The Problem
AI can make decisions. Can you reconstruct them?
Modern AI applications can involve models, agents, prompts, documents, databases, APIs, policies, retrieval systems and human intervention. Each of those changes over time — and so does the evidence about them.
Questions asked afterwards
What a board, auditor, regulator or customer may later ask.
- Q01
What information was available to the AI?
- Q02
What did the organisation believe to be true at that moment?
- Q03
Which model and model version were used?
- Q04
Which system prompt and user prompt were active?
- Q05
Which documents or RAG chunks were retrieved?
- Q06
Which tools and APIs were invoked?
- Q07
Which business policies and controls applied?
- Q08
Was a human involved, and did they approve, reject or override the output?
- Q09
Has the evidence changed since the event?
Logs tell you that something happened. Safe Haven is designed to reconstruct the state in which it happened.
Bitemporal thinking
There is more than one kind of time.
10 March
Customer's actual status changes to LOW RISK.
14 March
AI makes a decision while the system still shows HIGH RISK.
18 March
Correct information reaches the organisation.
At the decision point
- Reality
- LOW RISK
- System knowledge
- HIGH RISK
An AI decision should be understood against the information and rules actually available when the decision occurred.
What was true? — Valid Time
What was known? — Transaction Time
Strategic engagement
Government, banking or technology stakeholder?
We are currently developing the Safe Haven architecture and exploring potential pilot, policy, infrastructure and funding partnerships.