Hazzy turns your docs, policies, and pricing pages into a chat widget that only speaks from what you've published. Every answer carries a citation back to its source — or it says it doesn't know.
Every query, embedding, and tool call is scoped to your account at the database layer — never inferred by the model, never trusted from the client. [1]
Any action that changes a customer's account or money requires a person on your team to approve it. The assistant proposes; it never executes alone. [2]
Every retrieval and every tool call lands in an append-only audit log — who asked, what was retrieved, what came back, and when. [3]
Your embed key only answers for the domains you've allow-listed. A copied script tag can't quietly impersonate your brand elsewhere. [4]
The same twenty questions land in your support inbox every week, the answer is buried in a PDF three folders deep, and the generic AI tool your team tried last quarter confidently made something up rather than admit it didn't know.
Upload your docs or point Hazzy at your site. It chunks, embeds, and indexes the content — then answers only from that material, with a source attached. Below a confidence floor, it hands off instead of guessing.
Create your account in minutes. No infrastructure to provision, nothing to install.
Each site gets its own isolated knowledge base — a client can run more than one.
Drop in PDFs and docs, or point Hazzy at your site and let it crawl.
Content is chunked, embedded, and indexed. Nothing goes live until you publish it.
One script tag, dropped anywhere HTML runs.
Visitors get grounded, cited answers. You get the full transcript.
Every answer traces back to a document. No citation, no answer — Hazzy retries once, then admits it doesn't know rather than guess.
Every query and embedding is scoped server-side to your account, checked at the database layer — never a prompt-level promise.
One script tag, rendered in an isolated frame so your site's styles and Hazzy's never collide. WordPress, Shopify, or raw HTML.
Once connected, the widget can look up a logged-in visitor's own order or ticket status — scoped to that one person, never anyone else's.
Early accessThe assistant can propose an action — replying to a ticket, say — but someone on your team confirms it before anything changes.
Every retrieval and tool call lands in an append-only audit trail — tenant, actor, input, output, timestamp.
Client A's knowledge base and conversations must never be reachable from Client B's widget — under any prompt, any query, any edge case.
Within one client's site, one visitor's order or ticket data must never surface to another visitor through the assistant.
We'd rather ship a narrow product that works than a broad one that doesn't. Each phase only starts once the one before it is solid.
Upload, train, embed, chat — grounded and cited, on your own site.
Collections, versioning, and review workflows for larger knowledge bases.
Deeper backend connectors and account-aware answers, approval-gated throughout.
Multi-step actions on your behalf — still never without a human's sign-off.
Proactive notifications and end-to-end workflows across your tools.
| Feature | Hazzy AI | Generic AI chatbot |
|---|---|---|
| Cites its sources on every answer | Always | Rarely |
| Tenant data isolated at the database layer | Enforced | Varies |
| Says "I don't know" below a confidence floor | Always | Rarely |
| Human approval required before any write action | Enforced | Uncommon |
| Every retrieval and tool call audit-logged | Always | Rarely |
| Embeds anywhere with one script tag | Yes | Varies |
Comparing against the general category, not a specific named product — we haven't tested every alternative ourselves.
Hazzy is pre-pilot — we're onboarding a small number of design partners before opening signup widely. Pricing will be usage-based, tied to conversation volume, knowledge base size, and seats; nothing is final until we've priced it against real usage.
No credit card. We'll reply from a real person, not an autoresponder.
It says so. Below a confidence threshold, Hazzy hands off instead of guessing — a wrong "I don't know" costs you less than a wrong answer with your name on it.
No. Every table is scoped by tenant at the query layer, not just checked in application code — and it's verified with a deliberate adversarial test that tries to breach it.
Only the ones you turn on, and only after someone on your team approves each one individually. It can propose an action; it can't execute one unsupervised.
Inside an isolated frame on your page, loaded by a small asynchronous script. Your site's styles and scripts never touch it, and it never touches yours.
Not yet — we're pre-pilot, onboarding a small number of teams before opening signup widely. Request early access above and we'll follow up directly.