ReKid
English
Sign in Get a free key

The four safety layers

Each layer can refuse on its own. The design is fail-closed: when a check cannot complete, the result is dropped rather than shown.

Layer 1

The query

Runs before the model. Blocks the search outright and records the reason. Confusable characters, leetspeak and spacing are normalised first, so disguised spellings are caught too.

Layer 2

The proposed address

Runs on every address the model returns. Blocks adult and high-risk top-level domains, known adult and gambling domains, and unmoderated user-content platforms.

Layer 3

The fetch

Follows redirects one hop at a time and re-checks the destination at every hop. Refuses private, loopback and link-local addresses, so an address cannot be used to reach inside the server.

Layer 4

The page text

Scans the beginning of the real page HTML — title, description and body text. A page whose content trips a rule is dropped even though its address passed.

How a search actually works

  1. 1

    The question is checked first

    Before anything else, the query is normalised — leetspeak, look-alike characters and spacing tricks are collapsed — and matched against the blocked topics. Roughly thirty milliseconds, no model call.

  2. 2

    The model proposes pages

    A Claude model suggests addresses that would genuinely answer the question, written for a child's reading level.

  3. 3

    Every address is checked

    The domain is checked against blocked and risky top-level domains and known unmoderated platforms. Private addresses and redirect tricks are refused.

  4. 4

    Every page is read

    The engine fetches the page, reads the beginning of the real HTML and scans it. If the page text trips a safety rule, it is dropped — even if the domain looked fine.

  5. 5

    Only survivors are printed

    What reaches the screen has passed all four layers and has a real title read from the page itself.

What the safety layers block

The list below is the topic dictionary, not the whole system: pages are also judged by their address and their actual text.

CategoryExamples of what is blocked
Adult contentPornography, nudity, sexual material, adult sites and adult top-level domains
Drugs, alcohol, tobaccoHow to obtain or use, purchase sites, vaping
GamblingBetting sites, casinos, odds, loot-box promotion
Violence and weaponsGraphic violence, gore, weapon purchase, explosives
Hate and extremismHate speech, terrorist or extremist material
Self-harmHandled with care — see below
Dating and stranger chatDating apps, random-stranger video chat
Unmoderated user contentSocial networks, forums, comment sites, chat platforms

Self-harm is handled differently

A child asking about self-harm is not misbehaving. ReKid does not return search results for these questions, and it does not scold. It shows a short, warm message encouraging the child to talk to a grown-up they trust, alongside a helpline. Nothing about the question is attached to a name, because ReKid does not know any names.