AI Safety & Governance
Test AI systems. Expose risks. Put safeguards into practice.
From red teaming and adversarial testing to bias, robustness, and safety evaluations, Daetis helps organizations identify how AI systems fail and test whether safeguards hold. We combine technical testing with human rights impact assessment, regulatory tools, and alignment research.
Put your AI to the test
An AI system can perform well in a demonstration and fail when faced with unexpected inputs, determined adversaries, or unfamiliar situations. We examine both the system's behaviour and the decisions people make using its outputs.
Red teaming & adversarial testing
Challenge systems with deliberate attempts to bypass instructions, manipulate outputs, expose sensitive information, or trigger harmful behaviour. Investigate how failures occur and whether protections withstand repeated attempts.
Bias & discrimination testing
Use comparative and synthetic cases to examine differences in treatment across groups. Trace how model outputs can translate into unequal access, decisions, or outcomes.
Robustness & reliability evaluations
Test ambiguous requests, edge cases, conflicting information, and changing conditions. Examine factual reliability, consistency, and how systems handle uncertainty.
Safeguard & human oversight testing
Check whether controls work in practice: when a system refuses, escalates, requests clarification, or hands a decision to a person. Assess whether reviewers have the information and authority to intervene effectively.
Assess the impact on people
Technical performance is one part of the assessment. The context of deployment, the people affected, and the consequences of a decision matter just as much.
Our human rights impact assessment work brings these elements together: mapping the system and its stakeholders, identifying potential harms, gathering evidence, and defining mitigation and oversight measures.
We support Human Rights Impact Assessments (HRIA), including the Fundamental Rights Impact Assessments required for certain deployers of high-risk AI systems under Article 27 of the EU AI Act.
Turn regulatory requirements into practical oversight
Institutions need to connect requirements to evidence, identify gaps, and document the reasoning behind their decisions.
The Aegis AI Regulation cartridge brings regulatory assessment into Daetis's evidence-based institutional platform, supporting structured review, traceable findings, and human decision-making.
Together, Aegis and our assessment work help organizations turn governance obligations into repeatable operational processes.
Investigate what makes alignment endure
Our alignment research explores how AI systems develop stable values and retain them under pressure.
Through Civilizational AI, we investigate how training environments, incentives, and social interaction may shape model behaviour, and how to distinguish learned compliance from more durable alignment.
This research informs the questions we ask when testing systems: does a safeguard generalize to unfamiliar situations? Does behaviour change when incentives shift? What evidence would demonstrate that an alignment approach holds?
From testing to action
Every engagement starts with a defined system, its intended use, and the decisions the assessment needs to support.
We agree the scope and evaluation criteria, investigate failure modes, and document findings with their evidence and limitations. We then help prioritize mitigations and define how improvements should be tested.
The aim is a clear basis for action: what failed, who could be affected, which safeguards need strengthening, and what remains unresolved.
Bring us the system you need to assess.
We work with teams building AI and institutions deploying, procuring, or overseeing it.