Foundations
From zero to AI-ready.
By the end, everyone opens VS Code on their own, loads a case, and has Claude summarise where it stands.
Setup · Mindset · First case
Block I+II run back-to-back. Block III follows one or two weeks later — so what you learned lands in real files.
From zero to AI-ready.
By the end, everyone opens VS Code on their own, loads a case, and has Claude summarise where it stands.
Setup · Mindset · First case
Tools become leverage.
You stop prompting and start delegating. Skills turn into reusable gold.
Prompts · Skills · Outlook
Your 24/7 staff.
Power features for those who really want to go deep. Half structured, half office hours on your real problems.
Agents · Routines · Office hours
Industry-agnostic. Law firms, tax advisors, consultancies, family offices — the workshop adapts to your vocabulary, your templates, your client records.
Sounds techie. It isn't. Your folders on the left, Claude in the chat on the right. That's it. We're opening your folders — promise.
This isn't a tool. It's your 24/7 assistant with a 250 IQ. Your full-time job from today on — a clean folder structure. Claude does the rest.
One folder per case. All case folders inside one parent folder. What goes inside is up to you — as long as Claude knows where to look.
Global: how you write. Per case: where you stand. Claude reads both every time it starts — automatically. They're the reading glasses through which it sees your world.
# Kanzlei-OS · v1
Kanzlei/
├── CLAUDE.md ← Stil & Briefkopf
├── .claude/skills/ ← Skills
├── Faelle/
│ ├── 2026-001_Mueller_vs_Schmidt/
│ │ ├── CLAUDE.md
│ │ ├── Schriftsaetze/
│ │ ├── Korrespondenz/
│ │ └── Beweise/
│ ├── 2026-002_Schulz_GmbH/
│ └── 2026-003_Bauer_Erbschaft/
└── Vorlagen/ ← Stil-AnkerThe more tokens in context, the worse the model gets. Claude holds out longest — but everyone eventually drops off. /clear on topic change. /compact past 120k tokens. Better too early than dumb too late.
# Firm-OS · v1 — sample structure, adapted to your industry.
Three principles that change everything: context beats cleverness. Examples beat description. Allow follow-up questions — better yet, force them.
Five parts every good prompt needs. Role before task. Context before format. Format before constraints.
A skill is an instruction plus logic that Claude loads automatically on certain triggers. Without skills you use 1 %. With the right skills you lever the same AI a hundredfold.
Summarise the state of play — what's happened since the last client action.
Filing in your own style — pulls from /Templates automatically.
Scans every case CLAUDE.md for deadlines, sorted by date.
Control isn't a feature — it's a position on a slider. You decide per task.
Claude thinks, writes a plan. Nothing is executed. Default for client data.
Reads without asking, writes with OK. The standard — where you spend 80 % of the time.
File edits without asking, bash with. Gold for drafting & refactoring.
Everything without asking. Isolated environments only, always with backup. Never in real client files.
Power features for those who really want to go deep. From „Claude calling Claude" to „a Claude team coordinating itself."
A sub-agent is a specialised Claude that the main Claude spawns for a bounded task. Own brief, own tools, own context window. It works in the back room — and returns only the summary.
Each helper is a full Claude session of its own — same task list, talking to the others directly, addressable individually. Sub-agents for speed. Agent teams for depth.
Output from git, grep, a mail export — piped in, an answer back out. Headless mode for scripts. Runs anywhere a terminal runs — over SSH on the firm server, in a container, in the cloud.
# Four lines, four worlds: interactive · one-shot · pipe · write to file.
# 1 · einfach starten
$ claude
> Fasse die Akte zusammen.
# 2 · einmalig, ohne Sitzung (Headless)
$ claude -p "Welche Frist läuft heute?"
# 3 · andere Tools reinpipen
$ git diff Schriftsatz.md \
| claude -p "Was hat sich geändert?"
# 4 · ausgeben, weiterverarbeiten
$ claude -p "Sachverhalt extrahieren" \
> sachverhalt.mdWhen you want to go even deeper. Mix and match. Book any time after.
Canva integration, letterheads, client pitches and one-pagers in 10 minutes instead of 4 hours.
OpenClaw as a 24/7 runtime. Telegram bridge. Claude answers even when you're away.
Win clients with AI. Content, SEO, Ads — the playbook we run daily across 100+ apps.
This isn't a tool. This is your 24/7 assistant with a 250 IQ.
Your full-time job from today on — a clean folder structure. Claude does the rest.
When you're stuck, ask Claude. It will help you set yourself up.
We're not consultants. We operate what we sell — our own apps with seven-figure ad spend, AI workflows running overnight, skills that ship daily. We come into your firm, your practice, your office. Three blocks later it runs.
Builds and runs a portfolio of subscription apps with seven-figure ad spend. Apple Search Ads, Meta, RevenueCat — daily.
Skills, sub-agents, OpenClaw runtimes. Builds Claude Code with Claude Code — and the same layers for clients.
30-minute discovery call. We'll figure out whether the programme fits your firm — free, no strings.
Grab a time that works. 30 minutes, video. Confirmed instantly.
If no slot fits — one line is enough. We reply within 24 hours.