# Access models for security and safety work that mainstream AI often refuses

> Source: <https://abliteration.ai/platform>
> Published: 2026-11-11 18:56:48+00:00

Platform

# Models, policies, and data.

Access models for security and safety work, apply your organization’s policies, and generate data for training and evaluation.

Model API

## Connect the tools you already use.

Access models for security and safety work that mainstream AI often refuses. Keep your OpenAI or Anthropic client; change the endpoint, API key, and model.

[Read the API documentation](https://docs.abliteration.ai)

Policy Gateway

## You decide what your team can ask for.

Write rules for the work your organization authorizes. Requests outside them are refused before they reach the model.

Your rule

Security testing: company-owned systems

- Run an SQL injection test against our staging site. Allowed· Reaches the model
- Run an SQL injection test against a competitor’s site. Refused· Stopped before the model

[Explore Policy Gateway](https://abliteration.ai/policy-gateway)

Training Data

## Turn one brief into training and evaluation data.

Describe the cases your classifier or model must handle. You receive records in the formats you train and test with.

Example brief

Payroll phishing and legitimate payroll messages for an email classifier, with hard cases held out for evaluation.

- ### Labeled examplesTrain a classifier Your payroll account is locked. Confirm your password at payro11-update.example within 2 hours. PhishingOctober payslips are available in the employee portal. Sign in using your saved bookmark. Legitimate
- ### Preference pairsTune a model’s responses Is this phishing? “Your deposit is on hold. Reply with your password to release this month’s pay.” 
  - Preferred
  - Phishing. It asks for a password by reply, which a payroll team would not request.
  - Rejected
  - Legitimate. Payroll notices about held deposits are often urgent.
- ### Evaluation setsMeasure a model before release Your W-2 is ready. Download it at payro1l-docs.example/secure. Expected: PhishingLookalike domain Open enrollment closes Friday. Review your benefits in Workday. Expected: LegitimateUrgent but safe

[Explore Training Data](https://abliteration.ai/training-data)

## Evaluate it on your own work.

Your prompts and outputs aren’t stored by default or used to train models. Review our evaluations and data policies, or talk with us about your organization’s requirements.