FTC · Open source
AI help for FTC teams, with a source for every answer

Re
fract.

AI help for FTC teams that refuses to guess: every answer comes from a real source, and it won't write robot code until it knows the robot.

5
AI skills, each tied to a source
2
Languages: Python and Java
5
Coding tools it works in
0
Answers without a source
Area
FTC
Status
Open source
Stack
Python · Java · MCP · Claude Code
What it is

What it
is.

Ask a general AI assistant an FTC question and it will answer confidently, even when it is wrong: a rule number that does not exist, or code for a robot part the team does not have.

Refract is a set of five AI skills for FTC teams that only answer from a real source: the game manual, parts specifications, or the team's own code. If it cannot find a source, it says so. It is open source.

How it works

How it
works.

Know the robot first

It reads the team's code and parts list, and it will not write robot code until the team confirms the robot's setup.

Answer rules from the manual

Rule questions are answered from a marked-up copy of the game manual, following its cross-references, with the rule cited.

Do the maths in code

Questions about motors and parts are worked out by a script from real specifications, not estimated in prose.

Try It

See it
decide.

The grounding gate

Pick a question a team might actually ask. This is the routing logic Refract applies before it answers anything.

The question
What Refract does
What I learned

What I
learned.

Saying "I don't know" is a feature

The goal was never an assistant that knows more. It was one that will say what it cannot know. For a team facing inspection, a confident wrong answer is worse than no answer at all.

One rule can remove a whole kind of mistake

Making the team confirm the robot's setup before any code is written removed the entire category of code written for a robot that does not exist.