Webinar: AI-Powered Development: Transformiere deinen Workflow mit Coding Tools und MCP Servern

Künstliche Intelligenz ist zu einem zentralen Bestandteil moderner Softwareentwicklung geworden und verspricht enorme Produktivitäts- und Effizienzgewinne. Doch gerade für Entwicklerinnen und Entwickler – insbesondere im Umfeld moderner Frameworks – sorgt die Vielzahl an verfügbaren AI-Tools und großen Sprachmodellen häufig eher für Verwirrung als für Klarheit. Ständig wechselnde APIs, sich wandelnde Standards und dynamische Kundenanforderungen erschweren die effektive Nutzung zusätzlich und führen bei Tools wie GitHub Copilot, Cursor oder Windsurf oft zu Frustration und suboptimalen Ergebnissen.

In diesem Vortrag führe ich dich durch die aktuelle AI-Tool-Landschaft und zeige, welche Lösungen in der realen Entwicklungspraxis tatsächlich einen Mehrwert bieten. Du lernst praktische Strategien kennen, um AI-Tools sinnvoll in deine Workflows zu integrieren, und erhältst Einblicke in ihre Grenzen und potenzielle Fallstricke. Nach dieser Session bist du in der Lage, AI-Tools gezielt einzusetzen, um deine Entwicklungsprozesse nachhaltig zu optimieren und zu vereinfachen.

Transcript

1. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Daniel Sogl @sogldaniel Software architect
2. Transform Your Workflow with Coding Tools and MCP Servers AI-Powered Development
3. Daniel Sogl • Software architect @ Thinktecture AG • Focus: Angular and Generative AI • Socials: https://linktr.ee/daniel_sogl About me Transform Your Workflow with Coding Tools and MCP Servers AI-Powered Development
4. Accelerate development: generate boilerplate code instantly Improve quality: AI can suggest best practices or detect issues Focus on logic: reduce time spent on repetitive tasks Documentation, tests, configs - automated AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Why use Generative AI for software development?
5. Can produce incorrect or insecure code Output must always be reviewed by humans Lacks true understanding of project context Legal/ethical questions: IP, licensing, data privacy AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Limitations and risks
6. • AI reduces critical thinking and problem-solving skills in the long term • Danger of cognitive laziness - “automation bias” • Blind trust in AI results increases the risk of errors AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Cognitive offloading
7. The promises • Developers complete tasks 26% faster (MIT, 2023) • Coding tasks are on average 55% faster (GitHub, 2024) The (current) reality • AI-generated code with security vulnerabilities: 44% (Stanford, 2025) • Code duplicates increased by a factor of 4 after AI deployment (GitClear, 2024) AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Productivity claims over productivity claims https://mitsloan.mit.edu/ideas-made-to-matter/how-generative-ai-affects-highly-skilled-workers https://github.blog/news-insights/research/research-quantifying-github-copilots-impact-in-the-enterprise-with-accenture https://ee.stanford.edu/dan-boneh-and-team-find-relying-ai-more-likely-make-your-code-buggier https://www.gitclear.com/ai_assistant_code_quality_2025_research
8. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers
9. Transform Your Workflow with Coding Tools and MCP Servers AI-Powered Development
10. Why coding tools fail to support you • LLMs were trained on older data • LLMs don’t understand your architecture without help • LLMs don’t know your company domains • LLMs don’t know your coding standards • Developers don’t write prompts describing every edge case or needed context to solve tasks • Different tasks require different context AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Limitations of LLMs
11. Context. Context. Context. • We can define so-called custom instructions to provide extra context to all Copilot actions • A custom instruction is a markdown file with rules, instructions and guidelines defined by developers • Custom instructions can be added in a fine-grained way to specific file types • Custom instructions are part of a project and can be shared with all other developers • This pattern can also be used with Cursor, Windsurf, Claude Code or Gemini CLI Info: There is currently no unified format supported by all tools - you need to create separate configuration files for each tool individually AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers How to solve that problem?
12. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Custom instructions example
13. Usage with Copilot • Copilot knows two types of instruction files • Global instructions: copilot-instructions.md • Fine-tuned instructions: custom.instructions.md • Instructions can be scoped so they are included for defined file types such as *.ts, *.html, *.css • Instructions can also be scoped for Copilot specific tasks like generating commit messages, generating tests or reviewing code • This pattern also works with other tools like Cursor or Windsurf Tip: Keep your instructions short. Each condition will be part of your context window AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Custom instructions hierarchy
14. • Custom instructions can be generated based on your current project architecture and existing files • Let the AI tool analyze your project • Use an example instructions file as reference • Generate instructions for your architecture, dependencies, best practices and code style with the help of the AI tool, adding extra context – for example, your ESLint file • Use predefined instructions • https://codingrules.ai • https://angular.dev/ai/develop-with-ai • https://www.cursordirectory.com • https://github.com/github/awesome-copilot AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers How to create custom instructions
15. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers
16. Fragmented AI Landscape: Multiple AI providers with different APIs, authentication and response types Complex Integration: Context management, tooling and response handling are challenging Security: Access control, 3rd party providers, private data can’t be accessed or shared AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Why MCP matters
17. The key for ”intelligent” workflows • Open-source protocol developed by Anthropic • Provides a consistent way for LLMs to interact with external resources • Client-Server architecture: AI applications (clients) request context from external services (servers) • Official servers are available for GitHub, Atlassian, Playwright, Stripe, Databases and more • It’s the key to useful AI-coding setups in complex environments AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Model Context Protocol (MCP)
18. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers MCP workflows Developer asks: “Explain failing tests in PR #42.” Copilot calls GitHub MCP → fetches PR diff + CI log LLM reviews context → returns root-cause & fix steps Dev clicks “Apply fix” → Copilot edits code & opens new PR
19. • Microsoft verified MCP Servers for Agent Mode: https://code.visualstudio.com/mcp • MCP GitHub Repo: https://github.com/modelcontextprotocol/servers • Awesome MCP Server: https://github.com/punkpeye/awesome-mcp-servers • MCP Collection: https://glama.ai/mcp • Official provider websites like Atlassian, GitHub or PayPal AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers How to find MCP servers?
20. GitHub MCP – connect to the GitHub API Atlassian MCP – connect to the Atlassian API (Jira, Confluence) Playwright MCP – control the browser Context7 – fetch library documentations (Angular, React, .Net) Perplexity MCP – search for web content File System MCP – access local file system Memory MCP – share memories between sessions and clients AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers MCP server recommendations
21. • Not all LLMs are equal: Performance varies widely • Understand reasoning vs. non-reasoning models • Context size matters greatly in coding scenarios • Benchmarks help guide practical model choice • Cost per 1 million input/output tokens AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Choosing the right LLM for your tasks
22. Reasoning • Chain-of-thought: Write internal planning steps before generating answers • Tool calls: Actively fetch data or run tools during generation • Self-reflection: Score multiple solution paths and choose the best one • Best for: Debugging, complex algorithms, architectural analysis • Examples: GPT-4o, Claude 4 (Sonnet, Opus) Non-Reasoning • Direct token prediction: Output tokens without internal planning • Optimized for: Fast code completions, simple tasks, boilerplate generation • Examples: GPT-4.1, Gemini 2.5-Flash AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Reasoning vs. Non-Reasoning LLMs
23. • Determines how much code/context an LLM can handle simultaneously. • Larger context → easier multi-file refactoring, whole-project reasoning. • Example contexts: • Small (~4k tokens): Single file, short functions. • Medium (16k–32k): Full modules, long functions. • Large (100k+): Entire repositories, API docs, complex integrations. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Why context size matters
24. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Popular LLMs for software development Model Provider Reasoning Context Window SWE-bench $ / 1M tokens Claude 4 Opus Anthropic 200k tokens 72.5 % $15 / $75 Claude 4 Sonnet Anthropic 200k tokens 72.7 % $3 / $15 GPT-4.1 OpenAI 1M tokens 54.6 % $2 / $8 GPT-o3-mini (high) OpenAI 200k tokens 49.3 % $1.10 / $4.40 Gemini 2.5 Pro Google 1M tokens 63 % $1.25 / $10 DeepSeek V3 DeepSeek 163k tokens 38.3 % $0.25 / $0.85 Grok 4 xAI 256k tokens 72 % $3 / $15 Kimi K2 Moonshot 131k tokens 65.8 % $0.13 / $0.13
25. Which LLM Should You Choose Use Claude 4 or Grok 4 for high-quality coding tasks Use Gemini 2.5 Pro for large context + Google ecosystem Use Kimi K2 for small tasks to save money Use reasoning models when debugging, planning, or testing Pay attention to context size for repo-scale automation Refer to benchmarks for grounded comparison Compare prices and premium request counters AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Practical recommendations
26. • AI tools promise enormous productivity gains, but the current reality looks frustrating • Expectations for an LLM are either too high or too low • Developers must understand the limitations of LLMs and the AI tooling behind them • Add as much relevant context to your prompts as possible to help the LLM understand your goals • Specify custom instructions to document your architecture, framework specific rules and coding styles • Expand the available context with the help of MCP servers • Validate generated code and refine your tools and rules based on the results • Checkout my demo project: https://github.com/danielsogl/copilot-workflow-demo AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers Conclusion
27. AI-Powered Development Transform Your Workflow with Coding Tools and MCP Servers The best developers won’t be replaced by AI, they’ll be the ones who learn to wield it
28. Thanks for your attention Daniel Sogl @sogldaniel daniel.sogl@thinktecture.com