Calibrity

• 

  Calibrity's home screen introduces the core idea: learn when to Trust, Verify, or Reject AI answers and calibrate confidence to evidence.

• 

  Core interaction screen: the student reads an AI answer, chooses Trust, Verify, or Reject, and rates confidence from 0–100%.

• 

  Example of a reliable AI answer with an explanation, user decision, confidence level, and score breakdown.

• 

  Example of an uncertain AI answer where verification is the ideal action, with feedback explaining why caution is warranted.

• 

  Example of an unreliable AI answer showing how Calibrity rewards correct rejection and explains the hidden error.

• 

  Final calibration profile showing the user's score, overtrust, undertrust, verification behavior, and confidence patterns.

Inspiration

AI answers can sound fluent and convincing even when they are wrong or uncertain.

Calibrity was built to teach students a practical skill: knowing when to trust an AI answer, when to verify it, and when to reject it.

What it does

Calibrity presents students with simulated AI answers across different topics.

For each answer, the user chooses:

• Trust
• Verify
• Reject

They also rate their confidence from 0–100%.

Calibrity then measures patterns such as overtrust, undertrust, appropriate verification, and overall confidence calibration.

How we built it

Calibrity is built with React, TypeScript, and Vite.

The prototype uses reviewed, pre-written scenarios so the educational feedback remains predictable and reliable.

The scoring system considers both the user's decision and their confidence level.

Everything runs locally in the browser with no account, backend, database, or personal-data collection.

Challenges

The main challenge was preventing users from getting a high score simply by choosing Verify for every answer.

We redesigned the scoring system so that Trust, Verify, and Reject are each valuable only when appropriate.

What we learned

AI literacy is not only about spotting false information.

Students also need to learn how strongly they should trust information based on the available evidence.

What's next

Future versions could include adaptive scenarios, more subjects, source-verification exercises, and classroom tools.

Built With

• css
• html
• react
• typescript
• vercel
• vite