Safe, sovereign AI for customer conversations.
Bespoke voice and chat agents that run on your infrastructure, answer only from sources you approve, and never keep your data.
- Zero data retention
- HIPAA-ready
- Your keys, your cloud
Safe by default, on every channel
Scripted demoTry a conversation
A scripted preview of Box One. Real deployments answer only from the systems and policies you approve, with every exchange logged.
Why sensitive organizations choose Box One
Request accessYour answers are already written down
Policies, program rules, scheduling, billing, claims. Your team answers the same questions by hand, all day, while callers wait. Most AI tools can’t be trusted with those conversations, because they guess, keep your data, and can’t prove what they said.
Box One is built for exactly those conversations.
Safe by design, not by promise
Box One answers only from sources you approve and cites every answer. It verifies identity before disclosing anything personal, never gives medical, legal, or financial advice, and hands off to a person when the source doesn't support an answer.
Before launch we red-team it on your real conversations: prompt injection, data-extraction attempts, and off-script questions. It doesn't go live until it passes.
Refusal behavior gets evaluated as rigorously as accuracy. A confident wrong answer is worse than no answer.
It runs inside your walls
Deployed into your own cloud accounts, respecting the permissions your systems already enforce. Model calls run under zero-retention, no-training terms, and the model sits behind an interface you own, so a better one swaps in without a rewrite.
At handoff the repository is yours. Stay with us for ongoing engineering, or take the keys.
Built for conversations that can’t go wrong.
Healthcare, finance, insurance, and public agencies can’t afford an AI that guesses, leaks, or forgets what it said. Every Box One deployment ships with these safeguards. None of them are add-ons.
No guessing
Answers come only from sources you approve, and every answer cites where it came from. When a source doesn’t support an answer, it says so instead of inventing one.
Stays in its lane
No medical, legal, or financial advice. Topics you rule out stay ruled out. Off-script, risky, or emotional conversations go straight to a person, with context passed along.
Verifies before it discloses
Callers and chatters are verified before anything personal is shared. PHI and PII are redacted from logs and transcripts by default.
Attacked before launch
We test every deployment against prompt injection, jailbreaks, and data-extraction attempts on your real conversation types. It doesn’t go live until it passes, and the tests re-run whenever the model changes.
Nothing kept, nothing trained
Every third-party model call runs under the provider’s zero-data-retention, no-training terms, disclosed to you before any data is sent. Your data never trains a model, ours or anyone’s.
Built for protected health information
PHI stays in your environment. Encrypted in transit and at rest, role-based access, HIPAA-eligible model endpoints only, and the administrative and technical safeguards your compliance team will ask for, documented.
Your infrastructure, your keys, your model
Deploy on your own servers or in your own cloud account, in the region you choose. You hold the encryption keys and the model keys. If your policy rules out external APIs, Box One runs on open-weight models hosted entirely inside your network.
Secure lines to your data and your customers
Connections to your records, scheduling, and billing systems run over private, encrypted channels with least-privilege access. Calls and chats with customers are encrypted in transit, and nothing is stored outside your environment.
Every word on the record
Every call, chat, source, tool call, and handoff is logged in your environment, searchable, and exportable for audits and complaints. You can always show exactly what was said and why.
| Box One | Typical AI voice & chat platforms | |
|---|---|---|
| Data retention | Zero retention, no training, disclosed per call path | Varies by vendor and plan |
| Sovereignty | Your servers or cloud account, your region, your keys | The vendor’s multi-tenant cloud and keys |
| Connections to your data | Private, encrypted, least-privilege, inside your network | Your data synced out to the vendor |
| Protected health information | Stays in your environment, HIPAA-eligible endpoints only | Sent to the vendor’s cloud |
| Safety testing | Red-teamed on your conversations before launch and on every model change | Generic, vendor-wide |
| Audit trail | Every word, source, and handoff, stored by you | Whatever the vendor’s dashboard keeps |
| How you pay for usage | The model provider’s rate, billed to you directly. No markup. | Per seat, per resolution, or per minute |
| When you leave | You keep the code, prompts, and evaluations | You start over |
Cost per use: no seat licenses, no per-minute or per-resolution fees, no markup on tokens. We benchmark models on your workload and pick the cheapest one that passes your safety and accuracy tests. Discovery ends with a written estimate of cost per call and per chat, next to what you pay today.
Box One: voice and chat AI, built for you and governed end to end.
Bespoke voice and chat agents on one safety layer. Start with one channel; the next reuses the same approved knowledge, guardrails, and audit trail. Every piece runs on the model that wins on your workload, and every piece is yours to keep.
Box One
The same answer, the same guardrails, and the same audit trail, whether people call or chat.
Box Voice
Bespoke phone and in-app voice agents. They verify callers, answer, book, route, and resolve, with every transcript logged and a warm handoff to a person when it matters.
Box Chat
Custom chat agents for your website and support channels. Answers from your policies and program rules with citations, and hands off when the source doesn't support an answer.
Box Guard
The safety layer under both. Guardrails, identity checks, PHI and PII redaction, access control, and a complete audit log of every call and chat. Model keys never leave your servers.
Also built to order
Workflow Analysis
Your workflows instrumented end to end. Where the time and cost actually go, and where AI pays for itself, before you build anything.
Ask about itRFP & Questionnaire Answering
Drafts answers to RFPs and security questionnaires from your past responses and policies, with every claim traced to its source for your team to approve.
Ask about itBring Box One inside your company.
Tell us which conversations to take on first: your phone line or your website chat. We build it around your systems and your compliance requirements, deploy it on infrastructure you control, and the code, prompts, and evaluations are yours to keep.
Sovereign. Zero data retention. HIPAA-ready. We reply within two business days.