The Continued Developer Evolution
summary
Claims that AI agents speed up development but do not replace developers, backed by concrete demos: a Pac-Man+Snake game built from a single prompt with iterative fixes, and a CRUD Flask app where an agent adds a delete feature and tests pass. Tools named: Amazon Q developer plugin, Kira, QD, Strands, Pedantic AI, MCP and A2A. Problems and practices called out: token theft, checkpointing and spec-driven flows. Worth watching if wanting hands-on agent workflows and mitigation tactics.
AI-written summary · about
chapters (12)
- 0:00Welcome
- 1:04AI-assisted coding journey
- 4:56Software craftsmanship evolution
- 7:26Code to prompts
- 8:29AI CRUD demo
- 12:49AI replacing developers myths
- 15:34Jevons paradox and demand
- 17:01AI-assisted challenges
- 19:53Spec-driven workflows
- 22:00Human craftsmanship value
- 23:05Experienced developers value
- 24:27Q&A
related talks
26mAI Agents as Your Co-Developer
59mFrom Pair to Peer Programmer
14mThe 4 Patterns of AI Native Development
30mBuilding Tools with Tools: Modern AI-Driven Development
25mThe Ai-Assisted Developer Workflow: Build Faster and Smarter Today
14mAgent-Driven Software Development
01h 02mSkills for the age of AI developer tools
29mPairing with the machine: How AI Agents are rewriting the rules of software development