Documentation

How Trust Turtl works

A quick tour of what happens when you click the icon on a page.

The short version

Trust Turtl reads the page you're looking at and sends the visible content to a language model. The model weighs a handful of clues and sends back a rating, a score, and a short explanation.

Think of it as a second set of eyes. The rating is a prompt to look closer, not a final call.

The pipeline

  1. Collect visible content

    When you click the icon, the extension reads the visible text of the active tab plus a sample of its images and embedded videos. Background tabs and pages you haven't opened it on are off limits.

  2. Send to the analysis service

    The collected content and the page URL go to the Trust Turtl backend on Firebase Cloud Functions. The backend forwards the material to a language model with a structured prompt.

  3. Look for clues on the page

    The model weighs the domain, the writing, the presence of citations, image and video context, and patterns that tend to show up on low-quality pages.

  4. Return a structured result

    The response includes a trust rating, a 1 to 10 score, a summary, and a per-section breakdown. The popup renders it and the toolbar icon picks up the rating color.

What the ratings mean

Suspect
Score 1 to 3

Patterns common on misleading pages. Missing sources, sensational framing, or claims that do not line up.

Uncertain
Score 4 to 7

A mixed bag. Some parts read as solid, others are vague, opinion-driven, or hard to check at a glance.

Trustworthy
Score 8 to 10

Reads like reliable content. Clear attribution, consistent voice, and context you can follow back to a source.

What the model looks at

language
Domain

Where the page lives. Known publishers, aggregators, and content farms all read differently.

text_fields
Text

Voice, rhythm, citations, and the quiet patterns that give AI-generated or templated copy away.

image
Images

Whether the visuals actually support the story, or feel generic, unrelated, or synthetic.

play_circle
Video

Where embedded clips come from and how much the page leans on them in place of reporting.

Privacy and data

Trust Turtl only reads a page when you click the icon on it. Background tabs, private windows you have not interacted with, and the new-tab screen stay untouched.

The page content and URL go to the Trust Turtl backend so it can be analyzed. Requests are not tied to an account, and the extension does not keep a history of your browsing.

info
A note on limits. Language models can be wrong, especially on niche topics or a story that broke ten minutes ago. Treat the rating as a nudge to look closer. For anything that matters, read the source.

Trust Turtl is a hint, not a verdict. Cross-check the things that matter.