41554 blogs · [ { "id": "01a0da74-49fa-728d-a680-ac48e12d92f5", "title": "Create your own voice for Gemini 3.8 TTS", "url": "https://www.philschmid.de/gemini-3-8-tts", "published_at": "2026-09-24T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74afab46ec", "title": "How Foundational Models Became Superhuman in Bash", "url": "https://www.philschmid.de/superhuman-bash", "published_at": "2026-09-01T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b05514a5", "title": "Setup OpenClaw 2.0 with Gemini in Under 60 Seconds", "url": "https://www.philschmid.de/openclaw-v2-gemini", "published_at": "2026-08-31T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b13f946e", "title": "Recursive Self-Improvement", "url": "https://www.philschmid.de/recursive-self-improvement", "published_at": "2026-08-21T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b23bba28", "title": "Controlling Android with Gemini 3.7 Flash and 150 lines of Python", "url": "https://www.philschmid.de/gemini-android-computer-use", "published_at": "2026-08-17T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b29dca11", "title": "Google Maps and Google Search now work together in the Gemini API", "url": "https://www.philschmid.de/gemini-search-maps", "published_at": "2026-08-12T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b2cf3517", "title": "Evaluating Agents Beyond the First Prompt", "url": "https://www.philschmid.de/evocode-bench", "published_at": "2026-07-27T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b353f9ec", "title": "Building Managed Agents That Use GitHub Without Exposing Your Token", "url": "https://www.philschmid.de/managed-agents-gh", "published_at": "2026-07-17T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b3d27ab1", "title": "Control an Android Phone with Gemini 3.5 Flash Computer Use", "url": "https://www.philschmid.de/gemini-android-use", "published_at": "2026-06-25T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b4534fef", "title": "Getting started with the Gemini Interactions API", "url": "https://www.philschmid.de/interactions-api-developer-guide", "published_at": "2026-06-23T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b4cbda5c", "title": "How Gemini Managed Agents Works under the Hood", "url": "https://www.philschmid.de/how-managed-agents-work", "published_at": "2026-06-10T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b556e36e", "title": "Gemini Managed Agents: Developer Guide", "url": "https://www.philschmid.de/gemini-managed-agents-developer-guide", "published_at": "2026-05-26T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b5d1de9e", "title": "How Agents Manage Other Agents: Four Subagents Patterns in 2026", "url": "https://www.philschmid.de/subagent-patterns-2026", "published_at": "2026-05-05T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b6ac6fb1", "title": "How to use Deep Research with the Gemini API", "url": "https://www.philschmid.de/deep-research-update", "published_at": "2026-04-29T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b737a57f", "title": "How to correctly use MCP servers with your AI Agents", "url": "https://www.philschmid.de/use-mcp-servers", "published_at": "2026-04-27T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b769d00a", "title": "8 Tips for Writing Agent Skills", "url": "https://www.philschmid.de/agent-skills-tips", "published_at": "2026-04-13T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b79b61aa", "title": "How to use Gemma 4 with the Gemini API and Google AI Studio", "url": "https://www.philschmid.de/gemma-4-gemini-api", "published_at": "2026-04-07T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b86747fc", "title": "How Kimi, Cursor, and Chroma Train Agentic Models with RL", "url": "https://www.philschmid.de/kimi-composer-context", "published_at": "2026-03-28T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b8bdf701", "title": "Combine Built-in Tools and Function Calling in the Gemini Interactions API", "url": "https://www.philschmid.de/tool-combo", "published_at": "2026-03-24T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b8c12dd0", "title": "Developer Guide: Nano Banana 2 with the Gemini Interactions API", "url": "https://www.philschmid.de/nano-banana-2-interactions-api", "published_at": "2026-03-16T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b9097870", "title": "How Autoresearch will change Small Language Models adoption", "url": "https://www.philschmid.de/autoresearch", "published_at": "2026-03-10T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b940d941", "title": "Practical Guide to Evaluating and Testing Agent Skills", "url": "https://www.philschmid.de/testing-skills", "published_at": "2026-03-04T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74b9dbd0e1", "title": "Writing a Good AGENTS.md", "url": "https://www.philschmid.de/writing-good-agents", "published_at": "2026-02-24T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bac9fea5", "title": "Agents: Inner Loop vs Outer Loop", "url": "https://www.philschmid.de/inner-loop-vs-outer-loop", "published_at": "2026-02-20T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bb623412", "title": "Can We Close the Loop in 2026?", "url": "https://www.philschmid.de/closing-the-loop", "published_at": "2026-02-17T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bc298585", "title": "Multimodal Function Calling with Gemini 3 and Interactions API", "url": "https://www.philschmid.de/interactions-multimodal-fc", "published_at": "2026-02-13T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bc6be03c", "title": "Getting Started with Gemini Deep Research API", "url": "https://www.philschmid.de/gemini-deep-research-getting-started", "published_at": "2026-02-02T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bc7750d7", "title": "The Agent Client Protocol Overview", "url": "https://www.philschmid.de/acp-overview", "published_at": "2026-02-01T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bca86eb8", "title": "Gemini Interactions API Quick Start", "url": "https://www.philschmid.de/interactions-api-quickstart", "published_at": "2026-01-22T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bcc55a09", "title": "MCP is Not the Problem, It's your Server: Best Practices for Building MCP Servers", "url": "https://www.philschmid.de/mcp-best-practices", "published_at": "2026-01-21T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bcca15fe", "title": "Transparent PNG Stickers with Nano Banana Pro and Gemini interactions API", "url": "https://www.philschmid.de/generate-stickers", "published_at": "2026-01-19T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bd7e46ea", "title": "Building Agents with the Gemini Interactions API", "url": "https://www.philschmid.de/building-agents-interactions-api", "published_at": "2026-01-14T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74be424d01", "title": "Introducing MCP CLI: A way to call MCP Servers Efficiently", "url": "https://www.philschmid.de/mcp-cli", "published_at": "2026-01-09T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74be9a9f76", "title": "The importance of Agent Harness in 2026", "url": "https://www.philschmid.de/agent-harness-2026", "published_at": "2026-01-05T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74beeefff8", "title": "8 Predictions for 2026. What comes next in AI?", "url": "https://www.philschmid.de/2026-predictions", "published_at": "2025-12-31T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74bfda7583", "title": "Context Engineering for AI Agents: Part 2", "url": "https://www.philschmid.de/context-engineering-part-2", "published_at": "2025-12-04T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c00ed50e", "title": "Why (Senior) Engineers Struggle to Build AI Agents", "url": "https://www.philschmid.de/why-engineers-struggle-building-agents", "published_at": "2025-11-26T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c09f3b99", "title": "Practical Guide on how to build an Agent from scratch with Gemini 3", "url": "https://www.philschmid.de/building-agents", "published_at": "2025-11-21T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c1366201", "title": "Gemini 3 Prompting: Best Practices for General Usage", "url": "https://www.philschmid.de/gemini-3-prompt-practices", "published_at": "2025-11-19T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c1655393", "title": "Gemini API File Search: A Web Developer Tutorial", "url": "https://www.philschmid.de/gemini-file-search-javascript", "published_at": "2025-11-07T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c22a562a", "title": "Build your first AI Agent with Gemini, n8n and Google Cloud Run", "url": "https://www.philschmid.de/n8n-cloud-run-gemini", "published_at": "2025-10-30T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c2c2a595", "title": "AI Agent Benchmark Compendium", "url": "https://www.philschmid.de/benchmark-compedium", "published_at": "2025-10-15T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c2d5e7c1", "title": "Agents 2.0: From Shallow Loops to Deep Agents", "url": "https://www.philschmid.de/agents-2.0-deep-agents", "published_at": "2025-10-12T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c358e05e", "title": "The Rise of Subagents", "url": "https://www.philschmid.de/the-rise-of-subagents", "published_at": "2025-09-15T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c38050ca", "title": "The 10 Steps for product AI generation with Gemini 2.5 Flash", "url": "https://www.philschmid.de/gemini-image-generation-product", "published_at": "2025-08-27T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c3b32f1c", "title": "Memory in Agents, Make LLMs remember.", "url": "https://www.philschmid.de/memory-in-agents", "published_at": "2025-08-04T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c426bdf0", "title": "Google Gemini CLI Cheatsheet", "url": "https://www.philschmid.de/gemini-cli-cheatsheet", "published_at": "2025-07-24T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c50ca30b", "title": "Code Sandbox MCP: A Simple Code Interpreter for Your AI Agents", "url": "https://www.philschmid.de/code-sandbox-mcp", "published_at": "2025-07-22T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c5b82616", "title": "Integrating Long-Term Memory with Gemini 2.5", "url": "https://www.philschmid.de/gemini-with-memory", "published_at": "2025-07-03T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c681e00c", "title": "The New Skill in AI is Not Prompting, It's Context Engineering", "url": "https://www.philschmid.de/context-engineering", "published_at": "2025-06-30T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c6fa6060", "title": "Single vs Multi-Agent System?", "url": "https://www.philschmid.de/single-vs-multi-agents", "published_at": "2025-06-20T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c70281e1", "title": "Zero to One: Learning Agentic Patterns", "url": "https://www.philschmid.de/agentic-pattern", "published_at": "2025-05-05T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c7df99b1", "title": "Google Gemini LangChain Cheatsheet", "url": "https://www.philschmid.de/gemini-langchain-cheatsheet", "published_at": "2025-04-28T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c8380dfd", "title": "OpenAI Codex CLI, how does it work?", "url": "https://www.philschmid.de/openai-codex-cli", "published_at": "2025-04-17T00:00:00+00:00" }, { "id": "01a087c2-4502-73eb-9450-3d74c90768dc", "title": "Model Context Protocol (MCP) an overview", "url": "https://www.philschmid.de/mcp-introduction", "published_at": "2025-04-03T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f019916ac", "title": "ReAct agent from scratch with Gemini 2.5 and LangGraph", "url": "https://www.philschmid.de/langgraph-gemini-2-5-react-agent", "published_at": "2025-03-31T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0257aaa7", "title": "Pass@k vs Pass^k: Understanding Agent Reliability", "url": "https://www.philschmid.de/agents-pass-at-k-pass-power-k", "published_at": "2025-03-24T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f02b300d2", "title": "Google Gemma 3 Function Calling Example", "url": "https://www.philschmid.de/gemma-function-calling", "published_at": "2025-03-14T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f02dcac18", "title": "Function Calling Guide: Google DeepMind Gemini 2.0 Flash", "url": "https://www.philschmid.de/gemini-function-calling", "published_at": "2025-03-05T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f03cbb9db", "title": "From PDFs to Insights: Structured Outputs from PDFs with Gemini 2.0", "url": "https://www.philschmid.de/gemini-pdf-to-data", "published_at": "2025-02-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f03cf7443", "title": "Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial", "url": "https://www.philschmid.de/mini-deepseek-r1", "published_at": "2025-01-30T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f04c9d6e4", "title": "How to align open LLMs in 2025 with DPO and and synthetic data", "url": "https://www.philschmid.de/rl-with-llms-in-2025-dpo", "published_at": "2025-01-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0550a453", "title": "Bite: How Deepseek R1 was trained", "url": "https://www.philschmid.de/deepseek-r1", "published_at": "2025-01-17T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0644618f", "title": "How to use Anthropic MCP Server with open LLMs, OpenAI or Google Gemini", "url": "https://www.philschmid.de/mcp-example-llama", "published_at": "2025-01-17T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f064a67a3", "title": "Fine-tune classifier with ModernBERT in 2025", "url": "https://www.philschmid.de/fine-tune-modern-bert-in-2025", "published_at": "2024-12-25T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0743e072", "title": "How to fine-tune open LLMs in 2025 with Hugging Face", "url": "https://www.philschmid.de/fine-tune-llms-in-2025", "published_at": "2024-12-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f079e67fd", "title": "Deploy QwQ-32B-Preview the best open Reasoning Model on AWS with Hugging Face", "url": "https://www.philschmid.de/sagemaker-deploy-qwq", "published_at": "2024-12-03T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f07f29387", "title": "Deploy Llama 3.2 Vision on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-llama32-vision", "published_at": "2024-10-17T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f082a6607", "title": "How to Fine-Tune Multimodal Models or VLMs with Hugging Face TRL", "url": "https://www.philschmid.de/fine-tune-multimodal-llms-with-trl", "published_at": "2024-09-30T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f08fff2be", "title": "Evaluate open LLMs with Vertex AI and Gemini", "url": "https://www.philschmid.de/evaluate-llm-with-gemini", "published_at": "2024-09-24T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f094b9b9d", "title": "Evaluate LLMs using Evaluation Harness and Hugging Face TGI/vLLM", "url": "https://www.philschmid.de/evaluate-llms-with-lm-eval-and-tgi-vllm", "published_at": "2024-09-19T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f09c367eb", "title": "Deploy open LLMs with Terraform and Amazon SageMaker", "url": "https://www.philschmid.de/terraform-llm-sagemaker", "published_at": "2024-08-05T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f09c567ea", "title": "LLM Evaluation doesn't need to be complicated", "url": "https://www.philschmid.de/llm-evaluation", "published_at": "2024-07-11T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0a6b8395", "title": "Evaluating Open LLMs with MixEval: The Closest Benchmark to LMSYS Chatbot Arena", "url": "https://www.philschmid.de/evaluate-llm-mixeval", "published_at": "2024-06-28T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0abbfed1", "title": "Train and Deploy open Embedding Models on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-train-deploy-embedding-models", "published_at": "2024-06-25T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0b9972a3", "title": "Deploy Mixtral 8x7B on AWS Inferentia2 with Hugging Face Optimum", "url": "https://www.philschmid.de/inferentia2-mixtral-8x7b", "published_at": "2024-06-18T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0c39ffd3", "title": "Fine-tune Llama 3 with PyTorch FSDP and Q-Lora on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-train-deploy-llama3", "published_at": "2024-06-11T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0c473ba5", "title": "Fine-tune Embedding models for Retrieval Augmented Generation (RAG)", "url": "https://www.philschmid.de/fine-tune-embedding-model-for-rag", "published_at": "2024-06-04T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0c81b9f2", "title": "Understanding the Cost of Generative AI Models in Production", "url": "https://www.philschmid.de/cost-generative-ai", "published_at": "2024-05-27T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0d77e036", "title": "Deploy Llama 3 70B on AWS Inferentia2 with Hugging Face Optimum", "url": "https://www.philschmid.de/inferentia2-llama3-70b", "published_at": "2024-05-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0e23b7ba", "title": "Deploy open LLMs with vLLM on Hugging Face Inference Endpoints", "url": "https://www.philschmid.de/vllm-inference-endpoints", "published_at": "2024-05-02T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0e84cc95", "title": "Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora", "url": "https://www.philschmid.de/fsdp-qlora-llama3", "published_at": "2024-04-22T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0ed8cb66", "title": "Deploy Llama 3 on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-llama3", "published_at": "2024-04-18T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0f65ade4", "title": "Accelerate Mixtral 8x7B with Speculative Decoding and Quantization on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-awq-medusa", "published_at": "2024-04-02T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f0fe0f86a", "title": "Deploy Llama 2 70B on AWS Inferentia2 with Hugging Face Optimum", "url": "https://www.philschmid.de/inferentia2-llama-70b-inference", "published_at": "2024-03-26T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f108a83d8", "title": "Fine-Tune and Evaluate LLMs in 2024 with Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-train-evalaute-llms-2024", "published_at": "2024-03-12T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f10c88975", "title": "Evaluate LLMs with Hugging Face Lighteval on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-evaluate-llm-lighteval", "published_at": "2024-03-05T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f119ffac3", "title": "How to fine-tune Google Gemma with ChatML and Hugging Face TRL", "url": "https://www.philschmid.de/fine-tune-google-gemma", "published_at": "2024-03-01T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1267b544", "title": "RLHF in 2024 with DPO and Hugging Face", "url": "https://www.philschmid.de/dpo-align-llms-in-2024-with-trl", "published_at": "2024-01-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1352cc8d", "title": "How to Fine-Tune LLMs in 2024 with Hugging Face", "url": "https://www.philschmid.de/fine-tune-llms-in-2024-with-trl", "published_at": "2024-01-23T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f13f30edb", "title": "Scale LLM Inference on Amazon SageMaker with Multi-Replica Endpoints", "url": "https://www.philschmid.de/sagemaker-multi-replica", "published_at": "2024-01-11T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f14d01054", "title": "Fine-tune Llama 7B on AWS Trainium", "url": "https://www.philschmid.de/fine-tune-llama-7b-trainium", "published_at": "2023-12-21T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f153c8bef", "title": "Programmatically manage 🤗 Inference Endpoints", "url": "https://www.philschmid.de/inference-endpoints-iac", "published_at": "2023-12-20T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f162dd153", "title": "Deploy Mixtral 8x7B on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-deploy-mixtral", "published_at": "2023-12-12T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f16c1065f", "title": "Deploy Embedding Models on AWS inferentia2 with Amazon SageMaker", "url": "https://www.philschmid.de/inferentia2-embeddings", "published_at": "2023-11-21T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f16e60846", "title": "Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker", "url": "https://www.philschmid.de/inferentia2-llama-7b", "published_at": "2023-11-14T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f179265d3", "title": "Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker", "url": "https://www.philschmid.de/inferentia2-stable-diffusion-xl", "published_at": "2023-11-07T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f181a4585", "title": "Amazon Bedrock: How good (bad) is Titan Embeddings?", "url": "https://www.philschmid.de/amazon-titan-embeddings", "published_at": "2023-11-03T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f1895d56c", "title": "Evaluate LLMs and RAG a practical example using Langchain and Hugging Face", "url": "https://www.philschmid.de/evaluate-llm", "published_at": "2023-10-30T00:00:00+00:00" }, { "id": "01a087c2-4503-712d-b220-aa8f18ccb8f6", "title": "Deploy Idefics 9B and 80B on Amazon SageMaker", "url": "https://www.philschmid.de/sagemaker-idefics", "published_at": "2023-10-12T00:00:00+00:00" } ] posts Claim your blog

Back to philschmid.de

Blog · corpus.blog/blogs/philschmid.de/posts

philschmid.de

philschmid.de

2026

Create your own voice for Gemini 3.8 TTS original ↗

24 Sept 2026

How Foundational Models Became Superhuman in Bash original ↗

1 Sept 2026

Setup OpenClaw 2.0 with Gemini in Under 60 Seconds original ↗

31 Aug 2026

Recursive Self-Improvement original ↗

21 Aug 2026

Controlling Android with Gemini 3.7 Flash and 150 lines of Python original ↗

17 Aug 2026

Google Maps and Google Search now work together in the Gemini API original ↗

12 Aug 2026

Evaluating Agents Beyond the First Prompt original ↗

27 Jul 2026

Building Managed Agents That Use GitHub Without Exposing Your Token original ↗

17 Jul 2026

Control an Android Phone with Gemini 3.5 Flash Computer Use original ↗

25 Jun 2026

Getting started with the Gemini Interactions API original ↗

23 Jun 2026

How Gemini Managed Agents Works under the Hood original ↗

10 Jun 2026

Gemini Managed Agents: Developer Guide original ↗

26 May 2026

How Agents Manage Other Agents: Four Subagents Patterns in 2026 original ↗

5 May 2026

How to use Deep Research with the Gemini API original ↗

29 Apr 2026

How to correctly use MCP servers with your AI Agents original ↗

27 Apr 2026

8 Tips for Writing Agent Skills original ↗

13 Apr 2026

How to use Gemma 4 with the Gemini API and Google AI Studio original ↗

7 Apr 2026

How Kimi, Cursor, and Chroma Train Agentic Models with RL original ↗

28 Mar 2026

Combine Built-in Tools and Function Calling in the Gemini Interactions API original ↗

24 Mar 2026

Developer Guide: Nano Banana 2 with the Gemini Interactions API original ↗

16 Mar 2026

How Autoresearch will change Small Language Models adoption original ↗

10 Mar 2026

Practical Guide to Evaluating and Testing Agent Skills original ↗

4 Mar 2026

Writing a Good AGENTS.md original ↗

24 Feb 2026

Agents: Inner Loop vs Outer Loop original ↗

20 Feb 2026

Can We Close the Loop in 2026?original ↗

17 Feb 2026

Multimodal Function Calling with Gemini 3 and Interactions API original ↗

13 Feb 2026

Getting Started with Gemini Deep Research API original ↗

2 Feb 2026

The Agent Client Protocol Overview original ↗

1 Feb 2026

Gemini Interactions API Quick Start original ↗

22 Jan 2026

MCP is Not the Problem, It's your Server: Best Practices for Building MCP Servers original ↗

21 Jan 2026

Transparent PNG Stickers with Nano Banana Pro and Gemini interactions API original ↗

19 Jan 2026

Building Agents with the Gemini Interactions API original ↗

14 Jan 2026

Introducing MCP CLI: A way to call MCP Servers Efficiently original ↗

9 Jan 2026

The importance of Agent Harness in 2026 original ↗

5 Jan 2026

2025

8 Predictions for 2026. What comes next in AI?original ↗

31 Dec 2025

Context Engineering for AI Agents: Part 2 original ↗

4 Dec 2025

Why (Senior) Engineers Struggle to Build AI Agents original ↗

26 Nov 2025

Practical Guide on how to build an Agent from scratch with Gemini 3 original ↗

21 Nov 2025

Gemini 3 Prompting: Best Practices for General Usage original ↗

19 Nov 2025

Gemini API File Search: A Web Developer Tutorial original ↗

7 Nov 2025

Build your first AI Agent with Gemini, n8n and Google Cloud Run original ↗

30 Oct 2025

AI Agent Benchmark Compendium original ↗

15 Oct 2025

Agents 2.0: From Shallow Loops to Deep Agents original ↗

12 Oct 2025

The Rise of Subagents original ↗

15 Sept 2025

The 10 Steps for product AI generation with Gemini 2.5 Flash original ↗

27 Aug 2025

Memory in Agents, Make LLMs remember.original ↗

4 Aug 2025

Google Gemini CLI Cheatsheet original ↗

24 Jul 2025

Code Sandbox MCP: A Simple Code Interpreter for Your AI Agents original ↗

22 Jul 2025

Integrating Long-Term Memory with Gemini 2.5 original ↗

3 Jul 2025

The New Skill in AI is Not Prompting, It's Context Engineering original ↗

30 Jun 2025

Single vs Multi-Agent System?original ↗

20 Jun 2025

Zero to One: Learning Agentic Patterns original ↗

5 May 2025

Google Gemini LangChain Cheatsheet original ↗

28 Apr 2025

OpenAI Codex CLI, how does it work?original ↗

17 Apr 2025

Model Context Protocol (MCP) an overview original ↗

3 Apr 2025

ReAct agent from scratch with Gemini 2.5 and LangGraph original ↗

31 Mar 2025

Pass@k vs Pass^k: Understanding Agent Reliability original ↗

24 Mar 2025

Google Gemma 3 Function Calling Example original ↗

14 Mar 2025

Function Calling Guide: Google DeepMind Gemini 2.0 Flash original ↗

5 Mar 2025

From PDFs to Insights: Structured Outputs from PDFs with Gemini 2.0 original ↗

7 Feb 2025

Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial original ↗

30 Jan 2025

How to align open LLMs in 2025 with DPO and and synthetic data original ↗

23 Jan 2025

Bite: How Deepseek R1 was trained original ↗

17 Jan 2025

How to use Anthropic MCP Server with open LLMs, OpenAI or Google Gemini original ↗

17 Jan 2025

2024

Fine-tune classifier with ModernBERT in 2025 original ↗

25 Dec 2024

How to fine-tune open LLMs in 2025 with Hugging Face original ↗

20 Dec 2024

Deploy QwQ-32B-Preview the best open Reasoning Model on AWS with Hugging Face original ↗

3 Dec 2024

Deploy Llama 3.2 Vision on Amazon SageMaker original ↗

17 Oct 2024

How to Fine-Tune Multimodal Models or VLMs with Hugging Face TRL original ↗

30 Sept 2024

Evaluate open LLMs with Vertex AI and Gemini original ↗

24 Sept 2024

Evaluate LLMs using Evaluation Harness and Hugging Face TGI/vLLM original ↗

19 Sept 2024

Deploy open LLMs with Terraform and Amazon SageMaker original ↗

5 Aug 2024

LLM Evaluation doesn't need to be complicated original ↗

11 Jul 2024

Evaluating Open LLMs with MixEval: The Closest Benchmark to LMSYS Chatbot Arena original ↗

28 Jun 2024

Train and Deploy open Embedding Models on Amazon SageMaker original ↗

25 Jun 2024

Deploy Mixtral 8x7B on AWS Inferentia2 with Hugging Face Optimum original ↗

18 Jun 2024

Fine-tune Llama 3 with PyTorch FSDP and Q-Lora on Amazon SageMaker original ↗

11 Jun 2024

Fine-tune Embedding models for Retrieval Augmented Generation (RAG)original ↗

4 Jun 2024

Understanding the Cost of Generative AI Models in Production original ↗

27 May 2024

Deploy Llama 3 70B on AWS Inferentia2 with Hugging Face Optimum original ↗

23 May 2024

Deploy open LLMs with vLLM on Hugging Face Inference Endpoints original ↗

2 May 2024

Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora original ↗

22 Apr 2024

Deploy Llama 3 on Amazon SageMaker original ↗

18 Apr 2024

Accelerate Mixtral 8x7B with Speculative Decoding and Quantization on Amazon SageMaker original ↗

2 Apr 2024

Deploy Llama 2 70B on AWS Inferentia2 with Hugging Face Optimum original ↗

26 Mar 2024

Fine-Tune and Evaluate LLMs in 2024 with Amazon SageMaker original ↗

12 Mar 2024

Evaluate LLMs with Hugging Face Lighteval on Amazon SageMaker original ↗

5 Mar 2024

How to fine-tune Google Gemma with ChatML and Hugging Face TRL original ↗

1 Mar 2024

RLHF in 2024 with DPO and Hugging Face original ↗

23 Jan 2024

How to Fine-Tune LLMs in 2024 with Hugging Face original ↗

23 Jan 2024

Scale LLM Inference on Amazon SageMaker with Multi-Replica Endpoints original ↗

11 Jan 2024

2023

Fine-tune Llama 7B on AWS Trainium original ↗

21 Dec 2023

Programmatically manage 🤗 Inference Endpoints original ↗

20 Dec 2023

Deploy Mixtral 8x7B on Amazon SageMaker original ↗

12 Dec 2023

Deploy Embedding Models on AWS inferentia2 with Amazon SageMaker original ↗

21 Nov 2023

Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker original ↗

14 Nov 2023

Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker original ↗

7 Nov 2023

Amazon Bedrock: How good (bad) is Titan Embeddings?original ↗

3 Nov 2023

Evaluate LLMs and RAG a practical example using Langchain and Hugging Face original ↗

30 Oct 2023

Deploy Idefics 9B and 80B on Amazon SageMaker original ↗

12 Oct 2023