George Moreas.George MoreasGeorge MoreasGeorge Moreas.George Moreas.AI · Search · Automation
ExperienceInsights
George Moreas / Field notesKnowledge graph
All insights
  • AI DevelopmentAgents, evaluations and reliable delivery11
  • AI EconomicsCost, capacity and accepted outcomes10
  • Future of WorkHuman judgment in an agent-driven workplace9
  • Web & AI SearchDiscovery, answers and connected knowledge39
  • AccessibilityIndependent access and usable experiences4
  • Product StrategyBetter bets, sharper choices, real evidence6
  • Privacy & TrustData boundaries, provenance and accountability4
Seven fields. Connected ideas.
Start with a better question.
  • 01 / Product Strategy
    When Building Gets Cheap, Product Judgment Gets Expensive

    Claude Code expands the space of possible products. The differentiator is no longer a convincing specification—it is choosing, testing and shipping the right experience.

    8 min read · interactive
  • 02 / Future of Work
    More Agents. One Person Who Signs Off.

    Leaders are using AI more often, but adoption is not ability. As execution accelerates, accepted work—not generated output—becomes the real productivity measure.

    8 min read · interactive
LabLabLab
Now showing41 live experiments
  • Murmuration
  • Turing Patterns
  • The Sandpile
  • Fireflies
  • Every Drawing Is Circles
  • What Sorting Sounds Like
All experiments
Let’s talk
ExperienceInsightsResumeLet’s talkLabLabLabMurmurationTuring PatternsThe SandpileFirefliesEvery Drawing Is CirclesWhat Sorting Sounds Like
Read the field notes
← AI knowledge base/Agent tooling & protocols

Plan mode

A Claude Code mode in which the agent researches and proposes a plan without editing files until the user approves.

Part of
Claude Code

Connected

  • Claude CodeAnthropic's agentic coding tool that reads a codebase, edits files, runs commands and verifies its work from the terminal, IDE or web.

More agent tooling & protocols

  • agent-html-kitAn open-source template kit and Claude Code skill (kit.js) that lets agents emit content-only HTML components while design lives in one shared file, published with a 72-run HTML vs Markdown benchmark.
  • CLAUDE.mdA Markdown file of standing instructions that Claude Code loads at the start of every session, at user, project and folder level.
  • Karpathy-inspired CLAUDE.md rulesA widely starred public CLAUDE.md with four behaviour rules: think before coding, simplicity first, surgical changes and goal-driven execution.
  • AGENTS.mdAn open, tool-neutral Markdown convention for giving coding agents project instructions, introduced by OpenAI in August 2025 and now stewarded by the Linux Foundation's Agentic AI Foundation.
  • Claude Code hooksShell commands that Claude Code runs automatically at lifecycle events such as before or after a tool call, so rules can be enforced by code rather than requested in prose.
  • Claude Code subagentsSpecialised agents with their own instructions, tools and context window that the main Claude Code session can delegate tasks to.

Sources

  • Primary documentation
GM.
George Moreas.

Senior product leader and hands-on AI builder writing about search, automation, ecommerce, and the systems changing how companies operate.

moreas.george@gmail.com
Boca Raton, FL

Read the latest field notes →
Explore
  • All insights
  • AI development
  • Search & AI visibility
  • Knowledge graph
  • AI knowledge base
  • Resume
Site
  • Blog
  • Glossary
  • The Lab
  • About
  • LinkedIn ↗
  • Privacy
© 2026 George Moreas · Boca Raton, FLIndependent field notes from a working product builder.