Artificial Intelligence cards
Prompting changes the instructions at inference time, while fine-tuning changes model weights using additional training data.
Fine-tuning vs prompting
Function calling constrains the model to a structured action request, while free-form text leaves the output unconstrained.
Function calling vs free-form text output
RAG retrieves relevant external context and supplies it to the model at generation time.
RAG basics
Short-term memory is the active conversation context, while long-term memory is persisted information reused across sessions or tasks.
Short-term memory vs long-term memory in agents
Single-agent systems are simpler to control, while multi-agent systems split work across specialized roles at the cost of more orchestration overhead.
Single-agent vs multi-agent design
Evals are repeatable tests that measure whether a model or prompt setup performs well on the behaviors you care about.
What are AI evals?
Embeddings map text or other objects into dense vectors where similar meaning lands nearby.
What are embeddings?
Guardrails are checks and controls around the model that reduce unsafe, low-quality, or out-of-policy behavior.
What are guardrails in AI applications?
Structured outputs force the model response into a known schema such as JSON fields or typed arguments.
What are structured outputs in AI systems?
Tokens are the chunks of text a model processes, and they drive both context window limits and usage cost.
What are tokens in LLM systems?