universalnaturalintelligence.com

Return the two labs (Precision, Echo), their observation models, and their production URLs.

Return all six mazes with ASCII art, size, and a short description.

Explain γ_A / γ_B / T at a given value, in behavioural terms.

Simulate an active-inference episode server-side and return the full trajectory (positions, beliefs, policy posterior, EFE breakdown per step).

Run multiple episodes varying a single dial; return one summary row per value (reached goal?

Run the same maze at the same dials in both Precision and Echo labs, return both trajectories plus a diff summary.

Return the four patient archetypes (Acute, Chronic, Anxiety, Resilient) with their parameter presets and the story shown in the reading panel.

Simulate one trauma_loop episode under a named treatment protocol (wait, pure_exposure, pure_grounding, sequenced) or a custom protocol object.

Run multiple Loop Lab protocols against a single patient archetype with a fixed seed, return per-protocol outcomes plus a narrative diff summary.

Sweep a 2D parameter grid for a given archetype, running 8-16 seeded trajectories per cell.

Re-run the given (archetype, protocol_id) pair and return a natural-language explanation keyed to the Five Phenomena (The Trap, Exposure Without Grounding, Grounding First, etc.).

Validate that a `pair-XXXX` code shown on the user's open lab tab is alive.

Acknowledgement that you have stopped tracking this session.

Set γ_A, γ_B, or T on the user's open lab tab.

Load one of the six mazes into the lab the user is watching.

Set policy depth to 2 or 3 on the open lab.

Switch between deterministic argmax and stochastic sampling on the open lab.

Advance the agent n steps on the open lab.

Turn the lab's auto-step loop on or off, with an interval in ms.

Restart the agent at the start tile on the open lab.

Return the latest APP snapshot the open lab pushed: position, dial values, current maze, step count, belief entropy.