Firmcraft
← Back to home ·  Security & trust
Security & trust

Your data. Your environment.
Your audit log.

Most "AI for business" tools route your client data through a multi-tenant cloud you don't control, with a "trust us" attached. We don't. Each firm gets a private deployment, every action is logged and reversible, and sensitive work waits for partner approval. The default posture is paranoid.

DeploymentPrivate per firm
Audit logEvery action recorded
EncryptionAt rest & in transit
ComplianceSOC 2 in progress
Three trust principles

How we think about your data — before any feature decision.

We've thrown out features that violated any of these. They're load-bearing, not aspirational.

01

Your data doesn't leave your boundary.

The operator runs in a deployment dedicated to your firm. Your client records, chats, and documents stay in that boundary. No multi-tenant brain. No training on your data. No shared embeddings.

02

Every action is visible and reversible.

Every read, every write, every send is logged with who triggered it, what it touched, and why. Filterable, exportable, addressable by audit. If it shouldn't have happened, you can see it and undo it.

03

The risky stuff asks first.

Money out, contracts going live, client sends, anything irreversible — partner approval required, by default. You configure which actions need a human and which just run. Nothing slips.

01 / Deployment

Where your data actually lives.

We deploy a dedicated environment for every firm. Your operator, your memory store, your connector credentials, your audit trail — all live in compute that belongs to your engagement and nobody else's.

What that means in practice: if a vulnerability hit one customer's deployment, it does not reach yours. If a different customer corrupts their memory store, you don't see it. There is no shared brain.

You choose where it sits. Default is our managed infrastructure (US-East or US-West). For firms with compliance constraints — HIPAA-leaning, regulated finance, public-sector — we deploy into your own AWS / GCP / Azure account or your on-prem hardware on the same five-day timeline.

"Multi-tenant SaaS is fine for a notes app. It is not fine for client charts and engagement letters."
Deployment posture
Per-firm isolationDedicated
Tenancy modelsingle-tenant
Default regionUS-East-1
BYO cloudAWS · GCP · Azure
On-premAvailable
Encryption at restAES-256
Encryption in transitTLS 1.3
Customer data in trainingNever
Provider redundancy≥2 LLMs
Sub-processors3 · listed
02 / Access & roles

Who can see what, and what can run.

The operator inherits your firm's hierarchy. Front desk doesn't see partner-only matters. Associates can't approve their own engagement letters. The intern can't trigger the "send to all clients" playbook.

Per-channel scope. Each playbook is bound to specific channels and specific roles. A playbook in #partners-only never reads from #general and never writes into #client-x.

Approval chains. Sensitive actions can require N-of-M approval — e.g. partner OR senior associate for engagement letters, two partners for any wire over $25k.

"I want my front desk to file the claim. I do not want my front desk to refund anyone."
Example: a 14-person dental practice
ActionFront deskHygienistDoctor
Read patient chart
Submit insurance claim
Submit appeal > $1kapprove
Refund a patientapprove
Run recall campaignapprove
Edit playbook config
Export audit log
03 / Audit log

Every action recorded.

Read, write, send, fail, retry, approve, reject. Each entry carries who triggered it, what it touched, why it ran, and the resulting artifacts. Searchable in the dashboard. Exportable as CSV or JSON for your auditor.

Reversible by default. The operator auto-snapshots its working state before every file change. Any individual action can be undone with /rollback. The full-text session index is the searchable layer underneath the dashboard. None of this is bolted on — it's how the runtime works by default.

Compliant retention. Logs retained for the period your industry requires — 7 years for tax practices, 10 for legal, indefinite if you tell us so. Stored in your environment, not ours.

Audit log · last 24 hours · #front-desk
09:18:02Maya R. mentioned operator · claim_submission
09:18:14Operator read · Eaglesoft / chart 4421
09:18:31Operator wrote · claim_882041.pdf → /Drive/Claims/
09:18:44Operator sent · POST delta-dental.com/claims
11:42:08Inbound webhook · EOB received · $710 paid
11:42:12Action held · pending Dr. Chen approval
11:48:55Dr. Chen approved · patient text drafted
11:48:57Operator sent · SMS +1 ••• ••• 4421
14:01:03Scheduled run · recall_reactivation · 38 drafts queued
04 / Compliance posture

What we have, what's in flight.

We're a pre-Series-A company. We will not claim certifications we don't hold. Here's where everything actually stands, with target dates we'll keep updated.

HIPAA posture. The architecture is HIPAA-ready: per-firm boundaries, encryption, audit logs, BAA-able sub-processors. BAAs are signed at onboarding for any healthcare engagement — dental, medical, behavioral health. Full HIPAA attestation is on the SOC 2 Type II timeline.

What we'll never claim. We are not "ISO 27001 certified," "FedRAMP authorized," or "SOC 2 Type II" until those audits are complete. If you need any of those today, talk to us — we'll either tell you when we'll have it or that you should pick someone else.

"I'd rather miss a deal than fake a certification."
In progress · Q3 '26SOC 2 Type II

Auditor engaged. Type I report available under NDA.

In progressHIPAA

BAA-able today. Full attestation on SOC 2 timeline.

AnnualPenetration testing

External pen test every 12 months · NDA required.

LiveDPA + sub-processor list

GDPR-aligned DPA on request. Three sub-processors.

LiveVulnerability disclosure

security@firmcraft · 90-day fix SLA · public bounty soon.

Roadmap '27ISO 27001

Pursued after SOC 2 Type II clears.

Questions partners ask before they sign.

Will my client data be used to train models?

No. Your firm's data — chats, documents, charts, audit logs — is never used for model training. Not by us, not by the model providers we route through. This is enforced contractually with our model providers and architecturally by the per-firm deployment.

Where is my data physically stored?

By default, US-East-1 (Northern Virginia) for managed deployments. We can deploy to US-West, EU regions, or your own AWS / GCP / Azure account. On-prem deployment is available for firms with that requirement; we'll quote the engagement separately.

What happens to my data if we churn?

You get a full export within 5 business days — every chat, document, audit log entry, and playbook configuration in open formats (CSV, JSON, Markdown, PDF). Your deployment is then destroyed and we hold a 30-day backup for emergency recovery, after which it's also destroyed. We notify you when the final destruction completes.

Who at Firmcraft can see my data?

Three engineers, named in our DPA. Access is logged, scoped to the specific issue, and time-boxed. Routine support and onboarding don't require access to your data — they work from telemetry and your screen-share.

What if a model provider has an outage or breach?

The operator routes across 45+ supported LLM providers, with built-in automatic failover and credential pools that distribute load across keys. If Anthropic has an outage, we route to OpenAI, Bedrock, or Gemini without you noticing. In the case of a security incident at a provider, we have contractual notification obligations and our own 24-hour incident SLA — we'd notify you, isolate any affected workflows, and switch routing.

Do you offer a BAA?

Yes — BAAs are part of standard onboarding for healthcare deployments (dental, medical, behavioral health). Signed before any patient data flows.

Can I see your SOC 2 Type I report or pen test?

Yes, under NDA. Email security@firmcraft and we'll get it to you within one business day.

What happens if Firmcraft goes out of business?

The operator runs on Hermes Agent, an MIT-licensed open-source platform maintained by Nous Research. Your skills, memory files, integrations, and audit logs are all stored in standard formats on infrastructure you can take with you. You — or another vendor — can pick them up and run a Hermes deployment elsewhere on day one. We don't own the runtime. We operate it for you. No lock-in, by design.

For your CISO / compliance lead

We'll send the full security packet by close of business.

Architecture diagram, sub-processor list, DPA, BAA template, SOC 2 Type I, pen-test summary, incident-response runbook. One email.

Direct lines

Reach the right person.