Six Principles for Production AI Agents
Practical lessons from building production agentic systems
Agents
Docs for AI agents
Utkarsh Kanwat - AI Engineer
AI Engineer at ANZ Bank working on intelligent systems, LLM optimization, and scalable ML platforms.
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and...
This study critically distinguishes between AI Agents and Agentic AI, offering a structured conceptual taxonomy, application mapping, and challenge analysis to clarify their divergent design...
Enterprise Agentic AI Hierarchy of Needs
The crucial layers of infrastructure that make up a production grade Agentic AI system.
Which agent framework should you use? I tried 7. The winners will surprise you 🤯
I rewrote my "tech writer" agent in 7 frameworks: Agno, Autogen, Google ADK, Atomic Agents, DSPy, Langgraph, and Pydantic AI. You'll NEVER guess the winners.
Lect02 2up
SmolAgents— Grocery Finder
A complete walkthrough for building a code-generating AI agent that recommends grocery items by querying SurrealDB's HNSW vector index.
NirDiamant/agents-towards-production: This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re...
Cognition | Don’t Build Multi-Agents
Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.
Cohere: Building Enterprise AI agents
Evaluation Driven Development for Agentic Systems.
My step-by-step approach for building and evolving Agentic Systems that work.
12 Factor Agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
GitHub - business-science/awesome-generative-ai-data-scientist: A curated list of 100+ resources for building and deploying generative AI specifically focusing on helping you become a Generative AI Data Scientist with LLMs
A curated list of 100+ resources for building and deploying generative AI specifically focusing on helping you become a Generative AI Data Scientist with LLMs - business-science/awesome-generative-...
Zero to One: Learning Agentic Patterns
Learn common agentic design patterns and workflows for building robust, scalable AI applications, understanding when to use each.
gemini-samples/guides/langgraph-react-agent.ipynb at main · philschmid/gemini-samples
Contribute to philschmid/gemini-samples development by creating an account on GitHub.
The LLM Mesh
A Visual Guide to LLM Agents
Explore the main components of what makes LLM Agents special.
An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
Agents interact with their environment and typically consist of several important components
chain-of-thought
This is where planning comes in. Planning in LLM Agents involves breaking a given task up into actionable steps.
reasoning” and “thinking” a bit loosely as we can argue whether this is human-like thinking or merely breaking the answer down to structured steps.
without any examples (zero-shot prompting)
Providing examples (also called few-shot prompting7)
ReAct
Reflecting
These Multi-Agent systems usually consist of specialized Agents, each equipped with their own toolset and overseen by a supervisor.
three LLM roles
SELF-REFINE
To enable planning in LLM Agents, let’s first look at the foundation of this technique, namely reasoning.
Weaviate Agentic Architectures eBook
Agents
Foundation models enable many new application interfaces, but one that has especially grown in popularity is the conversational interface, such as with chatbots and assistants. The conversational interface makes it easier for users to give feedback but harder for developers to extract signals. This post will discuss what conversational AI feedback looks like and how to design a system to collect the right feedback without hurting user experience.
Building effective agents \ Anthropic
A post for developers with advice and workflows for building effective AI agents
AI Agent In Production - Insights from the market
Explore the capabilities of AI Agents and their real-world applications. CrewAI showcases the power and versatility of AI technologies across various sectors.
A Multi-Agent Framework for Synthetic Data Generation
Presents MAG-V, a multi-agent framework that first generates a dataset of questions that mimic customer queries. It then reverse engineer alternate questions from responses to verify agent trajectories.
Reports that the…
— elvis (@omarsar0)
Agentless is a great example of how a more constrained agent is better than a general agent for specific tasks 💡 - it achieves much higher scores on SWE-Bench Lite for bug-fixing than other agent approaches 🛠️
The whole point is to not let the agent do everything, but to do a…
— Jerry Liu (@jerryjliu0)
(12) Pedro Domingos on X: "Calling an LLM an agent doesn’t suddenly make it more intelligent." / X
— Pedro Domingos (@pmddomingos)
Multi-Agent Orchestrator framework
Manage multiple AI agents and handle complex conversations
NirDiamant/GenAI_Agents: This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.
This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive A...
I've been building agents for almost 1.5 years and can confidently 99% of the "ai browsing" demos are useless.
the reality is consumers won't have millions of AI agents working 24/7 for them, bargaining and shopping to save $20. there will just be an ai shopping app.
compute…
— Sully (@SullyOmarr)
openai/swarm: Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team. - openai/swarm
Orchestrating Agents: Routines and Handoffs | OpenAI Cookbook
Open-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.