Is it safe to put company code into Cursor or Copilot?

Not by default. Whatever you paste or open gets sent to the AI provider's servers, including secrets and customer data. Emil sits between your tools and the model and catches API keys, credentials, customer data, and source code before they ever leave.

Can AI coding tools see my API keys and .env files?

Yes, whenever they end up in the files or prompts you send, which is the most common way secrets leak. Emil detects keys, tokens, passwords, and .env values and redacts them before the prompt reaches the model.

Does Emil slow down my AI?

No. Emil screens in the moment and hands the model a clean prompt, so you get the same responses at the same speed.

Does Emil store my prompts or my code?

No. Emil processes your text in memory and keeps only a short screening record (the decision, risk score, and a redacted preview), never the full content. Classification runs on Emil's own infrastructure, is never sent to a third-party model, and is never used for training.

Which tools does Emil work with?

Anything OpenAI-compatible: Cursor, Claude Code, Copilot, Lovable, v0, ChatGPT, Gemini, DeepSeek, Ollama, and self-hosted models. Point your tool at Emil instead of the provider, or use the browser extension if you don't write code.

Do I need to be technical to use it?

No. Developers change one line of config (the base URL). Everyone else uses the one-click browser extension that screens prompts before they reach the AI.

Education

AI in education that protects students by default

For staff, Emil redacts FERPA-protected student records before prompts reach an AI. For edtech platforms, one API call screens every prompt and response for age-appropriate content.

Protect your team For developers

The problem

Teachers paste student work and records into AI tools to draft feedback, exposing FERPA-protected data.
An edtech platform's AI can surface age-inappropriate content to minors.
Schools and vendors must answer to FERPA and COPPA but lack technical controls.

What Emil catches for education

Student names tied to records or grades
Education record identifiers
Age-inappropriate or unsafe content in AI output
PII in prompts and responses

Regulations this maps to

FERPA
COPPA (under-13)
State student-privacy laws

A content filter reduces regulatory risk but isn't compliance on its own. Review presets with counsel.

Questions

How does Emil help with FERPA?

Emil detects and redacts student-record identifiers before a prompt reaches an AI tool, and keeps only metadata — so FERPA-protected data isn't disclosed to an AI vendor.

Can it keep an edtech AI age-appropriate?

Yes. Emil screens AI responses and can block unsafe or age-inappropriate content before it reaches a student — for staff via the browser extension, for platforms via one API call.

Does it work for both teachers and platforms?

Both. Teachers use the no-code browser extension; edtech platforms route their AI through Emil's OpenAI-compatible proxy.

What about students under 13?

Emil includes a COPPA-aware policy preset for products serving children under 13, blocking prohibited data collection and unsafe content.

Other industries

Healthcare Legal AI Builders