301 - The AI coding ladder

Most folks reference "AI coding" like it's one thing. It's really not. In this foundational episode Kaushik & Iury walk through (at least) four paradigms — from super autocomplete to agent orchestration — each with different workflows, expectations, and mental models.

What do most developers follow today? Where is the frontier? What's coming in the future?

Listen to the episode and find out!

Full shownotes at fragmentedpodcast.com.

Show NotesGen 1: Super autocomplete

• Intellisense - regular autocomplete
• Github Copilot
• Cursor Tab

Gen 2: Chat Oriented Programming

• Cursor IDE
• Firebender

Gen 3: Agent

• Nvidia's definition of an Agent
• ReAct Prompting
• Chain of Thought was a prompting hack
• DeepSeek
  • DeepSeek - R1 paper
• TUI tools (or Harnesses):
  • Claude Code
  • Open Code
  • Codex Cli
  • Gemini Cli
• IDE style tools
  • Cursor Agent
  • Copilot (MS)
  • Junie - Intellij
  • Antigravity - Google
• Headless Tools:
  • Jules - Google
  • Claude Code on the Web
  • Codex Web

Gen 4: Agent Orchestration

• Git worktrees

Tips

• Iury: Transfer between agents using your own compact command
• KG: Ask the agent to clarify your prompt

Confirm if my requirements are clear. If you have follow up questions, ask mefirst and clarify before executing anything.

Contact us

• Newsletter
• Website
• Contact us
• Youtube

Co-hosts:

• Kaushik Gopal
• Iury Souza