Agentic AI
Planning, memory, tool use, and multi-agent orchestration patterns
Reasoning And Planning
- Agentic AI
Agent Architectures
An agent architecture is the loop that turns a goal into actions: see the world, think with memory, act with tools, then read the result and repeat.
- Agentic AI
Planning in Agents: Goals to Steps
A goal is not a plan. Planning in agents turns one distant goal into ordered steps with checks, works them top to bottom, and replans the rest when a step fails.
- Agentic AI
Tool Use Agents
A tool-use agent turns words into checked actions: the model names a function and its arguments, real code runs it, and the result comes back as context.
- Agentic AI
ReAct Framework Agents Think and Act
A model that only reasons guesses from memory, and a model that only acts flails with tools. ReAct framework agents alternate a written Thought, one tool Action, and a harness-written Observation until the answer is grounded.
- Agentic AI
Chain of Thought Agents
Let the agent write its plan in words before it touches a tool. Those written steps are what turn guessing into checking.
- Agentic AI
Self Reflection Agents
A self-reflection agent reads its own draft like a reviewer, names what is wrong, and rewrites once before the answer ships.
- Agentic AI
Agentic Workflow Evaluation
A correct final answer can hide a wasteful, lucky path. Score the steps the agent took, not just the file it handed back.
- Agentic AI
Task Decomposition
Task decomposition turns one vague goal into a small ordered plan: parallel searches first, then the summary that needs them, with room for one replan.
- Agentic AI
Long-Horizon Planning for AI Agents
A reactive agent picks the best next step and walks into dead ends. Long-horizon planning writes milestones first, checkpoints each one, and replans the rest when a check fails.
- Agentic AI
Retrieval Augmented Agents
A retrieval-augmented agent looks things up before it answers: it searches its sources, keeps only the passages that pass a check, and writes from those.
- Agentic AI
Agent Benchmarks
An agent benchmark drops a model into a sandboxed task with tools, then grades the final state, so planning and recovery count instead of just the answer.
Memory
- Agentic AI
Agent Memory Systems That Persist State
Model calls forget everything between sessions. Agent memory systems file distilled facts outside the window and pull back only the top match for the task at hand.
- Agentic AI
Agent Memory Types
Agent memory types split what an agent knows into working context for right now, episodic recall of past runs, and semantic facts, then assemble only what fits.
Multi Agent Systems
- Agentic AI
Multi-Agent Orchestration Patterns
One agent doing everything fills its window and mixes jobs. Multi-agent orchestration splits the work across specialists in parallel, then one supervisor merges results and breaks ties.
- Agentic AI
Agent Communication Protocols
A communication protocol is the envelope every agent message travels in: who sent it, what kind it is, and where the task stands, checked before anyone acts.
- Agentic AI
Supervisor Subagent Patterns
One manager agent decides who works next and checks each result. Workers never talk to each other, so every step stays easy to trace.
- Agentic AI
Agent Sandboxing Ethics
Sandboxing ethics means an agent works in a disposable machine that sees almost nothing, and anything irreversible waits for a human before it touches the world.
- Agentic AI
Emergent Agent Behavior
Give three narrow agents a shared board and a turn order. The fix they reach together is one none of them was taught alone.
Agents
- Agentic AI
Code Execution Agents
Guessing math in words fails. Write a short script, run it apart from the chat, and read back the exact result.
- Agentic AI
Human-in-the-Loop Agents
Let the agent run alone for the safe parts and freeze before the risky call. A person reads the plan, then approves, denies, or fixes it.