Agents
When LLMs become decision-makers in a loop.
Agentic systems use an LLM to decide which actions to take, observe their results, and continue. The concepts below cover the building blocks — tool use, function calling, planning, trajectory pruning — and the operational patterns that make agent loops reliable enough to ship. Specialized small models increasingly handle the narrow tasks inside agents (tool selection, argument extraction, sub-task decomposition) while the LLM does the open-ended reasoning.
- Agent
An agent is an LLM placed in a perception/decision/action loop — it reads context, picks an action (often a tool call), observes the result, and iterates until the goal is met.
- Agent Guardrails
Agent guardrails are the input/output filters, tool-call validators, and allow-lists that bound what an agent can do and say. Defense-in-depth: layered checks at the prompt boundary, the tool boundary.
- Agent Loop
The agent loop is the execution scaffold that wraps an LLM into an agent: perceive → think → act → observe → repeat. It's the trajectory primitive.
- Agent Memory
Agent memory is how an agent persists information across turns and sessions. Short-term memory lives in the context window; long-term memory lives in an external store (vector DB, structured records, files).
- Agent Orchestration
Agent orchestration is the routing layer that decides which agent or model handles each step. The dominant patterns are workflow orchestration (a deterministic graph of agents) and autonomous orchestration (a supervisor delegating to sub-agents).
- Agentic RAG
Agentic RAG is RAG where the model decides what to retrieve, reformulates queries, and iterates — instead of a single pre-baked query going to the index.
- Function Calling
Function calling is the structured-API mechanism that providers (OpenAI, Anthropic, Google) expose for tool use: you give the model a JSON schema describing each function, and the model responds with a typed call request the runtime can execute.
- MCP (Model Context Protocol)
MCP is Anthropic's open standard for connecting LLMs to tools and data sources. An MCP server exposes a catalog of tools, resources, and prompts; any MCP-aware client can use them.
- Multi-Agent Systems
Multi-agent systems use multiple specialized agents — different roles, tools, or models — coordinating to solve a task. Patterns range from a coordinator dispatching to specialists to debate setups where agents argue toward a better answer.
- Planning and Decomposition
Planning and decomposition is the agent pattern of breaking a complex goal into ordered sub-tasks and executing them, instead of trying to one-shot the whole thing.
- Reflection and Critique
Reflection is the agent self-evaluation pattern: produce an answer, evaluate it against the goal or known criteria, refine if needed. It catches errors that one-shot generation misses, at the cost of extra tokens and latency.
- Tool Use
Tool use is the pattern where an LLM emits a structured request to call an external function — a search API, a code runner, a database query — and the runtime executes it and returns the result.
- Foundations 48
The bedrock primitives every other topic builds on.
- Data 18
The corpora, curation, and quality decisions that make models possible.
- Language Models 32
The foundational substrate of modern AI.
- Multimodal 13
When text isn't the only signal — vision, audio, and joint embedding spaces.
- Prompting 16
How you talk to an LLM, and when you stop.
- Search & Retrieval 21
How systems find relevant documents in the first place.
- Embeddings 16
The dense-vector layer of modern retrieval.
- Rerankers 9
The second stage that puts the right answer at the top.
- Evaluation 21
How to measure retrieval quality and trust the numbers.
- Training Methodology 21
How modern retrieval models get their relevance signal.
- Performance Engineering 25
Squeezing throughput, latency, and memory out of GPUs.
- Production 16
From notebook to live traffic.
