# \#function-calling **URL:** https://www.artofsm.art/tag/function-calling/190.md [Latest](https://www.artofsm.art/latest.md) · [Categories](https://www.artofsm.art/categories.md) · [Tags](https://www.artofsm.art/tags.md) --- ## [Use Needle to Create an AI Assistant on Your Raspberry Pi](https://www.artofsm.art/t/use-needle-to-create-an-ai-assistant-on-your-raspberry-pi/27793)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 November 2026 13:21 UTC](https://www.artofsm.art/t/use-needle-to-create-an-ai-assistant-on-your-raspberry-pi/27793 "2026-11-06T13:21:00Z")
The video demonstrates how to create a privacy-focused, local AI assistant on a Raspberry Pi using Needle, a lightweight, CPU-only AI model that interprets user requests to call predefined functions without… --- ## [NVIDIA's NEW Nemotron 3.5 Bolt 4B Model Is INSANE... I Tested It 10 Ways On An 8GB Laptop](https://www.artofsm.art/t/nvidias-new-nemotron-3-5-bolt-4b-model-is-insane-i-tested-it-10-ways-on-an-8gb-laptop/26877)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [26 October 2026 14:17 UTC](https://www.artofsm.art/t/nvidias-new-nemotron-3-5-bolt-4b-model-is-insane-i-tested-it-10-ways-on-an-8gb-laptop/26877 "2026-10-26T14:17:23Z")
NVIDIA’s Neatron 3.5 Bolt 4B model delivers fast, efficient multi-turn conversational AI with strong tool integration and context handling on an 8GB laptop, excelling in tasks like calculator use and vision… --- ## [Saluki 27B: a 54 GB model squeezed into 7.89 GB (88 vs 84 on tool calling)](https://www.artofsm.art/t/saluki-27b-a-54-gb-model-squeezed-into-7-89-gb-88-vs-84-on-tool-calling/25640)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [11 October 2026 01:55 UTC](https://www.artofsm.art/t/saluki-27b-a-54-gb-model-squeezed-into-7-89-gb-88-vs-84-on-tool-calling/25640 "2026-10-11T01:55:02Z")
Saluki is a 27 billion parameter AI model by Underdog that has been efficiently compressed from 54 GB to 7.89 GB, enabling it to run on a 16 GB laptop while outperforming the original model in tool calling … --- ## [My Fine-Tuned Open Laya Beat Jev at Agent Tool-Calling](https://www.artofsm.art/t/my-fine-tuned-open-laya-beat-jev-at-agent-tool-calling/25206)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 October 2026 14:25 UTC](https://www.artofsm.art/t/my-fine-tuned-open-laya-beat-jev-at-agent-tool-calling/25206 "2026-10-07T14:25:10Z")
The video showcases how fine-tuning the open-source model Laya significantly improves its performance in agent tool-calling tasks, surpassing the popular Jev model and demonstrating strong generalization ac… --- ## [Holo4: A Model That Clicks, Codes and Calls Tools](https://www.artofsm.art/t/holo4-a-model-that-clicks-codes-and-calls-tools/25127)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [6 October 2026 14:31 UTC](https://www.artofsm.art/t/holo4-a-model-that-clicks-codes-and-calls-tools/25127 "2026-10-06T14:31:04Z")
Holo4, developed by H Company, is a unified AI model that dynamically integrates GUI interactions, code execution, and API/tool calls to handle complex, multi-modal tasks within a single framework, offering… --- ## [Can A 29MB Model Replace Your Cloud LLM?](https://www.artofsm.art/t/can-a-29mb-model-replace-your-cloud-llm/24554)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [29 September 2026 08:24 UTC](https://www.artofsm.art/t/can-a-29mb-model-replace-your-cloud-llm/24554 "2026-09-29T08:24:18Z")
Cactus Compute’s Needle 3 is a highly compact AI model, only 29MB in size, designed to execute specific offline commands by selecting predefined actions rather than generating conversational text, making it… --- ## [I Trained the TinyStories Model to Do Math](https://www.artofsm.art/t/i-trained-the-tinystories-model-to-do-math/21756)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [27 July 2026 17:20 UTC](https://www.artofsm.art/t/i-trained-the-tinystories-model-to-do-math/21756 "2026-07-27T17:20:45Z")
The video demonstrates how a small language model trained on children’s stories was enhanced to perform arithmetic by integrating external calculator modules through tool calls, enabling accurate math witho… --- ## [LLMs Can Use Tools, Just Like You and I](https://www.artofsm.art/t/llms-can-use-tools-just-like-you-and-i/21740)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [27 July 2026 13:19 UTC](https://www.artofsm.art/t/llms-can-use-tools-just-like-you-and-i/21740 "2026-07-27T13:19:34Z")
The video explains how large language models (LLMs) can enhance their accuracy and functionality by dynamically integrating external tools, such as simple and advanced string manipulation programs, during t… --- ## [Cactus Needle - The 26M Function Calling Model](https://www.artofsm.art/t/cactus-needle-the-26m-function-calling-model/21130)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [12 July 2026 13:20 UTC](https://www.artofsm.art/t/cactus-needle-the-26m-function-calling-model/21130 "2026-07-12T13:20:38Z")
Cactus Needle is an open-source, lightweight function calling model with only 26 million parameters that efficiently performs tasks like setting timers and controlling smart home devices on consumer hardwar… --- ## [The New Agents Window in VS Code | LIVE169](https://www.artofsm.art/t/the-new-agents-window-in-vs-code-live169/19639)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [5 June 2026 14:05 UTC](https://www.artofsm.art/t/the-new-agents-window-in-vs-code-live169/19639 "2026-06-05T14:05:36Z")
Harold from the VS Code team introduces the new Agent Window, a unified interface that helps developers efficiently manage multiple agents across local and remote workspaces, including GitHub repositories a… --- ## [Stop Building Just Websites: AutoCoder Builds Real Apps](https://www.artofsm.art/t/stop-building-just-websites-autocoder-builds-real-apps/18909)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [19 May 2026 13:34 UTC](https://www.artofsm.art/t/stop-building-just-websites-autocoder-builds-real-apps/18909 "2026-05-19T13:34:44Z")
AutoCoder is an all-in-one platform that effortlessly builds full-stack web and mobile applications from simple prompts, featuring interactive user flow diagrams, multi-role security management, and a marke… --- ## [ChatGPT Codex Masterclass: Complete Beginner’s Guide](https://www.artofsm.art/t/chatgpt-codex-masterclass-complete-beginner-s-guide/18546)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [13 May 2026 16:53 UTC](https://www.artofsm.art/t/chatgpt-codex-masterclass-complete-beginner-s-guide/18546 "2026-05-13T16:53:37Z")
The video introduces Codex as a leading all-in-one AI platform featuring advanced co-working, image generation, and browser capabilities, highlighting its superiority over competitors. It showcases practica… --- ## [CLI vs MCP: How AI Agents Choose the Right Tool for the Job](https://www.artofsm.art/t/cli-vs-mcp-how-ai-agents-choose-the-right-tool-for-the-job/18306)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [4 May 2026 11:21 UTC](https://www.artofsm.art/t/cli-vs-mcp-how-ai-agents-choose-the-right-tool-for-the-job/18306 "2026-05-04T11:21:33Z")
The video compares AI agents using Command Line Interface (CLI) and Model Context Protocol (MCP) for interacting with external systems, highlighting CLI’s efficiency and compactness for straightforward task… --- ## [Why Every AI Coding Tool is Converging on Plan Mode?](https://www.artofsm.art/t/why-every-ai-coding-tool-is-converging-on-plan-mode/18234)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [1 May 2026 14:21 UTC](https://www.artofsm.art/t/why-every-ai-coding-tool-is-converging-on-plan-mode/18234 "2026-05-01T14:21:30Z")
In 2026, AI coding tools like Claude Code, Cursor, and Codex have converged on a “plan mode” approach that prioritizes detailed, spec-driven planning based on product requirements before development begins.… --- ## [Custom Instructions: How I Really Made Copilot Listen! | Ep 2 of 8](https://www.artofsm.art/t/custom-instructions-how-i-really-made-copilot-listen-ep-2-of-8/17997)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [24 April 2026 20:20 UTC](https://www.artofsm.art/t/custom-instructions-how-i-really-made-copilot-listen-ep-2-of-8/17997 "2026-04-24T20:20:55Z")
The video demonstrates how custom instructions in Copilot serve as a powerful rulebook within VS Code, enabling users to enforce coding standards like SOLID principles and WCAG accessibility automatically a… --- ## [I Finally Fixed My Claude Code Usage Limits (Here's How)](https://www.artofsm.art/t/i-finally-fixed-my-claude-code-usage-limits-heres-how/17581)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [13 April 2026 20:05 UTC](https://www.artofsm.art/t/i-finally-fixed-my-claude-code-usage-limits-heres-how/17581 "2026-04-13T20:05:27Z")
The video explains how to manage and reduce token usage in Claude AI by employing strategies such as clearing context between tasks, using rewind features, optimizing MCP servers and LSP plugins, and mainta… --- ## [4 Ways AI Agents Should Behave for Smarter Systems](https://www.artofsm.art/t/4-ways-ai-agents-should-behave-for-smarter-systems/16540)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [8 March 2026 11:21 UTC](https://www.artofsm.art/t/4-ways-ai-agents-should-behave-for-smarter-systems/16540 "2026-03-08T11:21:23Z")
The video argues that AI agents should be designed as specialized, narrowly-permissioned collaborators rather than all-powerful “super agents,” minimizing both their autonomy and access to reduce risks. It … --- ## [Claude Code Skills Just Changed Forever](https://www.artofsm.art/t/claude-code-skills-just-changed-forever/16495)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [5 March 2026 22:31 UTC](https://www.artofsm.art/t/claude-code-skills-just-changed-forever/16495 "2026-03-05T22:31:12Z")
The video introduces Claude Skill Creator 2.0, a major upgrade that streamlines building, testing, and optimizing AI workflows with automated evaluation, interactive benchmarks, and improved reliability for… --- ## [How to create JOBS for OpenClaw agents](https://www.artofsm.art/t/how-to-create-jobs-for-openclaw-agents/16267)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [25 February 2026 13:22 UTC](https://www.artofsm.art/t/how-to-create-jobs-for-openclaw-agents/16267 "2026-02-25T13:22:06Z")
The video explains that to create jobs for OpenClaw AI agents, you should treat them as employees handling recurring roles rather than just assistants for one-off tasks, enabling scalable delegation of ongo… --- ## [Never Run claude /init](https://www.artofsm.art/t/never-run-claude-init/16228)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [24 February 2026 09:52 UTC](https://www.artofsm.art/t/never-run-claude-init/16228 "2026-02-24T09:52:31Z")
The video warns against using commands like “claude /init” to generate global context files (e.g., claw.md) for coding agents, as these files waste valuable context space, quickly become outdated, and often… --- ## [So, uh, about that CLAUDE.md file](https://www.artofsm.art/t/so-uh-about-that-claude-md-file/16170)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [23 February 2026 08:56 UTC](https://www.artofsm.art/t/so-uh-about-that-claude-md-file/16170 "2026-02-23T08:56:18Z")
The video examines whether Agent MD and Claude MD context files actually improve AI coding agent performance, citing a study that found these files often have little benefit and can even reduce effectivenes… --- ## [VSCLive004](https://www.artofsm.art/t/vsclive004/16117)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [20 February 2026 12:21 UTC](https://www.artofsm.art/t/vsclive004/16117 "2026-02-20T12:21:12Z")
The video introduces MCTP (Multi-Channel Tool Protocol) as a powerful framework for extending AI agents with structured tool integration, asynchronous tasks, and interactive resource handling, enabling rich… --- ## [How to Build Human-in-the-Loop for AI Agents (Practical Guide)](https://www.artofsm.art/t/how-to-build-human-in-the-loop-for-ai-agents-practical-guide/15350)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [19 January 2026 14:20 UTC](https://www.artofsm.art/t/how-to-build-human-in-the-loop-for-ai-agents-practical-guide/15350 "2026-01-19T14:20:34Z")
The video explains how to implement human-in-the-loop (HITL) systems for AI agents, allowing AI to handle routine tasks autonomously while requiring human approval for higher-risk actions. It covers practic… --- ## [MiroThinker 1.5 - The 30B That Outperforms 1T Models](https://www.artofsm.art/t/mirothinker-1-5-the-30b-that-outperforms-1t-models/15147)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 January 2026 15:50 UTC](https://www.artofsm.art/t/mirothinker-1-5-the-30b-that-outperforms-1t-models/15147 "2026-01-07T15:50:50Z")
The video introduces MiroThinker 1.5, an open-source, agentic AI model designed for advanced tool use and multi-step reasoning, offering competitive performance to much larger models while remaining accessi… --- ## [Agent Skills in VS Code](https://www.artofsm.art/t/agent-skills-in-vs-code/14985)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [26 December 2025 11:20 UTC](https://www.artofsm.art/t/agent-skills-in-vs-code/14985 "2025-12-26T11:20:43Z")
The video explains how “agent skills” in Visual Studio Code allow users to modularly customize AI agent behavior by organizing specialized instructions and resources into skill folders, which the agent load… --- ## [FunctionGemma - Function Calling at the Edge](https://www.artofsm.art/t/functiongemma-function-calling-at-the-edge/14854)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [19 December 2025 12:21 UTC](https://www.artofsm.art/t/functiongemma-function-calling-at-the-edge/14854 "2025-12-19T12:21:28Z")
Function Gemma is a lightweight, customizable function-calling language model designed to run efficiently on edge devices like mobile phones, enabling apps and games to execute specific functions locally. B… --- ## [AI Tool Calling via Natural Language: LLMs, APIs & Docker in Action](https://www.artofsm.art/t/ai-tool-calling-via-natural-language-llms-apis-docker-in-action/14827)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [18 December 2025 12:21 UTC](https://www.artofsm.art/t/ai-tool-calling-via-natural-language-llms-apis-docker-in-action/14827 "2025-12-18T12:21:31Z")
The video explains how large language models (LLMs) can be extended beyond text generation to perform real-world actions by detecting when to call external APIs through a tool orchestrator that manages func… --- ## [MCP vs. RAG: How AI Agents & LLMs Connect to Data](https://www.artofsm.art/t/mcp-vs-rag-how-ai-agents-llms-connect-to-data/14035)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [17 November 2025 12:24 UTC](https://www.artofsm.art/t/mcp-vs-rag-how-ai-agents-llms-connect-to-data/14035 "2025-11-17T12:24:42Z")
The video explains how Retrieval Augmented Generation (RAG) enhances large language models by retrieving relevant external information to provide accurate, context-rich responses, while Model Context Protoc… --- ## [Build Hour: Built-In Tools](https://www.artofsm.art/t/build-hour-built-in-tools/12336)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [3 September 2025 00:44 UTC](https://www.artofsm.art/t/build-hour-built-in-tools/12336 "2025-09-03T00:44:20Z")
The video “Build Hour: Built-In Tools” features Christine and Katya from OpenAI demonstrating how built-in tools like web search, file search, and the code interpreter enable large language models to perfor… --- ## [Build Hour: Agentic Tool Calling](https://www.artofsm.art/t/build-hour-agentic-tool-calling/12333)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [3 September 2025 00:44 UTC](https://www.artofsm.art/t/build-hour-agentic-tool-calling/12333 "2025-09-03T00:44:18Z")
The Build Hour session hosted by Sarah Urbonus and Alain from OpenAI demonstrated how to build agentic systems that autonomously plan and execute tasks using OpenAI’s latest APIs, combining advanced reasoni… [Next page](https://www.artofsm.art/tag/function-calling/190.md?match_all_tags=true&page=1&tags%5B%5D=function-calling)