Skip to content
Agentic Levels
  • New to AI?
  • Assessment
  • Levels
  • Lessons
  • Tracks
  • Resources
  • Reference
  • What's New
  • What's Next
  • More
    Tool SetupCompareAboutThanksFAQPricingPreferences
  • New to AI?
  • Assessment
  • Levels
  • Lessons
  • Tracks
  • Resources
  • Reference
  • Tool Setup
  • Compare
  • What's New
  • About
  • Thanks
  • FAQ
  • What's Next
  • Pricing

© 2026 Fuentes Studio·Privacy·Terms

yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

What's New

Product changes and workflow shifts mapped to your level. Filter to see only what matters for where you are, then follow the guidance on the interfaces page when you need the operating pattern behind the feature.

How to use Claude Code updates

Start here for the shortest path: what changed recently, which shifts affect your current tool, and what to learn next.

Claude Code Focus

Watch the execution primitives

For Claude Code, product changes matter most when they alter how the agent can execute, remember, or orchestrate work inside the repo.

Memory + command updates

Anything that changes CLAUDE.md, slash commands, or skills affects day-to-day leverage immediately.

Hooks, MCP, sub-agents

These are the features that move you up the ladder by changing what the system can actually do.

Review hooks docs →
Model + SDK changes

Track them when they change reliability, headless execution, or automation surfaces you depend on.

Current Track

Claude Code updates

Showing the latest official product updates and workflow-relevant notes for Claude Code. Use the feed when you want to compare across systems.

May 2026Claude
Feature

Google Labs Releases design.md

Google Labs published design.md, an open-source pipeline that analyzes any public URL and outputs a structured DESIGN.md file with color tokens, fonts, spacing values, and component patterns. For Levels 2-4, this turns the reference-site-to-design-brief workflow into a repeatable pipeline instead of a manual analysis session.

L2L3L4
Read more →
Mar 2026Claude
Feature

Computer use research preview in Cowork and Claude Code + Dispatch improvements

Anthropic brought computer use into Cowork and paired it with stronger Dispatch flows. For Levels 4-6, this is the moment Claude shifts from advising you to actually driving local work on your behalf when the task is scoped well.

L2L3L4L5
Read more →
Mar 2026Claude
Feature

Computer Use in Cowork and Claude Code plus Dispatch Improvements

Anthropic added computer use to Cowork and Claude Code and paired it with stronger Dispatch flows. For Levels 4-6, this is the shift from Claude advising you to Claude operating a machine on your behalf when the task is scoped well.

L4L5L6
Read more →
Mar 2026Claude
Feature

Control Cowork from your phone with a persistent thread (research preview for Pro/Max)

Anthropic extended Cowork with persistent remote control from mobile and Dispatch. For Levels 3-5, this matters because long-running delegated work no longer has to stay tied to one desktop session.

L2L3L4L5
Read more →