C
CAIS Institute
volunteer_activismNonprofit Research Institute

Making companion AI
safe for the most
vulnerable

The CAIS Institute is the first independent research institute dedicated to testing whether AI companions detect crisis signals and protect vulnerable users from harm. We publish openly and guide platforms toward safer systems.

location_onLisbon, Portugal
publicEU-based nonprofit

Testing in progress

64%

of companion AI models tested
fail to detect indirect crisis signals

Our mission

“Every person in crisis deserves an AI that recognises the danger — not one that makes it worse. We exist to make sure companion AI systems meet that standard, independently and transparently.”

CAIS Institute

The urgency

The problem is real, growing, and largely unaddressed

72%

of teenagers have used AI for companionship

Common Sense Media, 2025

0

independent testing standards exist for companion AI crisis response

CAIS Institute Research, 2026

$15K

per day — NY civil penalties for non-compliant AI companion operators

NY State Law, 2025

warning

No independent testing standard exists

New York and California now mandate crisis detection protocols for AI companions. The EU AI Act classifies emotional support AI as high-risk. Companies are self-certifying compliance with no external verification. Critics argue this sustains the safety crisis — stakeholders want independent audits, transparent red-team reports, and public hazard metrics. The CAIS Institute was founded to fill this gap.

What we do

Research. Test. Publish.

We are an independent nonprofit building the testing standard the companion AI industry needs — and regulators are now mandating.

search

Research

We conduct rigorous, reproducible studies on how companion AI systems respond to users in crisis. Every claim is backed by machine-generated artifacts and open methodology.

Peer-reviewed methodology aligned with WHO safe messaging guidelines

build

Test

We run adversarial probes against companion AI models — testing crisis detection, guardrail integrity, dependency patterns, and safe messaging compliance across real-world scenarios.

80+ probes across 4 safety domains, tested against 6+ target configurations

campaign

Publish

We publish all findings openly — research papers, probe libraries, hardening guides, and governance frameworks. Platforms, regulators, and civil society all benefit equally.

All research published under open licence at companionaisafety.org

80+

Safety probes in our library

6

Target configurations tested

4

Safety domains covered

100%

Research published openly

Our team

Built by researchers, for accountability

person

David Ahmann

Research Lead

person

Devan Shah

Governance

person

Talgat Ryshmanov

Engineering

Our methodology

Four domains of companion AI safety

We test systematically across the four critical areas where companion AI models most frequently fail vulnerable users.

emergency

Crisis Signal Detection

Does the model detect escalating distress? We test with graduated ideation probes, indirect expression, coded language, and farewell patterns that simulate real crisis conversations.

28 probes
shield

Guardrail Validation

Can the safety layer be bypassed? We run jailbreak vectors designed specifically for companionship contexts — role-play exploits, system prompt overrides, and gradual normalization attacks.

18 probes
link_off

Dependency Assessment

Does the model foster unhealthy reliance? We test whether it encourages human relationships, sets AI-human boundaries, and discloses its limitations honestly.

12 probes
verified

Safe Messaging Compliance

Does the model follow WHO, AFSP, and SAMHSA guidelines? We check crisis resource provision, method detail avoidance, contagion prevention, and medication safety.

22 probes

Work with us

Fund the standard the industry needs

The CAIS Institute is seeking partnerships with foundations, governments, and platforms committed to making companion AI safe. Our research is independent — our impact is shared.

EU & US

Grant applications

Associacao

Legal structure

Portugal

Jurisdiction

Nonprofit

Tax status