Sponsored Session: Hands Off the Keyboard: An Introduction to Agentic Coding for GraphQL Developers
summary
Argues that the fix for wrong AI code is not hand editing but improving prompts and codifying those lessons as markdown skills that capture specific schema rules, resolver conventions and CI checks. Shows Apollo’s downloadable project vs general skills distinction, explains a demand driven workflow that turns an iterative 99% result into a 99% to 100% fix by dialogue, then baking that conversation into a skill, and demos a hands‑free HTML/CSS slide deck and CI integration.
AI-written summary · about
chapters (15)
- 0:00Introduction and welcome
- 1:03AI and human expertise paradox
- 3:07Retrospectives and accountability
- 5:34GraphQL as deterministic layer
- 7:19AI and distributed software patterns
- 8:23The 99% problem with AI
- 9:46Agent skills as solution
- 13:15General vs project skills
- 15:02How to build project skills
- 18:11Delegating work to AI
- 20:19AI and human collaboration
- 21:44Evolving skills into team processes
- 22:46Ownership cannot be delegated
- 23:06Hands off the keyboard advice
- 23:51Q&A session
related talks
45mPanel Discussion on AI for Code Generation
29mClosing the Loop: How GraphQL Gives Coding Agents Eyes on What Actually Matters
51mCode Smarter, Not Harder: AI-Powered Dev Hacks for All
27mAgentic Engineering: Working With AI, Not Just Using It
27mAgentic Coding with Discipline & Skill: Practical Techniques and Tips
18m"Software Fundamentals Matter More Than Ever"
01h 02mSkills for the age of AI developer tools
35mAgentic coding