Anatoli Kopadze

Anatoli Kopadze · Launch Video Breakdown: Hook, Pacing & Motion Design

the engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work I've seen $300 courses that don't cover what he shows in the first 10 minutes CLAUDE.md…

Developer ToolsLaunchJune 9, 2026@AnatoliKopadze
0:00 · The Hook · Installation & Initial Setup
0:00 / 0:00

Scene-by-scene timeline & spoken transcript

  1. The Hook

    Installation & Initial Setup

    “(No spoken dialogue — Driving electronic rhythm and ambient sound design.)”

    On screen
    Follow along: npm install -g @anthropic-ai/claude-code
    Camera
    Wide shot of presenter on stage with a large screen displaying code. Camera slowly zooms in.
    Motion
    Subtle zoom, static text overlay.
  2. Product Reveal

    Claude Code Core Functionality

    “um but also because it can do so much asking questions to your codebase something that I do a lot also a little bit more what can be one shot it”

    On screen
    Use Claude Code to answer questions about your codebase 1 The easiest way for new users to start with Code 2 Zero setup needed 3 Your data stays local Example prompts: > How is @RoutingController.py used? > How do I make a new @app/services/ValidationTemplateFactory? > Why does recoverFromException take so many arguments? Look through git history to answer > Why did we fix issue #18383 by adding the if/else in @src/login.ts API? > In which version did we release the new @api/ext/PreHooks.php API? > Look at PR #9383, then carefully verify which app versions were impacted > What did I ship last week? Code w/ Claude
    Camera
    Alternates between medium shot of presenter and wide shot of presenter with screen. Screen content changes dynamically.
    Motion
    Dynamic text reveal, cursor animation, content slide transitions.
  3. Feature Teaser

    Advanced Workflows & Context Management

    “but Quantum d is pulled in automatically so maybe I have an enterprise policy I'll usually just switch into auto accept mode if you hadn't played around with this so I'll have usually like one quad running at a time”

    On screen
    Common workflows Explore > plan > confirm > code > commit > Figure out the root cause for issue #983, then propose a few fixes. Let me choose an approach before you code. ultrathink Write tests > commit > code > iterate > commit > Write tests for @utils/markdown.ts to make sure links render properly (note the tests won't pass yet, since links aren't yet implemented). Then commit. Then update the code to make the tests pass. Write code > screenshot result > iterate > Implement [mock.png]. Then screentshot it with Puppeteen and iterate till it looks like the mock. Give Claude more context Auto-add common bash commands, files, and style conventions to every session: * </enterprise root>/CLAUDE.md Shared across all projects * ~/.claude/CLAUDE.md Shared across all projects * project-root/ * CLAUDE.md Checked in * CLAUDE.local.md Not checked in (Shortcut: type #) Give Claude more context Pull in context on demand: * ~/.claude/commands/foo.md Type /user:foo * project-root/ * .claude/commands/foo.md Type /project:foo * a/ * commands/foo.md Type @a * CLAUDE.md Pulled in on demand * foo.py Type @a/foo.py claude commands create-release-pr.md fix-github-issue.md get-feedback.md label-github-issues.md lint.md settings.json settings.local.json Share permissions, memory, and MCP servers with your team Enterprise policy Global (just me) Project (checked in) Project (just me) Welcome to Claude Code! Memory Files L managed: /Library/Application Support/ClaudeCode/CLAUDE.md L user: ~/.claude/CLAUDE.md L project: CLAUDE.md L vendor/CLAUDE.md Learn more: https://docs.anthropic.com/en/docs/claude-code/memory Select memory to edit: > Project memory Checked in at ./CLAUDE.md > Project memory (local) Gitignored in ./CLAUDE.local.md > User memory Saved in ~/.claude/CLAUDE.md > [ANT-ONLY] Ultra memory Critical instructions in ~/.claude/ULTRACLAUDE.md 38 memories in ./CLAUDE.md Interlude: Keybindings Key combos for common tasks: 1 Shift+tab to auto-accept edits 2 # to create a memory 3 ! to enter bash mode 4 @ to add a file/folder to context 5 Esc to cancel 6 Double-esc to jump back in history, --resume to resume 7 ctrl-r for verbose output 8 /vibe Claude Code SDK Use the SDK for programmatic, low-level access to Claude Code Useful for CLI and non-interactive contexts, automation, and building block for interactive apps Currently supports CLI (TypeScript) & Python SDKs coming soon! $ claude -c \ "what did I do this week?" \ --allowed-foils $(git log -r)\ --output-format json Your agentic application Claude Code SDK Anthropic, Bedrock, or Vertex API Claude models Interlude: Multi-claude There are many ways to run more claudes in parallel: 1 Use multiple checkouts in separate terminal tabs 2 Use one checkout with git worktrees 3 SSH + TMUX 4 Github Actions, launch jobs in parallel
    Camera
    Dynamic cuts between presenter and screen. Screen content features various code snippets, diagrams, and lists.
    Motion
    Rapid content changes, list item reveals, diagram animations, subtle camera pans.
  4. Call to Action

    Q&A and Future Outlook

    “and it can change system state in unexpected and some people use VS code”

    On screen
    Q+A
    Camera
    Close-up on presenter, then wider shot of presenter on stage with a 'Q+A' overlay.
    Motion
    Static text overlay, direct address to camera.

Related Developer Tools Product Launches

Explore all Developer Tools launches →
SpaceXAI
Hook 8.9204.0M
SpaceXAIDeveloper Tools

xAI opens voice cloning on its API: build a custom voice in about two minutes or pick from 80+ voices in 28 languages.

@SpaceXAI
Claude
Hook 9.178.3M
ClaudeDeveloper Tools

Claude can now operate your Mac, opening apps, browsing and filling spreadsheets, as a research preview in Cowork and Claude Code.

@claudeai
xAI
Hook 8.873.2M
xAIDeveloper Tools

Agentic CLI for coding, building apps, and automating workflows.

@SpaceXAI