Research / models

Base models

Specialized base models built to keep AI agents within the law

Base model • Legal

Seny

When we fine-tuned our judges on top of publicly available base models, they lacked specialized legal knowledge and multilingual capabilities. So we built our own base model.
Explore Seny →

Judge catalog

Use our judges to check whether your AI is behaving within the law and your policies. Our judges are built on Seny, so they're fast, accurate and multilingual.

Explore benchmarks →

Core protection

Safety

Detects user messages that violate the Alinia safety policy in a named category: violence, hate, wrongdoing, or sexual. The category is supplied per request, so one model serves all four.

v2.2.1 · Oct 2026
Security

Detects user messages attempting to bypass, manipulate, or override an AI assistant's safety constraints.

v2.4 · Oct 2026

Regulatory judges

Investment advice

Detects assistant responses constituting investment advice under MiFID: a personal recommendation on transactions in financial instruments, presented as suitable for the person or based on their circumstances.

v3.3 · Oct 2026
Creditworthiness

Detects assistant responses that evaluate, infer, or apply a creditworthiness or affordability judgment about an individual, or use one to set or restrict credit access or terms.

v0.3 · Oct 2026
Life & health insurance advice

Detects agent responses giving personalised life or health insurance advice: individualised pricing, risk assessment, eligibility, underwriting classification, or product recommendation.

v1.2 · Oct 2026
Insurance advice (US)

Detects assistant responses that cross from general insurance education into regulated advice: a personalised, product-specific steer.

v0.2 · Oct 2026
Tax advice

Detects assistant responses that give tax advice: applying a specific tax rule to an identifiable person, entity or transaction and reaching a conclusion, computation or recommendation.

v1 · Oct 2026
Legal advice

Detects assistant responses that give legal advice: engaging a specific person's legal situation and analysing it, answering it or directing their next legal step.

v1 · Oct 2026
resources

Latest news from Alinia

Research, Articles, Product Updates, and Customer Stories

​
See all under Resources
AI Research
•
•
October 1, 2026
Seny, a specialized base model built to keep AI agents within the law
AI Research
•
•
October 1, 2026
Alinia Releases Benchmark Data for Legal and Tax Advice Evaluation
AI Research
•
•
February 6, 2026
Improved version of Alinia’s Security Guard