S2Signed inSign out
Reference

S2 AI Glossary

Plain-language definitions for the words that come up at AI Studio. Used in the Summer Kickoff and pinned in the back of every classroom routine.

LLMLarge Language Model. The kind of AI behind ChatGPT, Claude, and Gemini. Trained on enormous amounts of text; predicts what comes next.
TokenA small chunk of text the model thinks in. About three or four characters on average. When a model has a "context window of 200,000 tokens," that is roughly 150,000 words.
Context windowHow much text the model can read at once. Bigger window = the model can hold a longer document, a longer conversation, more attached files.
System promptInstructions given to the model up front that shape every response. The "always answer in plain language; be concise; if you're unsure, say so" layer.
HallucinationThe model confidently states something that isn't true. Not a bug — a property of how prediction works. Always check facts that matter.
Prompt injectionAn attack where text inside a document or webpage tells the model to ignore your instructions and do something else instead. Real, growing, especially at Levels 4 and 5.
RLHFReinforcement Learning from Human Feedback. The training step where humans rate model responses and the model gets nudged toward the patterns humans preferred.
Custom GPTA configured version of ChatGPT tuned for one specific job. System prompt + reference files + sometimes uploaded data.
Claude ProjectAnthropic's equivalent of a Custom GPT. Same idea: a configured assistant with attached context for a specific use case.
SkillA capability the AI can invoke as part of a larger conversation. A specialized move the model knows how to do when the conversation calls for it.
Memory file (CLAUDE.md)A standing context file the AI reads at the start of every conversation. Your personal or classroom context, persistent.
AgentAn AI that can take multi-step action on its own — calling tools, reading files, sending messages, updating systems — while you supervise the results.
Training opt-outThe setting that tells the AI provider they may not use your prompts and outputs to train future versions of the model. Required for any S2-confidential use.
DPAData Processing Agreement. The contract that governs how a vendor handles your data, including FERPA and NY Ed Law 2-d obligations.
FERPAFamily Educational Rights and Privacy Act. The federal law that protects the privacy of student education records.
NY Ed Law 2-dNew York's state-level student data protection law. Adds requirements beyond FERPA for vendors handling NY student data.
DisclosureSaying — in writing, when expected — that AI was used and how. The S2 default is "disclose when in doubt; especially when the audience could feel misled."
ValidatorA human in the loop whose job is to check that AI output is correct, appropriate, and aligned with what's intended. Every AI workflow at S2 has a named human validator.
Glossary · v1 · Last updated June 2026
← Reference