n- Context engineering from a developer\u2019s perspective\n- Context document examples\nSummary and takeaways\n\n\n- Responsible AI principles in software development\n- Generative AI \u2013 Resources and additional guidance","outline_plain":"- A brief history of Artificial Intelligence\n- Responsible AI\n- Using GenAI responsibly in software development\n- Summary and takeaways\nA must-have primer for those looking to understand and responsibly adopt agentic GenAI in their software development projects. Building on these foundations, and depending on the technology stack, we suggest continuing with one of the Generative AI courses - see Agentic software development with generative AI in C++\/Java\/C#\/Python. For those working on machine learning solutions, the comprehensive 4-day Machine Learning Security course offers a natural next step.","summary_plain":"Generative AI is reshaping the software industry, moving beyond code suggestions into autonomous, agent-driven development. Tools like GitHub Copilot and MCP-enabled agents can now participate in requirements gathering, design, testing, and deployment \u2013 not just code generation. This evolution sparks both excitement and caution: while productivity gains are clear, new risks around reliability, security, and bias demand responsible use.\n\nThis course first introduces participants to the foundations of Generative AI and Responsible AI and then explores how agentic GenAI is changing the software development lifecycle. Participants will study prompting techniques, context engineering, and the integration of AI into requirements specification, design, and testing. A major emphasis is placed on agentic workflows, including automated scaffolding, code-to-spec and spec-to-code transformations, and Dev(Sec)Ops integration via the Model Context Protocol.\n\nThrough numerous demonstrations and hands-on labs, participants will gain practical experience with opportunities and pitfalls: from improved productivity and testing support, to challenges such as hallucinations, dangers of \u201cvibe coding\u201d, and the expanded attack surfaces in agentic systems.\n\nBy the end of the course, software engineers and managers will understand both the capabilities and the limitations of Generative AI and especially agentic GenAI, and will be equipped with skills to integrate these tools responsibly into modern software engineering practices.","version":"1.0","duration":{"unit":"d","value":1,"formatted":"1 jour"},"pricelist":{"List Price":{"DE":{"country":"DE","currency":"EUR","taxrate":19,"price":750},"SI":{"country":"SI","currency":"EUR","taxrate":20,"price":750},"AT":{"country":"AT","currency":"EUR","taxrate":20,"price":750},"SE":{"country":"SE","currency":"EUR","taxrate":25,"price":750},"CH":{"country":"CH","currency":"CHF","taxrate":8.1,"price":750}}},"lastchanged":"2025-10-29T08:37:09+01:00","parenturl":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-courses","nexturl_course_schedule":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course-schedule\/36408","source_lang":"fr","source":"https:\/\/portal.flane.ch\/swisscom\/fr\/json-course\/cydrill-raiasd"}}