The library

Every move, in one place.

117 free lessons. The whole practice, intake through appeal, plus building your own tools.

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 Docket for a lesson on anything

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

The matter work

Intake to discovery to brief. 12 desks · 32 lessons on the matter work, all free.

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

Client confidences under Rule 1.6, grounding, and what never gets pasted. The skeleton, practiced to reflex.

Show it one memo that cleared the partner›What matter information can go in a prompt (almost nothing)›Build your firm's research master prompt›Delegate a full pre-filing review›Make AI defer to the record, 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 approval gate before anything leaves the firm›Spec the follow-up cadence for missing client documents›Automate the matter-opening checklist›Set the control dial: where a human stays in the filing workflow›

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

4Verify before you file6 lessons›

Why the model invents a case that sounds right, extracting every authority and opening each one, the three ways a cite fails, what asking it to double-check does not do, your judge's standing order, and red-teaming last month's brief.

Why the model invents a case that sounds exactly right›Extract every authority from a draft and check each one›The three failure modes: nonexistent case, real case wrong holding, real case wrong pin›What 'I asked it to double-check' does not do›Read your judge's standing order before you use AI at all›Red-team the brief you filed last month›

5Confidentiality and the client's facts6 lessons›

Rule 1.6 when the tool is a third party, de-identifying a fact pattern without losing the question, open against closed models, what the vendor's terms actually say, consent and disclosure, and the firm's AI policy as a recipe.

Rule 1.6 when the tool is a third party›De-identify a fact pattern without destroying the legal question›Open model vs closed model, and why Oregon's opinion cares›What your vendor's terms actually say about retention and training›Consent, disclosure, and when to tell the client›Write the firm's AI policy, and make the associates read it›

6The attorney's week5 lessons›

Audit the week before you hand the first task over, catch the authority that does not say what the answer says, cost the scripted run, wrap the day into the matter file, and know where a filing goes when you did not open the case.

Audit your week before you hand the first task over›Audit an answer before it goes in a brief›Cost the scripted run before the document review›Wrap the day into the matter file›Where a filing goes when you did not open the case›

7Research and memos0 lessons›

Ask the question narrowly, force the authority and open it, the memo skeleton from a messy email, subsequent history before a case is called controlling, and when to stop and call it a position. Written next.

Ask the research question the model cannot answer from vibesSoon

Force the authority, then open it: the memo that lists its own page-opensSoon

The memo skeleton from a messy client emailSoon

Subsequent history before you call a case controllingSoon

Settled, split and silent: three words the memo keeps apartSoon

When to stop researching and call it a positionSoon

8Discovery and documents0 lessons›

Sort a request set into objectionable and not, the privilege log from a production index, first-pass summaries that cite the document, the deposition outline, and what never leaves the firm. Written next.

Sort forty requests into objectionable and not, with the objection namedSoon

The privilege log from the production index, parties letteredSoon

First-pass document summaries that cite the document, not the modelSoon

The deposition outline from the de-identified indexSoon

Discovery responses that promise only what the record showsSoon

What never leaves the firm, by category, before any pasteSoon

9Drafting and transactional0 lessons›

A first draft from a term sheet, the redline explained to a client, defined terms that stay defined, the clause bank that never invents precedent, and the closing checklist. Written next.

A first draft from a term sheet, every open term markedSoon

Explain the redline to a client without taking a side you did not takeSoon

Defined terms that stay defined across sixty pagesSoon

The clause bank that never invents a precedentSoon

The closing checklist with an owner by role on every lineSoon

Governing law and venue: the clause the model gets confident aboutSoon

10Client communication and intake0 lessons›

The intake questionnaire that prevents the second call, status letters in plain language, the bad-news email a client can act on, fee conversations in writing, and what a client is entitled to know about the tool. Written next.

The intake questionnaire that prevents the second callSoon

Status letters in plain language, with no date the calendar did not giveSoon

The bad-news email a client can act onSoon

Fee conversations in writing, before the billSoon

What a client is entitled to know about the tool, and whenSoon

The conflicts check before the first fact is typedSoon

11Billing, fees and the business0 lessons›

Time actually expended, the engagement letter that names the tool, scoping the flat fee, the collections letter, and what the opinion says about charging for the hours the tool saved. Written next.

Time actually expended: the only number on the billSoon

The engagement letter that names the tool, the data and the purposeSoon

Scoping the flat fee when the first draft takes ten minutesSoon

The collections letter that stays on the right side of the rulesSoon

What the opinion says about charging for the hours the tool savedSoon

The firm's technology line on the bill, explained to a clientSoon

12Supervision, ethics and the record0 lessons›

Supervising the paralegal's use, the certification above the signature, correcting a filed brief, the conflicts check before a paste, and whether to disclose your AI use to the court and the client. Written next.

Supervising the paralegal's use: the monthly check with a yes or noSoon

The certification above the signature, in your judge's wordsSoon

Correcting a filed brief: the rule, the question, the partnerSoon

The conflicts check before a paste, not afterSoon

Disclose your AI use to the court and the client, or do not. Decide it deliberatelySoon

The sanctions orders, read as a checklist of what nobody openedSoon

Builder track

Stop using AI. Start building with it. Claude Code, skills, agents, and systems that run without you. 13 areas · 85 lessons, capability-first, all free.

B1Setup & first contactInstall Claude Code, meet the terminal, and have your first real conversation about the matter on your desk.›

Four words before you startBuild →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 firm's standing context, your voice, your confidentiality 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, and it is the difference where a client's confidences are involved.›

Permission modesBuild →Grill, then planBuild →/permissions rulesBuild →Bypass mode, safelyBuild →Cost capsBuild →The human-in-the-loop matrixBuild →

B4Context engineeringKnow what fills the window before you paste a 200-page deposition transcript into it.›

/context anatomyBuild →Handoff, clear, compactBuild →Token densityBuild →Specific beats vagueBuild →Pick model & effortBuild →The overhead auditBuild →

B5The verify loopTask -> do -> verify. On a brief, the verify step IS the work; skip it and you have signed an authority nobody opened.›

Task → do → verifyBuild →Screenshot loopsBuild →Tests as verificationBuild →Fresh-data testingBuild →Cold-start runsBuild →Self-annealingBuild →

B6Skills: package your processThe intake checklists and discovery procedures you already keep become software the AI runs the same way every matter.›

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)Connectors that let it read the document index and the calendar, plus 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 a long chain drifts, and why a citation never comes from the judge.›

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. The adversary agent is the one worth running.›

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 graphicsEngagement letters, the client one-pager and the firm's year-end note that look designed, built against a reference you supply.›

The screenshot-compare loopBuild →Reference-driven designBuild →Component librariesBuild →Decks & one-pagersBuild →Brand consistencyBuild →The design QA criticBuild →

B11Office & data agentsPrivilege logs, production indexes and the matter status report that produce themselves, from exports you de-identified first.›

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 the firm, demoed.›

Deploy a static siteBuild →Wrap a skill in a URLBuild →WebhooksBuild →Cron in plain EnglishBuild →Secrets & observabilityBuild →Design pass: ten checks on a phoneBuild →Capstone: ship your practice toolBuild →One real build, start to finishBuild →

B16The work folderFrom chat to a folder of your own files that one agent reads and writes. Keep a list of your corrections, turn it into a skill, shape the folder around the work, and hand it on.›

Which layer are you onBuild →Test your setup with one tiny jobBuild →Keep a list of your correctionsBuild →Turn corrections into a skillBuild →Start with the outcomeBuild →Shape the folder around the workBuild →Give each stage a fileBuild →One model, different jobsBuild →Keep it current and hand it onBuild →

Vendor notes, dated

Prices and plan names move. Each note says when it was looked up, whether a person has confirmed it, and the day it comes due. Past that day, treat it as a question.

Claude. Claude Pro is $20 a month billed monthly, or $17 a month billed annually. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
ChatGPT. ChatGPT Plus is $20 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Google Gemini. Google Gemini's paid consumer plan is Google AI Pro at $19.99 a month; Google AI Ultra starts at $99.99 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Anthropic. Anthropic's consumer plans (Free, Pro, Max) may use chats to train models under a setting the user controls, with five-year retention when training is on and 30 days when it is off; Claude for Work, Education, Government and the API are excluded. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Anthropic. Anthropic's usage policy, effective 2025-09-15, requires a qualified human reviewer and disclosure of AI use for housing, legal and financial decisions. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
OpenAI. OpenAI's consumer plans train on chats unless the Improve the model setting is turned off, and a Temporary Chat is not used for training; Enterprise, Business, Edu and API data are not used by default. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Google Gemini. Google Gemini Apps keeps activity 18 months by default, keeps human-reviewed chats up to three years, and tells users not to enter confidential information. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Microsoft Copilot. Microsoft Copilot on a personal account may use chats to train models unless the user opts out; Entra and Microsoft 365 work accounts are excluded. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Claude. Claude Team, Enterprise and API inputs and outputs are not used for training by default; a BAA is available only on Enterprise and the first-party API after admin action. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Claude. Claude Free, Pro and Max inputs can be used for training if the user allows model improvement, with retention up to five years if allowed and 30-day deletion otherwise (pages dated 2026-03-16 and 2026-07-01). Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
OpenAI. OpenAI API inputs are not used for training by default; abuse-monitoring logs are kept up to 30 days; zero data retention is available by approval. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
OpenAI. OpenAI Business, Enterprise and Edu no-training defaults are reported by secondary sources only; the vendor trust pages returned 403 on the check date. Read the vendor page yourself. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Microsoft. Microsoft Copilot and Copilot Chat with Enterprise Data Protection: prompts and responses are not used to train foundation models, the DPA applies, and Microsoft acts as processor (Learn page updated 2026-08-18). Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Google. Gemini in Google Workspace content is not human-reviewed or used for training outside the customer's domain; default retention is 18 months. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
Every vendor. Every vendor's no-training or no-retention term is a contract term, not the duty: it does not by itself satisfy Rule 1.6 or Formal Opinion 512: the duty to understand the tool, and for some uses to obtain the client's informed consent, sits with the lawyer and not in the terms. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.

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