Agentic Blueprints 23
Filtersactive
AG2 Adaptive Research Team
An AG2 research team with sequential handoffs plus routing and fallback — the flow adapts when a step comes back weak.
Domain Deep Research Agent
A deep-research app that decomposes a domain question, researches the pieces, and synthesizes a cited report.
Company Research Team
A research team combines web search with live financial data to produce a company analysis: business, stock history, and outlook.
Multi-Agent Researcher
A compact research team — searcher, analyst, writer — that turns a question into a structured research write-up.
LATS (Language Agent Tree Search)
Monte-Carlo tree search over agent actions: generate candidates, reflect and score them, expand the best branches until one solves the task.
Agents SDK Research Bot
OpenAI's Agents SDK research flow: a planner derives searches, they run in parallel, and a writer synthesizes the report.
Financial Research Agent
Six agents produce a verified financial research note: planner, searcher, fundamentals and risk analysts as tools, writer, then a verifier.
Literature Review Team
Search agents pull papers from the web and arXiv, an analyst reads them, and a reporter writes the literature review round-robin.
AI Real Estate Agent Team
A property-search team: agents gather listings, analyze fit against the buyer's criteria, and assemble a recommendation report.
Stock Analysis Crew
Financial analyst, research analyst, and investment advisor agents dig through SEC filings and news to produce a full stock analysis.
Meeting Prep Crew
Researches the people and companies you're about to meet and compiles a briefing so you walk in knowing who's across the table.
AI Finance Agent Team
A two-agent finance desk: a web-search agent for news and context, a finance agent pulling real market data through YFinance.
Corrective RAG
Grades retrieved documents for relevance and, when they fail the grade, falls back to web search before answering.
Multi-Agent Collaboration
A researcher agent and a chart-generator agent divide a task and route work between themselves until the answer is a finished chart.
Plan-and-Execute (LangGraph tutorial)
The original plan-and-execute notebook: a planner writes the step list, an executor works through it, and a replanner revises as results come in.
Reflexion
An answerer that critiques itself with citations: draft, self-review for missing and superfluous content, search to fill gaps, revise.
Adaptive RAG
Routes each question to the right retrieval strategy, grades what comes back, and falls back to web search when the index can't answer.
Swarm Support Bot
A two-agent support bot: a user-interface agent talks to the customer while a help-center agent answers from docs in a vector store.
Job Posting Crew
Research, writer, and review agents draft a job posting from a company domain and role description, grounded in scraped company culture.
Write a Book Flow
An outline crew plans the book, then per-chapter writer crews produce it — a flow that fans a big deliverable into parallelizable pieces.
Surprise Trip Crew
Plans a surprise trip: one agent picks personalized activities, another scouts restaurants, a third compiles the full itinerary.