Workshop Video: Agentic AI SDD with Cursor IDE
Mentor - Viacheslav Koldovskyy, Competence Manager at SoftServe
Master Agentic Spec‑Driven Development in Cursor and learn to confidently use LLM tools, agents, and the GitHub Spec Kit in real-world projects. In two sessions, you'll go from PRD to specifications, design, and implementation, and understand the cost and risk assessment of working with agents.
In the course you will:
- Understand the capabilities and limitations of LLM: model comparison, tokenization, context window, hallucinations, safety.
- Learn about agent-driven development: tools, agent mode, MCP, security, costs and limitations.
- Understand the SDD approach: what is Spec-Driven Development and what tools to use (GitHub Spec Kit, Kiro, etc.).
- Configure Cursor for the agent-driven SDD approach: project initialization, PRD, rules for interacting with the model.
- Convert PRD into specifications and proceed to design and implementation.
- Learn to validate solutions and close the full cycle: "specifications → code → verification".
Mentor - Vyacheslav Koldovskyy, Competence Manager at SoftServe, 20+ years in IT, Certified Google Cloud Professional Cloud Architect, nVidia Generative AI LLMs
Course result
- Practical skills in working with SDD in Cursor
- Understanding the architecture of agents and MCPs, as well as their limitations and costs
- Ability to work with GitHub Spec Kit and build specifications based on PRD
- Clear a framework for moving from requirements to code with quality validation
Format:
Materials: Video recording of the workshop (5 hours) and a presentation with a selection of materials
Language of the event: Ukrainian
After purchasing a ticket, refresh the page and you will see the video recording and all materials.
Language of the presentation: English
Who will be interested?
- Developers of all levels and tech leads who want to accelerate projects with SDD and agents.
- DevOps/SRE and performance engineers – for integrating agents into the SDLC.
- QA/Automation – for describing specifications and quality validation.
- Mentors, team leads, and Engineering Management specialists who standardize development processes.
Program
Session 1: Agentic Development Theory and SDD
- Introduction to the features and use of LLM in development: model comparison, estimating code size in tokens, context window limitations, hallucinations, license purity.
- Development with AI agents - features and limitations: overview of available tools, working in agent mode, MCP, advantages/disadvantages of using agents, cost estimation, security and vulnerability issues.
- Introduction to SDD – concept and tools: GitHub Spec Kit, Kiro, other alternatives.
- Q&A
Session 2: Practical SDD in Cursor
- Preparing the IDE for work – important settings.
- Initializing the project, forming the PRD, setting the rules for interaction with model.
- Initialize GitHub Spec Kit, convert PRD to specifications.
- Move from specifications to design and implementation.
- Validate the solution and close the loop.
- Q&A
The course concept and all course materials are the intellectual property of FWDAYS. Copying the course content and materials is possible only with the consent of FWDAYS.
Mentor: Viacheslav Koldovskyi
— Competence Manager at SoftServe
— 20+ years in IT, certified Google Cloud Professional Cloud Architect, nVidia Generative AI LLMs
— Ph.D / Candidate of Economic Sciences, Associate Professor, Head of the Gen AI Center at IT STEP University
— Founder of YouTube and Telegram channels Programming Mentor
— Active speaker: speaking at iForum, DOU Day, etc.
— Leader of the AI community at DOU, author of publications
— Has implemented projects with Gen AI and AI-generated code, which successfully working in production
— Advises companies on transforming SDLC processes using AI
Event price
Presentation and materials
Access to the video recording of the workshop (5 hours)
Participants receive a 10% discount on participation in Fwdays conferences