For Law Firms

Ask what came in this morning.
Get a verified answer — not a guess.

GoDo reads your email, calendar, and matter records locally, flags new matters and potential conflicts, and builds an evidence packet for every recommendation. No cloud AI. No black-box decisions. Every action becomes part of the matter record.

Rule 1.6 Confidentiality of client information — architecture-enforced, not contractually promised
Local AI Gemma4 extracts and flags. GoDo verifies, routes, and requires human approval. AI proposes — lawyers decide.
Full Audit Trail Every workflow step logged + timestamped in your local Postgres — never leaves your server
The Problem

AI tools want your client data.
Your license agreement says no.

Model Rules of Professional Conduct 1.6 requires reasonable measures to prevent unauthorized disclosure of client information. Running client matter data through OpenAI, Anthropic, or Google — even in "enterprise" mode — is a risk assessment your malpractice carrier is starting to ask about.

Cloud AI tools route your data offsite

Every time a staff member uses an AI tool to draft a client update, search a matter file, or summarize a deposition, that content is processed on a third-party server. "We don't train on it" is a contractual promise, not a technical guarantee.

Manual processes don't scale — and don't prove themselves

Conflict checks in spreadsheets. Status updates by email. Billing write-off approvals in Slack. None of these produce a defensible record. An audit, a malpractice claim, or a bar inquiry reveals them immediately.

Legal-specific tools are expensive and rigid

Practice management software handles billing and docketing well. It doesn't handle the workflows that fall outside its templates. Every firm has five to fifteen processes that live in someone's inbox and would cost $200k to build custom.

New in 2026

The agentic web now reads and transacts on your data. That's the exposure — not the convenience.

Universal-cart and AP2-style payment-and-action rails — rolling out in 2026 — let a third-party cloud agent read and transact across the web on your behalf. For a firm bound by Rule 1.6, routing privileged matter data through a cloud agent is precisely the kind of disclosure your malpractice carrier is starting to ask about.

GoDo is the antidote. Its inference never leaves your building. There is no cloud agent reading your matters — privilege is enforced by where the computation runs, not by a vendor's terms of service. This is a structural fact about on-premises versus cloud computation; it is not a claim that any specific competitor is non-compliant.

Morning Counsel Mode

Every morning, GoDo tells you
what needs a lawyer's eyes.

Gemma4 reads your inbox and calendar locally, extracts people, companies, opposing parties, and matter-like facts, then compares them against your existing matter database. The result is a verified operations packet — not a summary, not a guess. Every flag comes with its evidence.

Sample Morning Brief
New potential matters — 3 flagged
1 may be outside firm practice area  ·  1 has missing opposing-party name  ·  1 appears urgent
Conflict candidates — 2 flagged
Acme Holdings appears as opposing party in Matter #2024-1187 · Partner review required
Calendar context
9:30 AM Smith intake call  ·  10:15 AM court deadline review  ·  11:00 AM partner meeting
Evidence drawer — every flag
Source email · Received 7:42 AM · Mentioned parties: Jane Johnson, Acme Holdings, Robert Lee · Existing matter match: Acme Holdings in Matter #2024-1187 · Confidence: 0.82 · Required action: Partner review
The guardrail that matters
"No source, no statement.
No confidence, no action.
No lawyer approval, no legal decision."

GoDo never says "this is a conflict." It says "potential conflict flag — partner review required." The system flags and routes. The lawyer decides. That distinction is not a disclaimer. It is the architecture.

AI
Gemma4 extracts & classifies
People, companies, opposing parties, matter-like facts — structured output, no freeform guessing.
GoDo matches & verifies
Deterministic conflict matching against your matter DB. Exact, alias, fuzzy, former-client, related-entity.
Lawyer reviews & decides
Every decision captured with timestamp, rationale, and actor attribution. Immutable. Bar audit-ready.
How It Works

The entire stack runs on a Mac Studio
in your server room.

Two models. Zero cloud. Zero runtime AI.

gpt-oss:120b is the primary reasoning engine — 116B open-weight parameters, running on your hardware via Ollama. It handles the conversation that turns your workflow description into an application blueprint, refines it, and arbitrates final decisions.

gemma4:31b is the adversarial reviewer — 31B parameters, completely different architecture and training lineage. It challenges the initial blueprint, finds gaps, bad assumptions, and missed edge cases. Because it was trained differently than gpt-oss, it has different blind spots. That architectural diversity is the point — it catches what gpt-oss misses.

Once an application is built, the runtime has zero AI. Workflows run entirely on deterministic code — no model inference, no API calls, no per-query cost. Rules fire, steps advance, audit trails write. All local, all free at runtime. Your staff never triggers an AI call just by using the platform.

Reference hardware

Machine Mac Studio Ultra (128 GB)
Primary reasoning gpt-oss:120b (116B)
Adversarial review gemma4:31b (31B)
Inference host Ollama (local)
Runtime AI calls Zero — deterministic code
Database Postgres (local)
Workflow engine Temporal (local)
Cloud API calls Zero in sovereign mode
Data residency Your server room
What We Build

The workflows your firm has been
running on email and spreadsheets.

Tell us the process. We'll map it out live in your first session. Each one includes a permanent, timestamped audit trail by default.

★ Lead Workflow · Conflict Check

Conflict Check Automation

Email arrives. Gemma4 extracts every named party locally. GoDo cross-references your matter database — exact name, alias, fuzzy match, former client, related corporate entity. Every potential conflict is flagged with its evidence and routed to the responsible partner for review. Decision captured with timestamp and rationale before the first meeting.

AI Extraction Deterministic Matching Partner Review Gate Audit Trail
02 · Matter Status

Client Update & Deadline Tracking

Scheduled status updates go out automatically. Court deadlines tracked with escalating alerts. Every client communication logged with delivery confirmation. Nothing falls through when someone is out.

Deadline Management Client Communication Escalation
03 · Billing

Write-Off Approval Workflow

Attorney submits write-off with reason. Workflow routes to supervising partner based on amount threshold. Approval or denial captured with justification. Client communication sent and logged. Every decision permanent.

Partner Approval Threshold Routing Decision Log
04 · Discovery

Document Request & Production Tracking

Requests go to opposing counsel, experts, and clients through structured intake. Missing items flagged automatically before deadlines. Every request, response, and follow-up logged with timestamps and actor attribution.

Multi-party Deadline Tracking Chain of Custody
05 · Settlement

Settlement Authority & Offer Tracking

Settlement authority granted and logged. Offer and counter sequences tracked with dates and amounts. Client authorization captured for each step. Final approval recorded with full history — defensible if the settlement is ever challenged.

Client Authorization Offer History Defensible Record
06 · Compliance

IOLTA Trust Account Reconciliation

Monthly reconciliation workflow ensures trust account balances are verified against client ledgers. Discrepancies flagged immediately. Reconciliation sign-off captured by the responsible attorney. State bar audit-ready by default.

IOLTA Compliance Discrepancy Alert Bar Audit-Ready
The Audit Trail

Every step. Every decision.
Permanent and immutable.

The GoDo audit trail isn't a log file someone can edit. It's written in the same database transaction as the workflow change — they commit together or not at all. A Postgres trigger physically prevents modification after the fact.

Co-transactional writes

Audit entry and workflow change write in the same transaction. It's impossible to have one without the other.

Immutability trigger

A Postgres-level trigger rejects any UPDATE or DELETE on audit rows — including from admin accounts.

Full attribution

Every entry captures who acted, what changed, when, and from which request context. Not just a user ID — a complete record.

Your database, your control

In sovereign mode, the audit trail lives in your local Postgres. You can export it, back it up, and present it to any auditor or regulator — on your terms.

Pricing

Most firms start with a pilot.
Every engagement starts with a discovery audit.

We map your intake process, identify your highest-risk workflows, and define a fixed-scope implementation — before any build begins. That audit is the engagement.

Step 1
Discovery Audit
$15–25k
Map your intake and conflict-check process. Identify email/calendar/matter systems. Security review. Prototype morning brief output. Fixed-scope implementation proposal. Mandatory before any build.
Most Common
Step 2
Pilot
$50–75k
+ $5–8k/month platform & support
Conflict check automation. Email + calendar ingestion. Matter database import. Morning brief. Evidence packets. Human review queue. Audit trail. 1–2 custom workflows. Sovereign local deployment.
Production
Full Build
$150–300k
+ $10–20k/month
Full matter intelligence layer. Morning Counsel mode. All intake, conflict, billing, discovery, and settlement workflows. Integrations with existing practice management software. Priority support.
Enterprise / Sovereign
Large Firm
$250k–$1M+
+ $25–75k/month
50+ attorney firms. Full sovereign hardware stack. Multi-office deployment. Compliance documentation. Dedicated support. Replaces a significant portion of Clio, iManage, and conflict-check tooling.
On hardware: Sovereign deployments ship on Apple Mac Studio Ultra (128–192 GB unified memory). We can bundle hardware at cost, spec a BYO configuration, or work with your existing server room. Hardware costs are separate from implementation fees.
FAQ

Straight answers.

Why not just ask ChatGPT or a cloud AI?

A cloud AI gives you a fluent guess. GoDo gives you a verified answer with an evidence packet for every recommendation — and your privileged data never leaves the building, because the inference runs locally on hardware you own.

Is this Rule 1.6 compliant?

Confidentiality is enforced by where the computation runs, not by a vendor's terms of service. GoDo's AI runs on-premises, so privileged matter data is never routed to a third-party cloud. We position GoDo as the cleanest path to ABA Opinion 512.

Where does our data live?

In your server room, on a Mac Studio you own. The full stack — workflow engine, AI inference, and audit trail — runs on hardware you own. Every question, decision, and output is recorded so you can defend the file. Zero cloud, zero runtime AI calls offsite.

What does it cost?

Every engagement starts with a paid discovery audit, then a pilot or full build, with predictable monthly maintenance. Sovereign deployments run on hardware you own. See the pricing section above for current tiers.

Does the AI make the decisions?

No. AI proposes; lawyers decide. GoDo's local model extracts and flags; the system verifies, routes, and requires human approval before anything becomes part of the matter record.

What happens to privileged data now that AI agents read and transact across the web on your behalf?

That is exactly the 2026 exposure. Universal-cart / AP2-style agents now read and transact through the cloud. For a firm bound by Rule 1.6, routing privileged matter data through a third-party cloud agent is the risk, not a convenience. GoDo's inference never leaves your building, so there is no cloud agent reading your matters.

Start with your conflict-check process.
We'll show you what GoDo can do with it.

Walk us through how your firm handles conflict checks today. We'll map it live, show you what Morning Counsel mode would flag from a real inbox, and spec a pilot — with sovereign deployment configured for your hardware from day one.

Book a Working Session →

Engagements start with a paid discovery audit ($15–25k). No account required before then. If it doesn't fit, we'll tell you.