Skip to main content

Observation · evidence · human judgement

How FASO works

FASO helps people examine how AI behaviour changes over time. Our focus is on changes that emerge from the model itself, rather than behaviour deliberately directed by people. We bring together observation, a dependable record and human judgement to understand what the evidence can tell us.

Current technical status · updated 11 September 2026

An operating system, with independent validation ahead.

Regular observation is underway. Independent assessment is now needed to test the system’s reliability, limitations and readiness for wider use.

Built and internally tested

Technical foundation

An operating observation system and its testing environment are in place. Internal checks support development and review.

Monitoring underway

Regular interval observation

Four AI models are being monitored at regular intervals. The first change in model behaviour was identified on 7 September 2026, and developer notification has been completed.

Not live

Continuous monitoring

Further monitoring capabilities have been developed, but continuous operation has not been enabled. Additional integration and assurance work remains.

Validation sought

Independent validation

Independent external validation has not been completed. Additional funding is being sought for detailed validation of the system and the organisational design.

The work in practice

From observation to a finding people can examine.

01 · Context

Establish what is being observed

We record which model is being observed, its stated version and the conditions of the observation. This context helps reviewers consider known developer updates or changes in how the model is being used.

02 · Observation

Follow behaviour over time

FASO retains observations with their source and timing, so later behaviour can be examined alongside earlier behaviour. The original evidence remains available for authorised review.

03 · Review

Examine a possible change

When a difference is identified, people examine the evidence and consider alternative explanations, including deliberate changes by a developer or user. A difference alone does not establish model-derived drift, its cause, harm or intent.

04 · Communication

Explain what the evidence supports

Findings explain what was observed, when it happened and what remains uncertain. Where appropriate, the relevant developer is notified. Wider sharing follows the permissions and confidentiality arrangements for the evidence.

Evidence that can be examined.

A useful record shows both what happened and how the understanding of it developed. The time of an observation, the time a change was recognised and any later review are kept distinct, so earlier evidence can be revisited without losing what was known at the time.

Read the evidence review guide

Explore the evidence and safeguards

Follow the detail that matters to you.

Testing and independent validation

See how internal testing differs from an independent assessment of validity.

Understand validation

The organisation behind the work

See the public-interest purpose FASO is being built to serve.

Explore the six organisational priorities, the proposed safeguards and the work still needed to establish the institution.