AI & ML Tech Glossary
Clear definitions of 500+ AI, ML, and systems terms, built for professionals.
T
Token Budget
A token budget caps how many tokens an LLM app can use across prompt, retrieved context, and output. It’s a key control for cost and...
Tool Credential Vault
A tool credential vault securely stores and rotates API keys and tokens for tool-enabled LLM apps so secrets never enter prompts. The agent plans tool...
Tree of Thoughts (ToT)
Tree of Thoughts (ToT) is a prompting and search strategy where an LLM explores multiple intermediate reasoning branches, scores them, and expands the best paths...
Temperature (LLM Sampling Temperature)
Temperature is a decoding setting for LLMs that controls randomness during token sampling. Lower temperatures make outputs more deterministic and consistent, while higher temperatures increase...
Top-p Sampling (Nucleus Sampling)
Top-p sampling, or nucleus sampling, generates text by sampling the next token only from the smallest set of tokens whose cumulative probability exceeds p. It...
Tool Use Policy
A tool use policy defines rules for when an AI agent can call external tools, which tools are allowed, what data can be sent, and...
Toolformer
HotToolformer refers to training approaches where an LLM learns to call external tools (APIs, search, calculators) by inserting tool calls into text and learning when/why...
