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.

Agentic Lessons

One lesson per level. Start at yours.

L0Standalone

AI Is Not a Search Engine

What these tools actually do behind the scenes

6 minFree
L1Standalone

Your First Productive AI Conversation

Stop testing. Start asking real questions

5 minFree
L2Standalone

Building a Tab Complete Habit

From occasional use to daily instinct

6 minFree
L3Standalone

Thinking in Agentic Sessions

How to structure your work for AI-assisted output

6 minFree
L4Standalone

Context Engineering Fundamentals

Your context window is RAM. Treat it like it.

6 minFree
L5Standalone

Scaling Context Across Projects

Managing what the model knows at scale

6 minFree
L6Standalone

Compounding Engineering Patterns

How your workflow gets faster every week

6 minFree
L7Standalone

How MCP Servers Work

Tools your AI can actually call

6 minFree
L8Standalone

Harness Engineering 101

Building systems that make AI reliable

6 minFree
L9Standalone

Running Background Agents

Async AI work that doesn't need you watching

6 minFree
L10Standalone

Designing Autonomous Teams

Multi-agent systems that coordinate on their own

6 minFree
L0Sprint

Your First Useful Output

After this, you'll be able to get a useful, specific response from AI on your first real task.

12 min
L0Sprint

Context Is Your Superpower

After this, you'll be able to write a context-rich prompt that gets a noticeably better response than a vague one.

15 min
L0Sprint

What AI Can't Know (And How to Check)

After this, you'll be able to identify which parts of an AI response to trust and which to double-check.

12 min
L0Sprint

Tell Claude Who You Are

After this, you'll be able to set up a personal profile so your AI tool already knows who you are at the start of every conversation.

15 min
L0Sprint

Ask Claude to Remember Things

After this, you'll be able to ask Claude to remember specific things so you don't have to repeat yourself each session.

12 min
L1Sprint

Ask Like a Real Human

After this, you'll be able to write a prompt that gives Claude enough context to respond the way a helpful colleague would.

12 min
L1Sprint

The Refinement Loop

After this, you'll be able to read a Claude response critically and do one targeted follow-up that makes the output significantly better.

14 min
L1Sprint

When to Switch Tools

After this, you'll be able to decide in under ten seconds whether to use Claude, ChatGPT, or Google for a given task.

12 min
L1Sprint

Find Your Daily Use Tipping Point

After this, you'll have identified one recurring task in your week that you can start delegating to Claude today.

15 min
L1Sprint

Set Up Your Persistent Workspace

After this, you'll have a one-time setup in your AI tool of choice that tells it who you are and how you want responses, so you never have to repeat yourself again.

13 min
L2Sprint

Write Stubs the Model Can Finish

After this, you'll be able to write function stubs that reliably produce useful inline completions, instead of vague or wrong ones.

14 min
L2Sprint

Read Before Tab

After this, you'll have a five-second scan habit that catches near-miss completions before they make it into your codebase.

12 min
L2Sprint

Pre-Load the Context

After this, you'll know how to arrange open files before you start completing, so the model has the types and patterns it needs to produce usable suggestions.

13 min
L2Sprint

Graduate to Chat

After this, you'll be able to identify when tab-complete is the wrong tool for your task and make the switch to chat for multi-file or decision-requiring work.

15 min
L2Sprint

Share a Document with Claude

After this, you'll be able to drop any document into Claude and ask focused questions that get you the specific answer you need, not a summary of everything.

14 min
L2Sprint

Know What Claude Sees in Your File

After this, you'll be able to tell in advance whether a file will give Claude useful text or just a picture of text, and fix it before you upload.

13 min
L2Sprint

Edit Without Rewriting

After this, you'll be able to ask Claude for surgical changes to an uploaded document, so you get the specific edit you need without Claude rewriting everything else.

15 min
L3Sprint

Tell the Model What to Look At

After this, you'll be able to use @ context references to point the model at the exact files it needs, so your answers are grounded in your actual code instead of a guess.

16 min
L3Sprint

Plan Before You Code

After this, you'll be able to use plan mode to catch a model misunderstanding before it edits a dozen files, saving you the cost of undoing confident but wrong changes.

17 min
L3Sprint

Write Your First CLAUDE.md

After this, you'll have a working CLAUDE.md with your first five project-specific rules, each written from a real mistake rather than speculation.

18 min
L3Sprint

Do Not Stuff CLAUDE.md

After this, you'll be able to distinguish rules that belong in CLAUDE.md from context that belongs in the chat, and keep your rules file lean enough to actually work.

15 min
L4Sprint

Audit Your Token Budget

After this, you'll be able to count what's actually eating your context window and trim it by at least 30% without losing anything that matters.

20 min
L4Sprint

Prune Like a Pro

After this, you'll be able to identify context poisoning in a failing session and fix it by removing content rather than adding more.

20 min
L4Sprint

Write a CLAUDE.md That Earns Its Tokens

After this, you'll have a CLAUDE.md that prevents your most common recurring mistakes without wasting tokens on things Claude already knows.

22 min
L4Sprint

Trust No Retrieved Document

After this, you'll be able to explain prompt injection through retrieved content and apply one practical defense to any agent or search-augmented workflow you build.

22 min
L4Sprint

Checkpoint and Clear

After this, you'll be able to use /clear and session checkpoints as a deliberate workflow rhythm, not just a panic button when things go wrong.

18 min
L5Sprint

Build Your First RAG Pipeline

After this, you'll have a working RAG pipeline on a real document set, and you'll be able to measure whether your retrieval is actually returning relevant chunks.

22 min
L5Sprint

Structured Output as Contract

After this, you'll be able to enforce structured output from any prompt that feeds a downstream system, using the right tool for the job: JSON mode, XML tags, or schema validation.

20 min
L5Sprint

Retrieve vs Fit: The Decision Rule

After this, you'll be able to apply a concrete decision rule to any document or dataset and choose between retrieval and full-context loading without guessing.

18 min
L5Sprint

Label Your Sources, Block Injection

After this, you'll be able to build a multi-source context pipeline that maintains provenance through the full turn and defends against prompt injection in retrieved content.

22 min
L6Sprint

The Codify-Loop

After this, you'll run the plan-delegate-assess-codify loop as a reflex, ending every significant session with at least one new rule written from a real observation.

18 min
L6Sprint

Track Three Numbers

After this, you'll be measuring acceptance rate, iteration count, and codification rate weekly, and you'll know what a compounding trend looks like versus an accumulation plateau.

16 min
L6Sprint

Prune the Rules File

After this, you'll be able to run a structured audit of your CLAUDE.md, identify stale and conflicting rules, and delete at least 20% of the file without losing anything that matters.

20 min
L6Sprint

Session Log vs Rules File

After this, you'll maintain two separate artifacts from every session: an append-only session log of what you tried and decided, and a CLAUDE.md that contains only durable rules.

22 min
L7Sprint

Wire Your First MCP

After this, you'll be able to install a real MCP server, connect it to your agent, and complete one actual task using it.

20 min
L7Sprint

Read a Tool Schema Like the Model Does

After this, you'll be able to read an MCP tool schema and predict when the model will (and will not) call each tool, then write your own 3-tool schema for a domain you know.

22 min
L7Sprint

Package Your First Skill

After this, you'll be able to turn a repeatable 3-step workflow into a named skill the agent invokes consistently, and audit it for least-privilege.

25 min
L7Sprint

Trust No Tool Response

After this, you'll be able to identify prompt injection through MCP tool responses and apply the wrap-and-label defense to any workflow where Claude reads external content.

22 min
L7Sprint

Track Cost Per Iteration

After this, you'll be able to measure the token cost of a skill or MCP workflow, identify the expensive steps, and restructure the sequence to front-load cheap validation before costly generation.

18 min
L8Sprint

Build the Inner Loop

After this, you'll be able to wire a feedback loop where the agent runs tests, reads the result, and fixes failures without you intervening at every step.

20 min
L8Sprint

Spec-as-Test

After this, you'll be able to write the expected output before the agent runs, verify the agent's output against that spec, and distinguish this from unit tests and model evals.

22 min
L8Sprint

Add Structured Logging

After this, you'll be able to instrument an agent run with structured JSON logs and a trace ID, then read a trace to find the real failure point in 90 seconds instead of 30 minutes of manual debugging.

22 min
L8Sprint

Build the Checkpoint and Replay

After this, you'll be able to add a checkpoint to an agent workflow so that a failure at step 8 of 10 does not restart from step 1, and verify that the resume path actually works.

20 min
L8Sprint

Define the Blast Radius

After this, you'll be able to classify any task into one of three risk tiers, add appropriate approval gates for higher-risk operations, and describe exactly what would happen if an unsupervised step went wrong.

18 min
L8Sprint

Your First Background Agent

After this, you'll be able to kick off one low-risk task as a background agent, verify the output when it finishes, and use a git worktree so the agent works in isolation.

25 min
L9Sprint

Cross the Diff-vs-Code Threshold

After this, you'll be able to identify whether you've crossed the threshold where reviewing an agent's diff is cheaper than writing the code yourself, and calibrate your trust accordingly.

20 min
L9Sprint

Three-Tier Setup

After this, you'll be able to describe the human/supervisor/worker architecture, write a minimal supervisor prompt, and explain why the middle tier is the one that makes scale possible.

22 min
L9Sprint

Manage the Money

After this, you'll be able to set per-run budgets, route tasks to the right model tier by stakes, and monitor spend before it becomes a surprise.

18 min
L9Sprint

Stale Context Is Not a Stale Bug

After this, you'll be able to describe the stale context coordination problem, implement branch-per-agent isolation with merge gates, and design a shared state file for your project.

22 min
L9Sprint

Hosted or Self-Hosted

After this, you'll be able to classify any background agent task as hosted-suitable or self-hosted-required, and explain the tradeoffs that drive that decision.

15 min
L10Sprint

Hub-and-Spoke vs Peer-to-Peer

After this, you'll be able to distinguish hub-and-spoke from peer-to-peer agent architectures, identify which pattern you're actually running, and map the seams in your own project where the architectures differ.

20 min
L10Sprint

Watch for Emergent Failures

After this, you'll be able to name the three main emergent failure modes in autonomous agent teams, recognize the early signals of each in a live run, and design one mitigation for each.

22 min
L10Sprint

Reproducibility Is the Architecture

After this, you'll be able to explain why reproducibility is a structural requirement at Level 10, implement the four-layer reproducibility checklist for a multi-agent run, and run a replay test on one existing flow.

25 min
L10Sprint

When NOT to Deploy a Team

After this, you'll be able to apply a four-question decision test to any candidate task and explain why human review checkpoints are design decisions, not overhead.

18 min
L10Sprint

Document the Frontier

After this, you'll be able to write a structured failure or success report from one of your autonomous team runs and explain why documentation at this level is a contribution, not just a record.

15 min
Browse tracks →