Building a Claude Stack for a Regulated Vertical (What I Learned Shipping for Law Firms)

Source: Dev.to

Introduction

Most of the “I built an AI workflow” posts you see on here treat Claude like a fancy text box: open chat, paste a prompt, copy the answer, ship.

That works for solo‑dev tasks, but it falls apart fast when you start building for someone else’s business—especially one with strict confidentiality, compliance baggage, and a workflow that runs on documents.

I’ve been building Claude‑powered tooling for law firms for the last year. The vertical doesn’t matter as much as you’d think. Replace “motion to compel” with “engineering change order” or “policy underwriting memo” and the architecture is roughly the same. So if you’re building for accountants, doctors, financial advisors, contractors, or any regulated professional‑services niche, this maps over cleanly.

Below is the stack I keep coming back to, and the part most people miss.

The mental model: Claude is not a chat tool, it’s a runtime

The biggest unlock isn’t a prompt trick. It’s realizing that Anthropic shipped a layered platform and the chat window is just the entry point.

What’s actually available?

If you stop thinking of these as “features” and start thinking of them as primitives in a stack, the architecture writes itself.

The architecture that works

For a vertical use case, here’s the layering I’ve landed on after a lot of dead ends.

Layer 1 – Projects = workspace per “matter”

Law: a case.
Other verticals: an account, a project, a client engagement, a deal—whatever the long‑running unit of work is, that’s a Project.

Inside each Project you load:

1. Reference documents that define the engagement
2. Project‑level instructions that pin the rules of the road (jurisdiction, style, default outputs, things to never do)
3. Output history, which becomes its own context over time

Skip this and every conversation is a cold‑start.
Use it and Claude walks in pre‑loaded.

Layer 2 – Skills = your firm’s playbook as code

Skills are the most underrated thing Anthropic has shipped. They’re literally a SKILL.md file plus optional supporting assets, and they tell Claude how to do a specific kind of work the way your team does it.

Example (law firm) – a Skill for demand letters that encodes structure, citation format, tone, the partner’s pet phrasings, and the things never to include. Any associate can fire it and get output that looks like the senior partner wrote it.

The pattern generalises:

skills/
  demand-letter/
    SKILL.md
  client-intake-summary/
    SKILL.md
  discovery-response/
    SKILL.md
  weekly-status-update/
    SKILL.md

Each file is your team’s institutional knowledge—versioned, reviewable, shareable across the org. This is the part that compounds.

Layer 3 – MCP for the boring plumbing

Claude has direct connectors for Google Drive, Gmail, Calendar, Slack, GitHub, and a growing list. You can also write your own MCP server for whatever niche tool the vertical lives in (legal practice management, EHRs, CRMs, ERPs, you name it).

The win: removing the file shuffle.

Without MCP: download from system A → upload to Claude → get answer → paste into system B.
With MCP: Claude reads from system A and writes to system B in the same turn.

If you’re building for a vertical, writing one custom MCP server for the dominant tool in that niche is probably the highest‑leverage thing you can do. Most verticals have one or two systems of record everyone uses, and nobody has built the connector yet.

Layer 4 – Cowork for the multi‑step stuff

Cowork is Anthropic’s agentic mode. You describe an outcome, Claude works through the steps, only checking in when it actually needs you. This is where Claude stops being reactive and starts being a junior team member.

Concrete example – “review these eight discovery documents, extract every date mentioned, identify the source for each, and produce a chronological timeline grouped by topic.”

Without Cowork: ~30 back‑and‑forths.
With Cowork: it runs automatically.

For your vertical, look for tasks that are:

• Multi‑document
• Sequential (output of step N feeds step N+1)
• Tedious enough that nobody actually does them well

Those are Cowork tasks. Build for them first.

Layer 5 – Claude Code when you’re ready to build

If your client (or your own team) has anyone semi‑technical, Claude Code is genuinely transformative. I’ve watched a paralegal with no coding background ship a working intake automation in a weekend with it. Marketing operators are building content pipelines. Office managers are wiring up internal AI agents.

The interesting thing for devs: you’re now competing on architecture, not on writing code. The leverage is in knowing what to build and how to structure it. The actual code generation is solved.

Layer 6 – API when you need a real product

Once a workflow stabilises inside the Claude UI, the next move is usually to lift it into an API‑backed product: client‑facing chatbot, internal tool, customer dashboard, whatever. Pricing is pay‑as‑you‑go and for most B2B use cases the monthly bill lands somewhere reasonable.

Half the legal‑AI startups charging four‑figure‑a‑month fees are wrapping the same API you have access to. That’s not a knock on them—it’s just an observation. If your vertical has a SaaS charging $500 per seat for AI features, you can probably build a focused alternative for one customer at a fraction of the cost.

The part nobody warns you about

Three failure patterns I see constantly when teams try to roll this out:

1. They never … (the original text cuts off here; you’ll want to finish the list based on your own experience)

   (Continue the list with the remaining two patterns you’ve observed.)

The Problem with “Claude‑only” Teams

• No shared Projects. People use the chat window, get tired of re‑uploading the same files, and think Claude is “too manual.” The fix is a fifteen‑minute setup that nobody does.
• No reusable Skills. Teams get good output once, never encode it. Every prompt starts from scratch, so the compounding benefits never appear.
• One‑person power‑user. A single individual produces magic while the rest of the org watches. Without shared Projects and Skills, the firm ends up with one AI‑savvy person rather than an AI‑augmented organization.

The Technical Fix (the same for all three)

1. Treat the Claude stack as infrastructure, not a personal tool.
2. Version‑control your Skills.
3. Document your Projects.
4. Onboard people into the stack the same way you’d onboard them into a codebase.

The Vertical Play

If you’re a developer or solo operator looking for an angle, here’s the unsexy advice:

1. Pick a vertical.
2. Learn its workflow obsessively.
3. Build the stack above it.
4. Ship.

Every regulated professional‑services niche shares the same shape:

• Long‑running engagements
• Dense documents
• Repetitive output
• Strict compliance

The same architecture works across all of them. The differentiation lies in knowing which Skills to build and which MCP connectors to write.

I went deep on the law‑firm version of this and wrote it up on Lawyer’s Marketer. See the full vertical breakdown of which Claude tools map to which legal workflows:

Claude Tools for Lawyers: Move the Needle In Your Practice

It’s written for lawyers, but the architecture translation is obvious if you read it as a developer.

Parting Thoughts

• The chat window is the demo.
• The stack is the product.

If you’re building anything serious on Claude, stop benchmarking against ChatGPT and start thinking like a platform engineer. The teams shipping real value right now are the ones treating Projects, Skills, MCP, and the API as a coherent stack rather than a checklist of features.

Call to Action

If you’re working on something in this space, I’d genuinely like to hear what you’re building. Drop it in the comments.