State survives model handoff
Begin with one model and resume through another while testing only observable continuity.
CURRENT EXPERIMENT / 001[DESIGNING]
Can an agent survive changing models?
Hypothesis: identity, memory, permissions, and unfinished work can remain continuous while the reasoning model and interface are replaced.
01 / TEST CONTRACT
WHAT MUST BE TRUE
A demo is not a result until it can fail.
The first public demonstration will use explicit success criteria, intentional failure cases, and a complete receipt trail. Passing conversation quality alone does not count.
[planned]
Private context remains private
Verify that continuity does not require disclosing unrelated private context.
Restart recovery
Stop the continuity service, restart it, and resume with correct state and provenance.
False-memory rejection
Inject a conflicting unsupported memory and require qualification or refusal.
Human-readable receipt
Explain what was recalled, its source, confidence, scope, and why it was disclosed.
02 / PUBLIC TEST SEQUENCE
01Begin
Establish a task and a small set of observable continuity criteria.
02Switch
Replace the model or interface without coaching the replacement.
03Resume
Measure whether authorized context and unfinished work remain usable.
04Challenge
Introduce incorrect or unauthorized context and observe the response.
05Inspect
Publish a human-readable result and evidence state.