The model proposes. Aurora-Lens decides what may proceed.
Aurora-Lens separates generation from authority. Candidate output is checked at the execution boundary before it becomes visible, actionable, or consequential.
Three layers. Three jobs.
The system stays legible because the jobs do not collapse into one another.
Lens determines whether candidate output may pass from model generation into consequence.
When output cannot pass, the Governor decides what may happen next: clarify, refuse, stop, or escalate.
Every governed turn leaves a replayable record of what happened, what was shown, and why.
From candidate output to controlled outcome.
This is the boundary where ordinary AI output becomes governed output.
Input enters the system
The user request is received with its session context, domain signals, authority constraints, and any relevant persistent state.
The model proposes candidate output
The LLM may generate a response, but that response is not automatically released. Generation is proposal, not permission.
Lens checks admissibility
Lens evaluates whether the candidate output is allowed to pass in this context. It checks the output against domain, authority, ambiguity, contradiction, and discourse state.
The Governor controls continuation
If the candidate cannot pass, the Governor does not appeal Lens or soften the blocked output. It determines the lawful continuation corridor.
The audit layer records the event
The governed outcome is recorded so the decision can be inspected, replayed, and defended later.
Non-answer is not failure.
In a governed system, refusal, clarification, and stop are legitimate decisions.
The candidate is admissible and may become visible to the user.
The system lacks enough structure to proceed without guessing.
The requested determination is outside the system’s authority or policy corridor.
The interaction cannot lawfully continue in its current form.
The domain requires a qualified human, reviewer, clinician, adviser, or institutional process.
The system preserves evidence of the decision path and governed output.
The boundary is enforced before release.
Ordinary guardrails try to shape model behaviour. Aurora-Lens governs the release boundary.
That distinction matters because the model is not the final authority. A fluent answer can still be inadmissible. A plausible answer can still exceed role, domain, context, or authority. A confident answer can still need to be stopped.
Aurora-Lens keeps the decisive question outside the model’s temperament: may this output proceed?
Decisions happen before output reaches the user.
Admissibility is governed by explicit rules, not vibes.
Outputs are checked against context and persistent discourse state.
Every governed turn can be inspected after the fact.
See the boundary in motion.
The fastest way to understand Aurora-Lens is to watch it allow, contain, refuse, and stop.