Diagram
Reference diagram showing how file-based AI work can move from upload to extraction, splitting, retrieval, active context, answer generation, and verification checks.
AI Workflow Diagrams: Architecture, Context, and Security
Browse technical diagrams for AI workflow architecture, prompt assembly, trust boundaries, file review, tool access, and attack surfaces.
Find the AI system boundary you need to inspect
Browse visual reference models for file processing, request assembly, model context, provenance, authorization, connector routing, web-tool access, and prompt-injection risk.
Request assembly & context selection
Open the diagram page for the full image, caption, text alternative, and related technical notes.
Diagram
Summary schematic of the request-assembly boundary highlighting common failure modes: instruction injection, precedence confusion, truncation, provenance loss, and memory poisoning.
Diagram
Reference diagram showing two common failures: chat-derived context influencing effective privileges, and model output persistence/replay into later context; highlights the server-side AuthZ + authoritative state invariant.
Diagram
Request assembly/context selection schematic with annotated risk points across tools, memory, retrieval/caching, and observability.
Diagram
Reference model of provenance boundary failure in prompt assembly: authority confusion and cross-turn drift.
Connectors & tool routing
Open the diagram page for the full image, caption, text alternative, and related technical notes.
Diagram
Reference schematic of prompt-injection risk in web tool access: routing manipulation and downstream failure modes (content-based instructions, source poisoning, query leakage, unbounded consumption, improper output handling).
Diagram
Schematic comparing basic-mode hinting vs connector/agent-mode routing to external services, with control/risk callouts.