[·]AnswerHatch
Cite or refuse

It cites, or it declines.

AnswerHatch is an embeddable question-and-answer widget that answers your visitors from the pages your site already publishes, puts a link to the source on every answer, and installs with one line of code.

<script async src="https://cdn.answerhatch.com/api/widget.js"
  data-agency="your-site" data-key="your-key" data-env="prod"></script>

That is the whole install

The two shapes an answer can take
Answered

Every answer carries the page it came from, so a reader can check it before acting on it.

answerhatch.com/security answerhatch.com/privacy

Declined

I do not have a source for that. My sources are AnswerHatch's own published pages, and that question sits outside them.

no registered source The reason goes to the reader. Nothing plausible is composed to fill the gap.

ProcessedOn our own machines
Model APINo third-party model in the path
RetentionQuestions deleted after 30 days
PricingFlat tiers from USD 19 a month
Live on this page

This page runs the widget. Try to break it.

The Ask button on this page is the real product, running over AnswerHatch's own published pages. Ask it something we cover and it answers with links you can open. Ask it something we do not cover and it declines, and tells you why. Courts in Canada and Germany have now held operators responsible for what their chatbot said, on the reasoning that the operator could have prevented the false statement. Declining is how we prevent it.

Probe 1 / in scope What happens when AnswerHatch has no source for a question?
Probe 2 / out of scope What is the best pizza in Chicago?

Then open the Ask button on this page

How it works

Three steps, and the third one is allowed to say no.

Governance sits outside the model, in code that runs before and after it. A prompt can be talked out of a rule. A gate in the request path cannot.

01 / SCREEN

Refused before the model

A deterministic scope screen and a prompt-injection screen run before the model is called. Off-topic and adversarial requests are turned away without reaching it.

02 / RETRIEVE

Only what we crawled

The question is matched against the pages crawled from your site. Every document in the registry carries the URL it came from, the date it was fetched and its hash.

03 / CITE OR REFUSE

No source, no answer

An answer ships only with registered sources attached. With no source, the widget declines and gives the reason. This is a gate in the platform, not an instruction in a prompt.

What you get

One line of code, and a key bound to your domain.

One script tag

The widget loads from our CDN and renders on your pages. Nothing to install on your server, and no rebuild of the site around it.

Keys bound to your origin

Each key is issued against the domain you nominate. A key copied out of your page source does not serve answers somewhere else.

Preprod and prod

Every subscription runs a preprod and a prod environment, each with its own corpus, keys and bindings. Test against preprod, promote when you accept it.

A registry, not footnotes

Crawled pages go into a provenance registry of sources, derivations and decisions. The citations in the widget are a view of that registry, and a compliance officer can ask for the registry itself.

Voice

Ask out loud. Hear the answer, sources included.

A visitor speaks the question and the answer is read back through their speakers. For a visitor who cannot read the screen, the whole exchange runs by ear.

Speech to text in the browser

The Ask by voice button transcribes the question in the visitor's browser. The same pipeline answers it as a typed question: screen, retrieve, cite or refuse.

Who does the transcribing

Chrome and Edge send the audio to their own vendor's speech service. Safari transcribes on the device. AnswerHatch receives text, never audio.

Answers read aloud

Every answer carries a Listen button. Setting data-voice="on" on the script tag makes the widget open listening, read the answer aloud, and listen again for the next question.

It is not a screen reader

It reads its own answers, not the rest of your page. Native screen readers work beside it through ARIA live regions, so nothing is read twice. Adding it does not make your site conformant, and we will never say it does.

Trust

Where the data goes, stated literally.

The category standard is "your data is not used to train models", which says nothing about where the data is processed, how long it is kept, or whose model API it passed through on the way. Here is the specific version.

Processed on our own machines

Visitor questions are processed on AnswerHatch-operated infrastructure, on machines we run.

No third-party model API

A question is never handed to an outside model provider in order to be answered. Models are not fine-tuned on your content either.

Thirty days, then deleted

Visitor questions are retained for 30 days so a fault can be diagnosed and a refusal reviewed, and are deleted after that.

One sub-processor

Cloudflare carries the network in front of the platform. That is the whole list. We hold no third-party security certification today and will not imply otherwise.

Pricing

Flat monthly tiers with the caps printed on them.

USD, ex tax. Annual billing is ten times the monthly price. No credit balance to burn down and no per-message meter behind the plan.

Personal $19 per month
  • 250 pages
  • 300 answers a month
  • 1 domain
Starter $89 per month
  • 2,000 pages
  • 750 answers a month
  • 1 domain
Professional $449 per month
  • 10,000 pages
  • 3,000 answers a month
  • 3 domains
Scale $1,290 per month
  • 50,000 pages
  • 10,000 answers a month
  • 10 domains
Objections

The four questions everyone asks.

Why not just point people at ChatGPT?

A general assistant answers from the whole web and from its training data. It has no way to know which of your pages is current, and no obligation to point at one of them. AnswerHatch answers only from the pages crawled from your site, attaches the page it used, and declines when it has none. The question text stays on our platform instead of being sent to a third-party model API.

see /security

What happens when it does not know?

It declines and gives the reason. It does not assemble a plausible answer out of adjacent material. Refusal is a gate in the pipeline: an answer with no registered source does not ship. You can test that on the widget on this page right now.

see the demo

Where does our data go?

It is processed on AnswerHatch-operated infrastructure, on machines we run. No third-party model API is in the path. Visitor questions are retained for 30 days and then deleted. Cloudflare sits in front of the platform as the network layer and is our only sub-processor.

see /privacy

What does it cost?

Flat monthly tiers from USD 19 to USD 1,290, ex tax, with the page and answer caps printed on each one. Annual billing is ten times the monthly price. Above the Scale tier it is a conversation rather than a plan: [email protected].

see /pricing

Subscribing takes a few minutes: pick a plan, add your site, paste one line of code. Start your subscription. For an estate larger than Scale, write to [email protected].