Skip to content
ProtocolProtocol

The library

Every move, in one place.

88 free lessons across 15 benches. The whole bench, raw instrument file through published figure, plus building your own tools.

3 benches · 15 lessons on the bench work, plus 12 areas · 73 lessons on building with Claude Code. Tap one, or describe what you're stuck on below.

New here? Start with Compliance & safe AI use (free) and go in order. Jump anywhere once it clicks. The Builder track is its own path. Start it whenever you want AI building FOR you.

⬡ Ask Protocol for a lesson on anything

Describe a real thing you need to get done. Protocol builds the drill from your exact situation.

The bench work

Instrument files to figures to manuscripts. 3 benches · 15 lessons on the bench work, all free.

1Compliance & safe AI use (free)7 lessons›

Fair Housing, client privacy, and what's never safe to paste. The skeleton, practiced to reflex.

Show it one compliant listing›What client data is safe to paste›Build your brokerage-compliance master prompt›Delegate a full compliance review›Make AI defer to your data, not its guess›Force the answer into a decision matrix›Convene an AI board of advisors›
2Workflows & automation5 lessons›

Design a repeatable task into an AI workflow. With a human approval gate exactly where it belongs.

Map a repeatable task into a workflow›Design the human-in-the-loop approval gate›Spec the weekly follow-up sequence›Automate the listing-launch checklist›Set the control dial: where a human stays in the loop›
3Claude & Cowork mastery3 lessons›

One platform, mapped to the job: a Project for your standing context, a Cowork skill for a repeatable prompt, MCP connectors for your live inbox and calendar.

Give Claude your business once›Turn your best prompt into a skill›Let Claude read your inbox and calendar›

Builder track

Stop using AI. Start building with it. Claude Code, skills, agents, and systems that run without you. 12 areas · 73 lessons, capability-first, all free.

B1Setup & first contactInstall Claude Code, meet the terminal, and have your first real conversation about your own work.›
Pick a plan & installBuild →Terminal tour: read your dashboardBuild →IDE setup: give it a windowBuild →Your first real task, iteratedBuild →Your files as contextBuild →Talk to it: voice inputBuild →
B2The project brainCLAUDE.md sets the trajectory, your voice, your market, your compliance rules, baked in.›
CLAUDE.md: set the trajectoryBuild →/init on a real folderBuild →The 200–500 line ruleBuild →Split into rules/Build →Auto-memoryBuild →Secrets & .env hygieneBuild →
B3Steering & safetyA minute of planning saves ten of building, especially where client data is involved.›
Permission modesBuild →Plan modeBuild →/permissions rulesBuild →Bypass mode, safelyBuild →Cost capsBuild →The human-in-the-loop matrixBuild →
B4Context engineeringKnow what fills the window before you type a word.›
/context anatomyBuild →Compact vs clearBuild →Token densityBuild →Specific beats vagueBuild →Pick model & effortBuild →The overhead auditBuild →
B5The verify loopTask -> do -> verify. Skip verification and you lose most of the value.›
Task → do → verifyBuild →Screenshot loopsBuild →Tests as verificationBuild →Fresh-data testingBuild →Cold-start runsBuild →Self-annealingBuild →
B6Skills: package your processYour repeatable SOPs become software the AI runs.›
SOP → SKILL.mdBuild →Frontmatter anatomyBuild →Scripts as musiciansBuild →Iterate to 99%Build →Self-healing skillsBuild →Your skill libraryBuild →
B7Connect your tools (CRM, calendar, your data)Skills other people built for you, install, vet, audit.›
What MCP isBuild →Install & vet a serverBuild →Audit the token costBuild →Paste the API docs insteadBuild →MCP → skill conversionBuild →Build a tiny serverBuild →
B8The DO frameworkCode executes, the LLM judges. Compound error math explains why.›
Docs → chatbots → agentsBuild →The PTMRO loopBuild →Directive anatomyBuild →Code executes, the LLM judgesBuild →Compound-error mathBuild →MetadirectivesBuild →
B9Subagents & parallel workFan out when it pays; feeling productive isn't being productive.›
When to fan outBuild →Reviewer & QA agentsBuild →Summaries, not raw textBuild →Git worktreesBuild →3 approaches in parallelBuild →The 3–4 agent capBuild →
B10Design: flyers & social graphicsReference-driven design with a screenshot-compare loop.›
The screenshot-compare loopBuild →Reference-driven designBuild →Component librariesBuild →Decks & one-pagersBuild →Brand consistencyBuild →The design QA criticBuild →
B11Office & data agentsSpreadsheets, documents, and reports that produce themselves.›
Excel that explains itselfBuild →docx & pptx skillsBuild →Sheet-connected pipelinesBuild →The weekly market report factoryBuild →Ask-your-workbook agentBuild →Deliverable factoriesBuild →Build your market second brainBuild →
B12Ship a real toolWebhooks, schedules, observability, one durable tool for your work, demoed.›
Deploy a static siteBuild →Wrap a skill in a URLBuild →WebhooksBuild →Cron in plain EnglishBuild →Secrets & observabilityBuild →Capstone: ship your realtor toolBuild →

Every area gives away its first moves free. Each track spins endless personalized lessons.