Pandoc already did that and I suspect most toolcalling LLMs just use that.
November 9, 2026 at 10:30 AM
Pandoc already did that and I suspect most toolcalling LLMs just use that.
Tool calling is how AI goes from smart text generator to action-taker. Explore function calling with .NET examples & understand the AI-app interaction loop. #AI #ToolCalling #LLM www.isaacl.dev/hdq
What is tool calling in AI? Build a simple .NET example
LLMs understand language, but they can't query your database or call an API on their own. Tool calling closes that gap: the model names a function and its arguments, and your app runs it. This post wa...
www.isaacl.dev
November 10, 2026 at 1:00 PM
Tool calling is how AI goes from smart text generator to action-taker. Explore function calling with .NET examples & understand the AI-app interaction loop. #AI #ToolCalling #LLM www.isaacl.dev/hdq
AI agents are built from raw API calls: tool schemas + a request–execute–respond loop let models fetch live data, then answer grounded results. Includes optional persistent conversation memory. 🤖🛠️ #AIagents #ToolCalling #Python #Anthropic #APIs
How (and Why) to Build an AI Agent from Scratch in Python - MachineLearningMastery.com
In this article, you will learn what an AI agent is and how to build one from scratch in plain Python using the Anthropic API, without relying on any orchestration framework.
machinelearningmastery.com
November 5, 2026 at 6:40 PM
AI agents are built from raw API calls: tool schemas + a request–execute–respond loop let models fetch live data, then answer grounded results. Includes optional persistent conversation memory. 🤖🛠️ #AIagents #ToolCalling #Python #Anthropic #APIs
Costo por token IA: la tarifa que no es plana
El costo por token IA no define el éxito: lo que construís alrededor del modelo sí importa. Descubrí cómo optimizarlo y mejorá tus resultados.
#costoportokenia #llm #rag #toolcalling #openai
El costo por token IA no define el éxito: lo que construís alrededor del modelo sí importa. Descubrí cómo optimizarlo y mejorá tus resultados.
#costoportokenia #llm #rag #toolcalling #openai
Costo por token IA: la tarifa que no es plana
Entrada y salida se cobran distinto, el historial se refactura en cada turno y el caching puede bajar el costo 90%. Repasamos el pricing real de OpenAI.
blog.donweb.com
November 7, 2026 at 1:44 PM
Tool calling needs contracts, not hope.
A model choosing an action is not a production-ready call. Every tool needs accepted inputs, permissions, validation, timeout and retry behavior, idempotency, safe failure handling.
The application enforces the boundaries.
#ToolCalling #nRouter
A model choosing an action is not a production-ready call. Every tool needs accepted inputs, permissions, validation, timeout and retry behavior, idempotency, safe failure handling.
The application enforces the boundaries.
#ToolCalling #nRouter
November 3, 2026 at 12:37 PM
Tool calling needs contracts, not hope.
A model choosing an action is not a production-ready call. Every tool needs accepted inputs, permissions, validation, timeout and retry behavior, idempotency, safe failure handling.
The application enforces the boundaries.
#ToolCalling #nRouter
A model choosing an action is not a production-ready call. Every tool needs accepted inputs, permissions, validation, timeout and retry behavior, idempotency, safe failure handling.
The application enforces the boundaries.
#ToolCalling #nRouter
vLLM 0.31 llega a 100% de precisión en tool calling
Tu agente falla llamadas a herramientas? vLLM 0.31 subio la precision tool calling vLLM al 100% con una sola flag. Mira que cambio y como activarlo
#vllm #toolcalling #constraineddecoding #xgrammar #kimik2
Tu agente falla llamadas a herramientas? vLLM 0.31 subio la precision tool calling vLLM al 100% con una sola flag. Mira que cambio y como activarlo
#vllm #toolcalling #constraineddecoding #xgrammar #kimik2
vLLM 0.31 llega a 100% de precisión en tool calling
Ubicloud confirmo 100% de schema accuracy en Kimi y DeepSeek activando constrained decoding en vLLM 0.31. Te contamos como funciona y como activarlo.
blog.donweb.com
October 27, 2026 at 12:41 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 7, 2026 at 3:18 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 7, 2026 at 3:18 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 7, 2026 at 12:40 AM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 7, 2026 at 12:21 AM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 7, 2026 at 12:39 AM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 6, 2026 at 11:00 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 6, 2026 at 11:00 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 6, 2026 at 6:04 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 6, 2026 at 6:29 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 4, 2026 at 6:29 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 4, 2026 at 6:28 PM
#AI #ArtificialIntelligence #AIEngineering #GenerativeAI #LLM #AIAgents #AgenticAI #LLMAgents #MCP #ModelContextProtocol #ToolCalling #RAG #SoftwareEngineering #FullStack #Backend #TypeScript #NextJS #NestJS #PostgreSQL #SaaS #Automation #TechStartup #BuildInPublic #IndieHackers
October 4, 2026 at 6:26 PM
Every AI agent runs on one simple pattern: Tool Calling.
The model never runs your code. It just asks for what it needs, and your app does the rest.
We break it down in 5 steps with a live GitHub demo.
#AIAgents #ToolCalling #TechExplained #AI
The model never runs your code. It just asks for what it needs, and your app does the rest.
We break it down in 5 steps with a live GitHub demo.
#AIAgents #ToolCalling #TechExplained #AI
September 16, 2026 at 2:50 PM
Every AI agent runs on one simple pattern: Tool Calling.
The model never runs your code. It just asks for what it needs, and your app does the rest.
We break it down in 5 steps with a live GitHub demo.
#AIAgents #ToolCalling #TechExplained #AI
The model never runs your code. It just asks for what it needs, and your app does the rest.
We break it down in 5 steps with a live GitHub demo.
#AIAgents #ToolCalling #TechExplained #AI
El bug de Ollama que hace que gemma4 invente datos
¿Por qué Ollama inventa valores en tool calling? El ollama function calling bug en gemma4 borra type y description sin avisar. Mirá el fix de 12 líneas
#ollama #gemma4 #functioncalling #toolcalling #bugsdeia
¿Por qué Ollama inventa valores en tool calling? El ollama function calling bug en gemma4 borra type y description sin avisar. Mirá el fix de 12 líneas
#ollama #gemma4 #functioncalling #toolcalling #bugsdeia
El bug de Ollama que hace que gemma4 invente datos
Un parámetro llamado type o description desaparece del prompt en Ollama y el modelo rellena el hueco inventando. Causa técnica y fix explicados.
blog.donweb.com
September 16, 2026 at 3:16 AM
has anyone done a model that’s good at toolcalling but optimized for narrative as opposed to “be good at writing code”. iirc theres the M2.5-Her rp fork but that’s it
September 10, 2026 at 10:01 PM
has anyone done a model that’s good at toolcalling but optimized for narrative as opposed to “be good at writing code”. iirc theres the M2.5-Her rp fork but that’s it
You can now build on top of the same voice system that we shipped to 1B users in ChatGPT.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
QT: https://twitter.com/i/status/2098099269551149398
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
QT: https://twitter.com/i/status/2098099269551149398
September 10, 2026 at 5:48 PM
You can now build on top of the same voice system that we shipped to 1B users in ChatGPT.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
QT: https://twitter.com/i/status/2098099269551149398
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
QT: https://twitter.com/i/status/2098099269551149398
You can now build on top of the same voice system that we shipped to 1B users in ChatGPT.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
RT @OpenAIDevs: GPT-Live-1 is now available in the API.
Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.
Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.
September 10, 2026 at 5:48 PM
You can now build on top of the same voice system that we shipped to 1B users in ChatGPT.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
So many fun applications of a full duplex system with solid toolcalling. Going back to text-only experiences after this feels harder than I had expected.
1. Capability-tagged models - wrong model + feature = compile error
Calling .tools(...) on a model that can't call tools? In sttp-ai that's now a compile error. Model constants carry capability tags (Vision, ToolCalling, StructuredOutput, Reasoning) and the agent builder checks them at compile time
Calling .tools(...) on a model that can't call tools? In sttp-ai that's now a compile error. Model constants carry capability tags (Vision, ToolCalling, StructuredOutput, Reasoning) and the agent builder checks them at compile time
August 31, 2026 at 12:50 PM
1. Capability-tagged models - wrong model + feature = compile error
Calling .tools(...) on a model that can't call tools? In sttp-ai that's now a compile error. Model constants carry capability tags (Vision, ToolCalling, StructuredOutput, Reasoning) and the agent builder checks them at compile time
Calling .tools(...) on a model that can't call tools? In sttp-ai that's now a compile error. Model constants carry capability tags (Vision, ToolCalling, StructuredOutput, Reasoning) and the agent builder checks them at compile time
Time to edit my #ToolCalling config for "Cherry": unspecified type descriptor youtu.be/6NukGtwJb7Y?...
#AgenticEngineering #SecondBrainPipeline #GroceryRunbook
#AgenticEngineering #SecondBrainPipeline #GroceryRunbook
second brain cringelords
YouTube video by Eric Morrison
youtu.be
August 24, 2026 at 6:52 AM
Time to edit my #ToolCalling config for "Cherry": unspecified type descriptor youtu.be/6NukGtwJb7Y?...
#AgenticEngineering #SecondBrainPipeline #GroceryRunbook
#AgenticEngineering #SecondBrainPipeline #GroceryRunbook