Now open — sign up and have a live widget today
Enterprise RAG chat platform

You can't answer at 11pm.
Hazzy can — and it never guesses.

Hazzy answers your customers instantly from your own documents — with the source attached to every reply, so it never makes anything up. No coding. Live today.

Free plan, no card needed Live in 10 minutes Every answer cites its source Indian pricing in ₹
Start free — no card needed
One script tag. Live on WordPress, Shopify, or hand-built HTML.
yourcompany.com
Hazzy AI 🟢 Online
What's your refund window on annual plans?
Annual plans can be refunded within 30 days of purchase, prorated after your first billing cycle.
[1] Refund Policy — refund-policy.pdf
Grounded & cited

Live interactive preview — type your own question, or try one below.

Cited
every answer sourced
Isolated
tenant-scoped by default
Approved
humans confirm writes
Logged
full audit trail
Built on Claude (Anthropic) Voyage AI embeddings PostgreSQL + pgvector Langfuse tracing
Not launched on trust — launched on architecture

We built the guardrails before we built the demo.

01

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]

02

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]

03

Every retrieval and every tool call lands in an append-only audit log — who asked, what was retrieved, what came back, and when. [3]

04

Your embed key only answers for the domains you've allow-listed. A copied script tag can't quietly impersonate your brand elsewhere. [4]

[1]Verified with an adversarial cross-tenant test that runs against the live stack, not just asserted in a spec.
[2]No "trusted client" exception — the rule holds for every account, on every write-capable action, with no override.
[3]Enforced at the application layer today; database-level write protection is the next hardening step.
[4]Enforced server-side on both the widget's config and chat requests — checked on every request, not just once at load.
The problem

Is your team answering the same question, every day?

The signs are everywhere:

  • The same twenty questions land in your support inbox every week
  • The answer is buried in a PDF three folders deep
  • New hires search five different docs before finding the real policy
  • The generic AI tool you tried last quarter confidently made something up
  • Customers give up before they get an answer
The Hazzy way

Imagine if every one of those was answered instantly — correctly, with a source attached.

It reads what you've actually published. Nothing else.

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.

Customer journey

From signup to a live widget, no staff required on our end.

01

Sign up

Create your account in minutes. No infrastructure to provision, nothing to install.

02

Create a workspace

Each site gets its own isolated knowledge base — a client can run more than one.

03

Upload your knowledge

Drop in PDFs and docs, or point Hazzy at your site and let it crawl.

04

Train

Content is chunked, embedded, and indexed. Nothing goes live until you publish it.

05

Install the widget

One script tag, dropped anywhere HTML runs.

06

Chat

Visitors get grounded, cited answers. You get the full transcript.

What to expect

What grounded support actually gets you.

Fewer repeat questions

Customers get the answer straight from your docs instead of waiting for someone to type the same reply again.

Always-on coverage

The widget answers around the clock — no time zone, no queue, no "we'll get back to you."

Consistent answers

Every reply traces back to the same published source of truth — not whoever happens to be on shift.

Less time hunting for policy

Support and sales stop digging through five PDFs to find the one paragraph that actually matters.

See it answer from your own docs, not a demo script.

Sign up
What's in the box

Built for the questions that actually keep you up at night.

Grounded & cited

Every answer traces back to a document. No citation, no answer — Hazzy retries once, then admits it doesn't know rather than guess.

Tenant isolation by design

Every query and embedding is scoped server-side to your account, checked at the database layer — never a prompt-level promise.

Embed anywhere

One script tag, rendered in an isolated frame so your site's styles and Hazzy's never collide. WordPress, Shopify, or raw HTML.

Account-aware, on request

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.

New

Humans approve every write

The assistant can propose an action — replying to a ticket, say — but someone on your team confirms it before anything changes.

Everything is logged

Every retrieval and tool call lands in an append-only audit trail — tenant, actor, input, output, timestamp.

Want this running on your own docs?

Sign up
Integration

One script tag. That's the whole integration.

Paste it into your theme, your page builder, or your <head> by hand. It loads asynchronously and stays out of your page-speed score.

<script
  src="https://cdn.haznox.in/widget.js"
  data-site="pk_live_9f2c…"
  async
></script>

Under 3kb over the wire, zero dependencies, renders inside its own isolated frame.

Integrations

Works with what you already run.

Embeds anywhere — it's just a script tag

WordPress Shopify Webflow React / Next.js Laravel / PHP Plain HTML

Connects to your backend, live today

WordPress plugin WooCommerce — read-only Shopify — read-only WHMCS

WhatsApp and Slack are on the roadmap — not live yet. See where things stand.

Who it's for

Built for teams that already have the answers written down.

Hosting & domain providers

Answer plan, pricing, and renewal questions from your own docs — Haznox is tenant #1, running this exact setup.

Ecommerce stores

Connect WooCommerce or Shopify so the widget can look up a customer's own order — scoped to that one account.

SaaS & service businesses

Turn your help docs and FAQ into a widget that answers support and pre-sales questions from what you've actually published.

Security & isolation

Two boundaries. Both non-negotiable.

The tenant boundary

Client A's knowledge base and conversations must never be reachable from Client B's widget — under any prompt, any query, any edge case.

Client B's widget asks a question
Client B's knowledge base only
Client A's data

The end-user boundary

Within one client's site, one visitor's order or ticket data must never surface to another visitor through the assistant.

Visitor X asks about their order
Visitor X's account only
Visitor Y's data
Roadmap

Phase one is live. The rest is being built in the open.

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.

Phase 1

Enterprise RAG Chat

Upload, train, embed, chat — grounded and cited, on your own site.

Live now
Phase 2

Knowledge Management

Collections, versioning, and review workflows for larger knowledge bases.

Phase 3

Enterprise AI Platform

Deeper backend connectors and account-aware answers, approval-gated throughout.

Planned
Phase 4

AI Agent Platform

Multi-step actions on your behalf — still never without a human's sign-off.

Planned
Phase 5

Workflow Automation

Proactive notifications and end-to-end workflows across your tools.

Planned

Follow the roadmap, or just get started on what's live today.

Sign up
Compared honestly

Hazzy vs. a generic AI chatbot tool.

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.

Pricing

Simple plans. Sign up and you're live today.

Every plan includes the full platform — upload, train, embed, chat, with a citation on every answer. Create your account, then pick a plan from your dashboard. No sales call required.

Citations on every answer Human approval workflow Full conversation logs

Need something larger or with specific compliance requirements? Talk to us about enterprise.

Questions

Straight answers, before you ask a widget.

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.

Yes — sign up and you're live today, no waitlist or sales call required.

Your content is split into chunks, turned into embeddings, and stored per-account. When someone asks a question, Hazzy retrieves the most relevant chunks — by meaning and keyword — and the model is only allowed to answer from what it retrieved, with a citation attached.

Every response is checked for a citation before it's sent. No valid citation triggers one retry with a stricter prompt, then a canned "I don't know" rather than ever shipping an uncited claim. It's a structural check, not just an instruction to the model.

Postgres for structured data and embeddings (with pgvector), object storage for raw uploaded files and transcript exports. Every table is partitioned by tenant, indexed on it, and scoped at the query layer — not just filtered after the fact.

Yes — PDF, DOCX, and plain text upload directly. Nothing reaches the live widget until you publish it, so you can review what got ingested first.

Yes — point it at one page, or let it crawl same-site links up to 20 pages and 3 levels deep. It respects robots.txt and is guarded against fetching internal/private addresses.

Brand color, greeting message, and tone today, plus up to four static conversation-starter buttons. Avatar/logo upload and widget positioning are on the near-term roadmap, not yet built.

The assistant itself will generally answer in whatever language it's asked in, since that's native to the underlying model — it isn't a separately built or tested feature yet. The widget's own buttons and labels are English-only today.

Claude is primary; if it's unreachable, the runtime automatically fails over to OpenAI or Gemini when those are configured, before ever falling back to a canned "I don't know." Provider failure degrades the answer quality, not the uptime.

Free, Starter, Growth, and Business plans, priced by message volume, knowledge base size, and seats — see current pricing above. Free never expires but sleeps after 30 days idle; paid tiers get annual billing for 2 months free, and you can change plans any time from your dashboard.

Ready when you are

Give your documents a voice that doesn't make things up.

Sign up
Built on architecture that assumes zero trust between tenants
Tenant-isolated by default Domain-allow-listed embeds Append-only audit log Human-approved writes
Sign up