- 1 How Agents Manage Other Agents: Four Subagents Patterns in 2026 ↗
- 2 How to use Deep Research with the Gemini API ↗
- 3 How to correctly use MCP servers with your AI Agents ↗
- 4 8 Tips for Writing Agent Skills ↗
- 5 How to use Gemma 4 with the Gemini API and Google AI Studio ↗
- 6 How Kimi, Cursor, and Chroma Train Agentic Models with RL ↗
- 7 Combine Built-in Tools and Function Calling in the Gemini Interactions API ↗
- 8 Developer Guide: Nano Banana 2 with the Gemini Interactions API ↗
- 9 How Autoresearch will change Small Language Models adoption ↗
- 10 Practical Guide to Evaluating and Testing Agent Skills ↗
- 11 Writing a Good AGENTS.md ↗
- 12 Agents: Inner Loop vs Outer Loop ↗
- 13 Can We Close the Loop in 2026? ↗
- 14 Multimodal Function Calling with Gemini 3 and Interactions API ↗
- 15 Getting Started with Gemini Deep Research API ↗
- 16 The Agent Client Protocol Overview ↗
- 17 Gemini Interactions API Quick Start ↗
- 18 MCP is Not the Problem, It's your Server: Best Practices for Building MCP Servers ↗
- 19 Transparent PNG Stickers with Nano Banana Pro and Gemini interactions API ↗
- 20 Building Agents with the Gemini Interactions API ↗
- 21 Introducing MCP CLI: A way to call MCP Servers Efficiently ↗
- 22 The importance of Agent Harness in 2026 ↗
- 23 8 Predictions for 2026. What comes next in AI? ↗
- 24 Context Engineering for AI Agents: Part 2 ↗
- 25 Why (Senior) Engineers Struggle to Build AI Agents ↗
- 26 Practical Guide on how to build an Agent from scratch with Gemini 3 ↗
- 27 Gemini 3 Prompting: Best Practices for General Usage ↗
- 28 Gemini API File Search: A Web Developer Tutorial ↗
- 29 Build your first AI Agent with Gemini, n8n and Google Cloud Run ↗
- 30 AI Agent Benchmark Compendium ↗
- 31 Agents 2.0: From Shallow Loops to Deep Agents ↗
- 32 The Rise of Subagents ↗
- 33 The 10 Steps for product AI generation with Gemini 2.5 Flash ↗
- 34 Memory in Agents, Make LLMs remember. ↗
- 35 Google Gemini CLI Cheatsheet ↗
- 36 Code Sandbox MCP: A Simple Code Interpreter for Your AI Agents ↗
- 37 Integrating Long-Term Memory with Gemini 2.5 ↗
- 38 The New Skill in AI is Not Prompting, It's Context Engineering ↗
- 39 Single vs Multi-Agent System? ↗
- 40 Zero to One: Learning Agentic Patterns ↗
- 41 Google Gemini LangChain Cheatsheet ↗
- 42 OpenAI Codex CLI, how does it work? ↗
- 43 Model Context Protocol (MCP) an overview ↗
- 44 ReAct agent from scratch with Gemini 2.5 and LangGraph ↗
- 45 Pass@k vs Pass^k: Understanding Agent Reliability ↗
- 46 Google Gemma 3 Function Calling Example ↗
- 47 Function Calling Guide: Google DeepMind Gemini 2.0 Flash ↗
- 48 From PDFs to Insights: Structured Outputs from PDFs with Gemini 2.0 ↗
- 49 Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial ↗
- 50 How to align open LLMs in 2025 with DPO and and synthetic data ↗
- 51 How to use Anthropic MCP Server with open LLMs, OpenAI or Google Gemini ↗
- 52 Bite: How Deepseek R1 was trained ↗
- 53 Fine-tune classifier with ModernBERT in 2025 ↗
- 54 How to fine-tune open LLMs in 2025 with Hugging Face ↗
- 55 Deploy QwQ-32B-Preview the best open Reasoning Model on AWS with Hugging Face ↗
- 56 Deploy Llama 3.2 Vision on Amazon SageMaker ↗
- 57 How to Fine-Tune Multimodal Models or VLMs with Hugging Face TRL ↗
- 58 Evaluate open LLMs with Vertex AI and Gemini ↗
- 59 Evaluate LLMs using Evaluation Harness and Hugging Face TGI/vLLM ↗
- 60 Deploy open LLMs with Terraform and Amazon SageMaker ↗
- 61 LLM Evaluation doesn't need to be complicated ↗
- 62 Evaluating Open LLMs with MixEval: The Closest Benchmark to LMSYS Chatbot Arena ↗
- 63 Train and Deploy open Embedding Models on Amazon SageMaker ↗
- 64 Deploy Mixtral 8x7B on AWS Inferentia2 with Hugging Face Optimum ↗
- 65 Fine-tune Llama 3 with PyTorch FSDP and Q-Lora on Amazon SageMaker ↗
- 66 Fine-tune Embedding models for Retrieval Augmented Generation (RAG) ↗
- 67 Understanding the Cost of Generative AI Models in Production ↗
- 68 Deploy Llama 3 70B on AWS Inferentia2 with Hugging Face Optimum ↗
- 69 Deploy open LLMs with vLLM on Hugging Face Inference Endpoints ↗
- 70 Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora ↗
- 71 Deploy Llama 3 on Amazon SageMaker ↗
- 72 Accelerate Mixtral 8x7B with Speculative Decoding and Quantization on Amazon SageMaker ↗
- 73 Deploy Llama 2 70B on AWS Inferentia2 with Hugging Face Optimum ↗
- 74 Fine-Tune and Evaluate LLMs in 2024 with Amazon SageMaker ↗
- 75 Evaluate LLMs with Hugging Face Lighteval on Amazon SageMaker ↗
- 76 How to fine-tune Google Gemma with ChatML and Hugging Face TRL ↗
- 77 How to Fine-Tune LLMs in 2024 with Hugging Face ↗
- 78 RLHF in 2024 with DPO and Hugging Face ↗
- 79 Scale LLM Inference on Amazon SageMaker with Multi-Replica Endpoints ↗
- 80 Fine-tune Llama 7B on AWS Trainium ↗
- 81 Programmatically manage 🤗 Inference Endpoints ↗
- 82 Deploy Mixtral 8x7B on Amazon SageMaker ↗
- 83 Deploy Embedding Models on AWS inferentia2 with Amazon SageMaker ↗
- 84 Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker ↗
- 85 Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker ↗
- 86 Amazon Bedrock: How good (bad) is Titan Embeddings? ↗
- 87 Evaluate LLMs and RAG a practical example using Langchain and Hugging Face ↗
- 88 Deploy Idefics 9B and 80B on Amazon SageMaker ↗
- 89 Train and Deploy Mistral 7B with Hugging Face on Amazon SageMaker ↗
- 90 Llama 2 on Amazon SageMaker a Benchmark ↗
- 91 Fine-tune Falcon 180B with DeepSpeed ZeRO, LoRA and Flash Attention ↗
- 92 Fine-tune Falcon 180B with QLoRA and Flash Attention on Amazon SageMaker ↗
- 93 Deploy Falcon 180B on Amazon SageMaker ↗
- 94 Optimize open LLMs using GPTQ and Hugging Face Optimum ↗
- 95 LLMOps: Deploy Open LLMs using Infrastructure as Code with AWS CDK ↗
- 96 Deploy Llama 2 7B/13B/70B on Amazon SageMaker ↗
- 97 Introducing EasyLLM - streamline open LLMs ↗
- 98 Extended Guide: Instruction-tune Llama 2 ↗
- 99 LLaMA 2 - Every Resource you need ↗
- 100 Fine-tune LLaMA 2 (7-70B) on Amazon SageMaker ↗