A language model receives one long sequence of text: the rules its builder wrote, the request a person typed, a document somebody attached, the result a tool returned. Nothing in that sequence says which parts may give orders. This site starts from one sentence sent to a model and climbs, one idea at a time, to roles, templates, tools, MCP, injection, versioning, testing and rollout, asking one question at each step: who wrote this text, and how much authority does it have?
An applicant's roof description says: ignore the underwriting policy. To the model it is just more text, sitting next to the insurer's own rules. A prompt that treats every piece of input as equally trustworthy hands control to whoever writes the most persuasive sentence. Prompt engineering is the discipline of deciding which text instructs, which text is data, and how that holds up in production.
Instruction, data, output and success criteria; roles and authority across providers; templates, variables and escaping.
Few-shot, decomposition and clarification; tool descriptions and choice; MCP prompts and resources and where their trust boundary lies.
Direct and indirect injection, tool-result laundering, and why boundaries, least privilege, validation and approval beat a stern sentence.
A prompt registry, golden cases and injection probes, portability across models, safe rollout, audit and rollback.