Automation Bias

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Constraining model outputs into a schema used to call external APIs/tools safely and deterministically.

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

System design where humans validate or guide model outputs, especially for high-stakes decisions.