ReKid ™
A knowledge engine, not a link list

Your child asks. ReKid™ answers — and checks itself.

ReKid™ writes the answer for your child's reading age, verifies every source it cites, and has a second model review the answer before it appears. No advertising, no tracking, no account for the child.

rekid.uk DEMO
ReKid™ A knowledge engine, not a link list
Query checked
Model proposed pages
Addresses checked
Pages read
Safe results shown

Pay per search — no subscription, nothing expires. No account for your child, no password, no email.

No ads No child accounts No tracking AI-driven

What ReKid™ actually is

Most kid-safe tools are ordinary search results with a blocklist bolted on: the child still gets ten links and has to work out which one to trust. ReKid™ does something different. It writes an answer — in language matched to your child's age — and shows the sources it used, after fetching each one to confirm it is real and still there. Before any of it reaches the screen, a second model reads the answer and can refuse it. An answer that fails that review is not shown at all.

An answer, written for the reader

The same question gets a different answer for a six-year-old and a twelve-year-old. You choose the age range when you buy; the writing follows it.

A second model checks the first

Every answer is reviewed by a separate model before it is shown. If the review does not pass — or does not complete — the answer is withheld. An unchecked answer is treated the same as a failed one.

Sources are fetched, not guessed

Models invent addresses that look right and do not exist. Every source is actually requested; dead links, 404s and parked pages are removed before your child sees the list.

THE PIPELINE

What happens between the question and the answer

Five steps run for every question a child types. Four of them can refuse.

  1. 1

    The question is checked first

    Before any model runs, the question is normalised — leetspeak, look-alike characters and spacing tricks are collapsed — and matched against blocked topics. Roughly thirty milliseconds, and no model is called at all.

  2. 2

    Unclear questions are asked back

    If a question could mean several things, ReKid™ offers a few clearer versions instead of guessing. This costs nothing from your allowance — we asked, so we pay for it.

  3. 3

    The answer is written for the age

    A model writes the answer at your child's reading level, together with a few quick facts. It can write in a different language from the interface — useful while a child is learning one.

  4. 4

    Every source is fetched

    Each address the model cites is actually requested. Ones that do not resolve, return 404, or land on an error or parking page are dropped. A dead link is worse than no link: a child clicks it and thinks they were wrong.

  5. 5

    A second model reviews it

    A different model reads the finished answer against the question and the age. It can approve, correct, or refuse. Refused answers are recorded so a grown-up can see the question was asked — but the text is never shown.

Four gates, each able to refuse

The design is fail-closed. When a check cannot complete, the answer is withheld rather than shown — an unchecked answer counts as a failed one.

Gate 1

The question

Runs before any model, so a blocked question costs nothing and produces nothing. Disguised spellings are normalised first, so look-alike characters and spacing tricks are caught too.

Gate 2

The writing

The answer is written for the age range on the package, not for an adult. Length, vocabulary and examples follow the reader, not the topic.

Gate 3

The sources

Every cited address is fetched. Blocked and high-risk domains are refused, redirects are re-checked at each hop, and private or loopback addresses are rejected outright. Dead and parked pages are dropped.

Gate 4

The review

A second model reads the finished answer before anyone else does. It approves, corrects or refuses. A refusal — or a review that fails to run — means the answer is not shown.

PRIVACY

What ReKid™ knows about your child

The honest answer is: almost nothing, and that is a design decision, not a promise.

What the search site stores

  • A one-way hash of the session key and of a device-specific secret — neither can be recovered from the database.
  • A salted hash of the IP address, used only for rate limiting.
  • A two-letter country code, taken from a header the network already sends.
  • The question and the answer that was written for it, so the same question can be answered again without spending your allowance twice.

What the search site never stores

  • No name, no surname, no date of birth, no school.
  • No email address and no password — there is nothing to sign in with.
  • On the search side there is no raw IP address anywhere, in any table or log. (On the buying side the order record keeps the IP address as part of the sale record.)
  • No location beyond the country code. No GPS, no city, no third-party lookup.
  • No advertising identifiers and no third-party trackers, because there are no ads.
ONE-WAY

The bridge between this site and the search site is one-way

getrekid.com knows who you are, because you bought something. The search site does not, and cannot ask. This site can tell that customer X owns package Y; the search site only ever sees package Y. It has no way to learn who asked what, and neither do we.

getrekid.com rekid.uk

Get your setup key

Pay per search — no subscription, nothing expires. No account for your child, no password, no email.

Buy questions