Four use cases that actually pay off.

After analysing 20 firms, four AI use cases consistently deliver measurable value. The others are mostly marketing. Start with these; they'll teach you what AI can and can't do in your firm before you bet bigger.

01

Inbox classification + routing

LLM classifies incoming mail (client, court, marketing, internal) and routes. Near-zero risk, high volume, immediate payoff. 4-week deployment typical.

02

Document summarisation

LLM summarises incoming documents (contracts, letters, reports) before partner review. Partner reads 200 words instead of 20 pages; drills down only when needed.

03

Deadline extraction (with mandatory human review)

LLM extracts deadlines from beA messages and emails. Human confirms before anything is written to DATEV/RA-MICRO. Saves hours weekly, zero risk if review gate is enforced.

04

Content drafting with approval

LLM drafts LinkedIn posts, blog articles, newsletters. Partner reviews against pre-defined criteria in <5 min. See the content-automation guide for depth.

Four use cases. Zero mystery. Everything else is marketing pretending to be products.

What doesn't work (and why).

Plenty of AI-for-legal products claim capabilities they don't reliably deliver. Here's what we've tested and seen fail — at least with current-generation models. This may change, but skepticism is the right default.

01

Autonomous legal advice

AI giving binding legal advice without human review: still too unreliable. Hallucinations are too frequent, citations too unreliable, context too easy to misread. Human-in-the-loop is mandatory.

02

Contract negotiation bots

AI negotiating contract terms with the other side's AI: impressive demos, poor real-world performance. Negotiation depends on strategy, ambiguity, power dynamics — things LLMs don't handle well.

03

End-to-end case prediction

AI predicting case outcomes: some specialised tools work for narrow domains (patent litigation in the US), but general-purpose prediction is unreliable and not worth betting on for most firms.

04

AI paralegal assistants without supervision

The marketing says "fully autonomous". The reality is: they need supervision like any junior staff. Treat them as a speed-up, not a replacement.

Compliance: BRAO, GDPR,
professional secrecy.

Legal professionals operate under stricter data rules than most industries. AI deployment must respect all three axes simultaneously — and it's fully doable, just not accidentally.

01

BRAO / bar rules

No advice without supervision. No comparative claims. No guaranteed outcomes. The generation prompt enforces these at output time; the review checklist verifies at sign-off time.

02

GDPR

EU-only endpoints. No-training agreements. 30-day data retention max. Personal data minimisation (only what's needed). Audit log for every AI call. Right to erasure implementable.

03

Professional secrecy

Mandate-level data doesn't leave the firm's infrastructure unless absolutely necessary. When it must (for extraction), it goes via EU endpoints with clear deletion terms. Never to US-residency services without explicit agreement.

Models and endpoints
— state 2026.

The AI landscape shifts monthly, but the stable choices for EU-based law firms in 2026 are:

Our default: Claude for high-stakes work, GPT-4o for volume, Mistral for EU-native, Llama for self-hosted. Choice depends on risk profile and latency tolerance — not on \"which is best\".

  • Anthropic Claude 3.5 Sonnet via AWS Frankfurt — best instruction-following, strong German.
  • Azure OpenAI GPT-4o in Frankfurt region — robust, wide ecosystem, slightly weaker on German nuance.
  • Mistral Large via Mistral API (French hosting) — fully EU-native, solid quality for most tasks.
  • Llama 3 self-hosted (for sensitive extraction) — runs on your server, no external API calls.
  • Avoid: any US-hosted API without data-residency agreement. Avoid: on-device tools that phone home.

Governance that firms trust.

AI in a law firm must be governable — auditable, reversible, reviewable. Four mechanisms that turn "black box" into "traceable system":

01

Audit log per call

Every AI call is logged: prompt, input, output, who requested, timestamp. Retained in EU-hosted Postgres for 12 months. Exportable.

02

Human-in-the-loop on binding outputs

Anything going to DATEV, beA, or a client without human review: no. Reviews are recorded — who approved, when, against what criteria.

03

Rollback capability

Any automated decision must be reversible. A deadline written incorrectly can be unwritten. A document tagged wrongly can be retagged. All via UI, no engineer needed.

04

Quarterly review of false positives/negatives

Every quarter, partners review a sample of AI decisions. What did it get wrong? What did it miss? Feed learnings back into prompts and review criteria.

How to start — year one.

If you're just beginning, here's the year-one plan that's worked for the firms we've helped. Resist the temptation to do everything at once; each step needs time to become habit.

  • Month 1–2: inbox classification + routing. Low-risk, high-volume. Teaches the firm what AI does and doesn't do.
  • Month 3–4: document summarisation. Partners experience time savings firsthand. Builds trust.
  • Month 5–7: deadline extraction with mandatory review. Higher stakes; justifies the review discipline.
  • Month 8–12: content drafting with approval. Adds value without risk. Often the most visible AI feature to clients.
  • After year 1: evaluate whether to add further cases based on actual outcomes, not demos.

Common questions.

01Which AI models do you recommend for law-firm work?+
Claude 3.5 Sonnet and GPT-4-class models via EU endpoints. Both handle German legal text well. For high-risk tasks (deadline extraction, advice-like outputs), we prefer Claude for its instruction-following. For volume tasks (classification, summarisation), either works.
02Is our data safe with these models?+
Yes — via EU endpoints (Azure OpenAI in Frankfurt, Anthropic via AWS Frankfurt) with no-training agreements. Data stays in the EU, is not used for training, and is deleted after 30 days. For maximum assurance, we can also self-host open-source models (Llama, Mistral) for specific tasks.
03What AI use cases pay off first in a law firm?+
1) Classification and routing of inbox messages. 2) Document summarisation before partner review. 3) Deadline extraction from beA and email (with mandatory human review). 4) Content drafting with human approval. These four cover most of what firms actually benefit from.
04What about hallucinations in legal AI?+
The risk is real and we design around it. Three controls: (1) structured outputs forced — no free-form claims; (2) source citations required for any factual claim; (3) mandatory human review for anything legally binding. Hallucination at review means "reject and try again", not "publish".
05Do lawyers need to learn prompt engineering?+
No. The prompts are embedded in the workflow — lawyers just review outputs. A partner or assistant who uses the review UI doesn't need to know what a prompt is. That's deliberate — AI should be invisible infrastructure, not a new skill to learn.