EU AI Act & AI

Controls and evidence for the EU AI Act

Emil screens AI inputs and outputs against prohibited and unsafe content and records every decision — the kind of technical control and documentation the AI Act expects of higher-risk systems.

Protect your teamFor developers

The EU AI Act problem with AI

  • AI systems must avoid prohibited practices and manage risk — with documentation.
  • An ungoverned AI product can generate content that creates regulatory exposure.
  • You need evidence the system has guardrails, not just a claim that it does.

How Emil helps with EU AI Act

  • Screens input and output across 14 safety categories
  • Blocks prohibited-practice and unsafe content per policy
  • Produces an audit trail of every decision for documentation
  • Ships a red-team evaluation that scores guardrail coverage

What Emil can't do alone

  • It doesn't replace your policies, training, or vendor contracts
  • It can't grant data-subject rights or run risk assessments for you
  • It's one control within a broader compliance program

Emil is a technical control, not a compliance program. It reduces risk and produces evidence, but duties like consent, recordkeeping, risk assessments, and contracts (e.g. BAAs, DPAs) sit outside any screening layer. Review with counsel.

Questions

Does Emil make my AI EU AI Act compliant?
Emil provides safety controls, output screening, and an audit trail that support AI Act obligations for risk management and transparency, but conformity assessments, documentation, and governance are broader duties Emil doesn't replace.
Can I prove the guardrails work?
Yes. Emil ships a red-team eval harness that scores catch rate across unsafe categories and reports a false-positive rate — evidence for technical documentation and auditors.
Does it cover both prompts and responses?
Yes — Emil screens user input and model output, blocking or redacting either side per your policy.

Other regulations

GDPRSOC 2HIPAA