Stage is an AI-native platform for commercial real estate. Because it handles sensitive portfolio and lease information, security is built into the foundation across three layers — perimeter, data, and AI — with every claim published at its honest maturity.
Last updated: 1 June 2026 · Version 1.0
Request full security package See implementation statusOverview
Traditional SaaS security stops at the application edge. An AI-native platform has a second trust boundary inside the app — the model's context window — so we treat AI as a first-class security domain, not an afterthought.
Authenticated, authorized, rate-limited, validated.
Isolated, encrypted, governed end-to-end.
Transparent, bounded, provenance-tracked.
The differentiator
Stage runs a small team of specialized agents — Sage (synthesis), Scribe (document reading), Scout (research), Strat (modelling), Sentry (governance). Each has a narrow job and only the data access that job requires. Here is how we keep them trustworthy.
Every agent action is logged with the model used, the provider (Anthropic or Google), the reason it was chosen, the exact prompt version, and a fingerprint. "Which AI processed our data, and when?" always has an answer.
Under Anthropic's and Google's commercial API terms, prompts and outputs are not used to train their models, and Stage opts into no data-sharing program.
Text inside uploaded documents is treated as data, never commands. We strip known manipulation patterns and wrap document text in a labeled boundary the model is told to read but never obey.
A second model verifies the first on document extraction; disagreements are held for a human, not auto-published. Nothing becomes your system-of-record without human approval.
Hard limits on orchestration loops, time, and tokens, plus a per-tenant daily spend cap with a soft alert and a hard cutoff, prevent a stuck or abused agent from running up cost or load.
Outputs carry a confidence tier, source references, and model attribution. A lineage API replays any result back to the document and upload event it came from.
Data protection
Each customer's data is walled off at the database level by an automatic guard that fails safe: if the system cannot confirm who is asking, it returns nothing.
A global database guard injects a tenant filter into every read and stamps every write — defense across application, database, vector, agent-context, and logging layers. A CI red-team test asserts cross-tenant reads return nothing, and runs before every release.
Tenant data and uploads live on Stage's hosted deployment with an encrypted persistent volume. Dedicated-region and single-tenant-instance deployments for enterprise contracts are on the roadmap.
| Sub-processor | Data received | Notes |
|---|---|---|
| Railway | All tenant data (at rest / in process) | Hosting · DPA · encrypted |
| Anthropic (Claude) | Agent prompts, transient | No training · DPA |
| Google (Gemini) | Document text/images, transient | No training · DPA |
| Clerk | User identity, org membership, roles | Auth · SOC 2 (provider) · DPA |
| Resend | Recipient email + message metadata | Transactional email · DPA |
| Sentry | Error metadata (no tenant PII by design) | Monitoring · DPA |
| AssemblyAI | Meeting audio (only when transcription used) | DPA |
Privacy & compliance
Data-subject / consumer rights — access, rectification, erasure, portability — fulfilled via tenant admin tools and a documented runbook. Stage does not sell or share personal information. DPA available on request.
Uploaded text is scanned for SSNs, card and account numbers, addresses, and attorney-client privilege markers before any model sees it. You choose the policy: STRICT (quarantine), WARN (allow + log), or PASSTHROUGH (your own DLP).
An idempotent six-step cascade removes data from source storage, the retrieval index, caches, and flags affected logs — with a verifiable confirmation. Retention is tiered and tenant- configurable 🟡.
Access & identity
A seven-tier role hierarchy (auditor → super-admin) enforced at the API layer, not just the UI. Maps cleanly to Admin / Operator / Viewer for procurement.
Operations
Application, auth, agent-run, model-routing, ingestion, deletion, and access events are logged; records are hash- and signature-protected. Tenant admins can query their own audit trail.
JSON / webhook log export for Splunk, Sentinel, and Datadog is on the roadmap; the audit and agent-run schemas are already export-ready.
Dependencies are pinned to CVE-safe floors and audited with pip-audit. Patch targets: Critical 24h · High 7d · Medium 30d · Low 90d 🟡.
SLO monitoring and health probes are live. Formal uptime SLA, RTO/RPO targets, and multi-region failover are on the roadmap 🔲.
Incident response
| Tier | Definition | Response target |
|---|---|---|
| P0 | Active breach or confirmed data exfiltration | Immediate |
| P1 | Suspected breach, outage, or compliance-triggering event | 1 hour |
| P2 | Security degradation, failed control, or anomaly | 4 hours |
| P3 | Low-severity event, policy violation, informational | 24 hours |
Certifications & roadmap
A page of all-green checkmarks fails the moment one claim doesn't survive diligence. We publish exactly what is live, partial, and planned, because trust is built on accuracy.
| Item | Status | Notes |
|---|---|---|
| Tenant isolation + CI red-team test | ✅ Live | Activated per deployment |
| AI model-routing ledger + prompt versioning | ✅ Live | Per-call provenance |
| Ingestion validation + PII scan + deletion | ✅ Live | 107-test security suite |
| SSO / SAML / OIDC / MFA | ✅ Live | via Clerk Enterprise |
| SCIM directory sync · BYOK encryption | 🟡 Scaffolded | Endpoints exist; IdP-certified sync in progress |
| Production vector store + embedding encryption | 🟡 Contract ready | Isolation enforced when shipped |
| SOC 2 Type I → Type II | 🔲 Roadmap | Many criteria already implemented · target dates on request |
| Third-party penetration test | 🔲 Roadmap | Summary shareable under NDA |
| SIEM export · IP allowlist · multi-region DR | 🔲 Roadmap | Schemas export-ready today |
Document library
The authoritative 9-section reference: threat model, isolation, AI security, access control, incident response, and a pre-filled 25-question vendor security questionnaire. ✅ Available
Countersigned DPA with sub-processor list and breach-notification commitments. ✅ On request
Procurement-ready Q&A and a structured ingestion architecture diagram. ✅ Available
The operational deletion procedure with SLAs. ✅ Available
Available after certification, under NDA. 🔲 Roadmap
Available after first engagement, under NDA. 🔲 Roadmap
Contact
For security questionnaires, DPAs, document requests, or to report a vulnerability:
📧 security@wxstage.com
🔐 PGP key & responsible-disclosure policy available on request
📄 Implementation status · Document library