The fastest way to kill a retail AI deal:
an agent with write access and no audit trail.
Ward starts read-only, runs on policy, and logs every query. Your security review is short. Your data team isn’t on the hook. Architecture, MSA, DPA, SOC 2 II report, and certificate of insurance. On the table before you sign.
Read-only by default.
Writes need a named human.
Ward queries your warehouse, POS, and ERP with read-only credentials. Agents can’t mutate the data they reason over. Anything that mutates state gates on approval from a role you define. Exports, write-backs, schedule pushes. The approver’s identity is on every record.
SELECT on the schemas you whitelist. No INSERT, no UPDATE, no DELETE. Confirm in your warehouse audit log.Policy as code.
Not click-admin drift.
Ward gives you the policy plane, the kill switch, and the audit trail your team would build for itself if it had a quarter to do it. AWS-grade governance, without the AWS-grade team. Visualized in a console your IT lead can hand to procurement.
// Finance Agent: read-only on warehouse.finance,
// no PII, region-scoped, writes require approval.
permit (
principal in Role::"FinanceAgent",
action in [Action::"read", Action::"summarize"],
resource in Source::"warehouse.finance"
)
when {
resource.classification != "pii"
&& context.region == principal.region
&& context.budget.tokens > 1000
};
forbid (
principal,
action == Action::"write",
resource
)
unless {
context.approval.status == "granted"
&& context.approval.approver in Role::"FinanceLead"
};-
Policy as code, visualizedCedar policies live in your Git. Versioned, peer-reviewed, signed. The console renders every rule as a graph: agent, action, source, condition. Your IT team reads policy without reading Cedar.
-
Scoped per role, tenant, resourceFinance Agent cannot see labor schedules. Vendor Agent cannot touch shrinkage. US tenant cannot query EU tables. Least-privilege, machine-enforced.
-
Classifications drive accessTag a column
pii,financial, oroperationalonce. Every agent, every query inherits the rule. No copies of the policy to keep in sync. -
Who changed what, on the recordEvery charter edit, prompt change, and policy update is logged with name, time, ticket, and approver. Diff two versions side by side. Roll back in one click. Export to your SIEM.
-
Writes need a named humanRead-only by default. Exports, write-backs, schedule pushes. Anything that mutates state gates on approval from a role you define. Logged with the approver’s identity.
-
Audit any number on the pageClick a forecast, a margin call, a shrinkage flag. Ward shows the SQL, the source tables, the model, the parameters, and the backtest. Procurement stops asking how the number was made.
Your data, your keys, your region.
Customer Data is yours. Ward processes it under a limited license to deliver the service, and only that. Nothing trains a public model. Nothing leaves your region without a contract that says it can.
Where we are, and where we’re going.
Status, not aspiration. We tell you what’s in place today, what’s in flight, and when we expect each item to land. If you need something on this list before signing, ask. We’ll either send it or tell you when we can.
Every vendor that touches your data.
Listed below. If a sub-processor changes, we notify by email 30 days before the change takes effect, with an objection window per the DPA.
Single-tenant deployments can exclude any third-party LLM. Self-hosted open-weight models supported on request.
Coverage on file.
Response on the clock.
Cyber liability and technology errors & omissions coverage in force, with an AI rider that covers errors in model output. Carrier name and certificate of insurance available to your procurement team within one business day.
- Cyber liability with breach response
- Tech E&O with AI/ML rider
- Additional insured endorsement on request
- COI delivered via email or vendor portal
Documented runbook. Customer notification SLA per the DPA. Post-incident report with root cause and corrective action.
- Detection: 24/7 SIEM alerting
- Triage: on-call within 15 minutes
- Notification: 72 hours per DPA
- Postmortem: within 14 days
On the table before you sign.
Architecture diagrams, contracts, audit letters, insurance certificates. Most arrive within a business day. The few under NDA arrive after a one-page MNDA.
Found something? Tell us.
Coordinated disclosure. We respond within one business day, triage within three, and credit researchers in the changelog when fixes ship.
Your security review starts with a short list of questions.
Architecture, MSA, DPA, SOC 2 letter, COI. On the table before you sign.
Find out what your data has been hiding.
Tell us about your operation. We’ll show you the problems Ward catches — and the ones your current tools miss.