𝗧𝗵𝗲 𝗟𝗟𝗠 𝗧𝗼𝗼𝗹𝗯𝗼𝘅 𝗬𝗼𝘂 𝗦𝗵𝗼𝘂𝗹𝗱 𝗞𝗻𝗼𝘄

The AI ecosystem is growing fast, and it can be confusing to understand where each tool actually fits.

Here’s a simple breakdown:

𝗟𝗟𝗠 𝗣𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀
The models powering AI applications.
→ OpenAI, Claude, Gemini, Llama, Mistral, Grok, DeepSeek

𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀
Build AI agents that can reason, plan, use tools, and complete tasks.
→ LangGraph, CrewAI, AutoGen, AutoGPT, CAMEL-AI

𝗟𝗟𝗠 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀
Connect models with data, tools, memory, and application logic.
→ LangChain, LlamaIndex, Haystack, DSPy, Guardrails AI

𝗣𝗿𝗼𝗺𝗽𝘁 & 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗧𝗼𝗼𝗹𝘀
Create, manage, test, monitor, and improve prompts.
→ Langfuse, PromptLayer, ChainForge, PromptPerfect

𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀
Store embeddings and power semantic search and RAG systems.
→ Pinecone, Qdrant, ChromaDB, FAISS, Weaviate, Milvus

𝗟𝗼𝘄-𝗖𝗼𝗱𝗲 / 𝗡𝗼-𝗖𝗼𝗱𝗲 𝗔𝗜 𝗕𝘂𝗶𝗹𝗱𝗲𝗿𝘀
Build AI workflows and applications with minimal coding.
→ n8n, Flowise, Langflow, Replit, Lovable, v0, Chatbase

𝗛𝗼𝘄 𝗗𝗼 𝗧𝗵𝗲𝘀𝗲 𝗣𝗶𝗲𝗰𝗲𝘀 𝗙𝗶𝘁 𝗧𝗼𝗴𝗲𝘁𝗵𝗲𝗿?

Think of an AI application like this:

𝗠𝗼𝗱𝗲𝗹 → 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 → 𝗗𝗮𝘁𝗮/𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗕 → 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 → 𝗔𝗴𝗲𝗻𝘁𝘀 → 𝗙𝗶𝗻𝗮𝗹 𝗔𝗽𝗽

Example:

𝗖𝗹𝗮𝘂𝗱𝗲/𝗢𝗽𝗲𝗻𝗔𝗜 → 𝗟𝗮𝗻𝗴𝗖𝗵𝗮𝗶𝗻 → 𝗤𝗱𝗿𝗮𝗻𝘁 → 𝗟𝗮𝗻𝗴𝗳𝘂𝘀𝗲 → 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 → 𝗔𝗜 𝗔𝗽𝗽

You don’t need to learn every tool.

The important part is understanding what problem each category solves and when to use it.

Credit: Artificial intelligence