Trajectory Observatory: Safety, Narrative, and Prompt Interventions

Public repository of multi-turn chatbot trajectories. This observatory tracks three things: safety handling, narrative amplification, and prompt/scaffold interventions such as CBT-style system prompts.

The point is not whether a single reply looks good. The point is what the conversation becomes by turn 18. Built by Impersonato.

Safety

Crisis detection, resource handoff, boundaries, dependency risk

Narrative

Validation traps, belief amplification, challenge quality

Interventions

Baseline vs CBT scaffold, and future prompt/product comparisons

How to read this repository
  • A good-looking response can still produce a worse trajectory
  • Prompting can redistribute failure rather than remove it
  • These are synthetic personas, used to expose failure without exposing real users
  • Models were tested via standard APIs without custom system prompts unless specified (baseline condition)

Need trajectory testing for your chatbot? Get in touch.

Loading trajectory cases...

Model Comparison

Click a model bar to filter trajectory cases. Click again to deselect.

Repository Snapshot

No trajectory cases available.