Microsoft
AI Agents for Beginners · Beginner to intermediate
A structured lesson path for understanding when to use agents and how to build simple agentic systems.
Topics
Agents, Multi-agent workflows, Tool use
AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
41 matches for "tool use"
AI Agents for Beginners · Beginner to intermediate
A structured lesson path for understanding when to use agents and how to build simple agentic systems.
Topics
Agents, Multi-agent workflows, Tool use
n8n AI workflow tutorials · Intermediate
Good for building agentic workflows that connect LLMs with APIs and business systems.
Topics
Automation, Agents, Tool use, Workflow design
CrewAI docs · Intermediate
Useful for learning role-based multi-agent patterns and orchestration concepts.
Topics
Agents, Multi-agent workflows, Tool use, Automation
Microsoft AutoGen docs · Intermediate
Good for learning multi-agent design patterns and conversation-based orchestration.
Topics
Agents, Multi-agent workflows, Tool use, AI engineering
Skill system
OpenClaw · Official docs
Use this to understand the OpenClaw skill format: markdown instruction files in directories with SKILL.md frontmatter and tool-use guidance.
Start
Read the official skills docs before installing community skills, then test one low-risk local skill in a disposable workspace.
Short course · DeepLearning.AI · Intermediate
You want a focused course on building stateful AI agents and agent workflows with LangGraph.
agents, langgraph, tool use, agentic workflows, ai engineering
Short course · DeepLearning.AI · Intermediate
You want a hands-on MCP course for connecting tools, context, and Claude-powered apps.
mcp, anthropic, tool use, context engineering, agents
Model launch and selection guide · Meta AI · Intermediate
You are comparing frontier models for long-horizon coding or knowledge work and need Meta's September 2, 2026 release notes on Muse Spark 1.3's tool use, instruction following, user steering, multitasking, model self-awareness, and availability through Muse Code and Meta Model API.
meta, muse spark 1.3, frontier models, coding agents, long-horizon agents
Open security benchmark · Hugging Face Community · Intermediate to advanced
You want a reproducible September 5, 2026 benchmark for comparing how agentic models handle indirect prompt injection, with public data, a public harness, control runs, tool-call traces, and outcome metrics tied to unauthorized payment actions.
agents, prompt injection, agent security, evals, tool use
Web agent guide · OpenAI · Intermediate
You want a website to expose predefined actions directly to ChatGPT Work or Codex in the built-in browser, using the same live page and signed-in session as the user.
openai, webmcp, site tools, browser agents, codex
Evaluation guide · Hugging Face Community · Intermediate
You need a practical evaluation plan built around representative tasks, controlled environments, observable traces, outcome and constraint metrics, repeated trials, and production failures turned into regression tests.
hugging face, agents, evals, evaluation harnesses, trajectory metrics
Model guide · OpenAI · Intermediate to advanced
You are evaluating or migrating to GPT-6 Astra and need implementation guidance for async tool calls, mid-turn steering, reasoning updates, Responses API tool use, unsupported parameters, and prompt changes.
openai, gpt-6 astra, responses api, async tool calling, mid-turn steering
Prompting guide · Anthropic · Intermediate to advanced
You are testing or migrating to Claude Fable 5.1 and want model-specific guidance for effort, progress updates, tool-call batching, long tasks, compaction, subagents, file edits, and verification.
anthropic, claude fable 5.1, prompting, coding agents, tool use
Evaluation guide · Google AI for Developers · Intermediate to advanced
You want Google's practical July 31, 2026 guide to running the same agent and model evaluations during development and on production traffic, with metrics for quality, safety, grounding, tool use, and trajectories.
google, gemini, agents, evals, model selection
Guide · Anthropic · Intermediate to advanced
You want Anthropic's current browser-specific toolset for page structure, element references, forms, tabs, screenshots, and browser actions without giving an agent a full desktop.
anthropic, claude, browser use, browser automation, agents
Migration guide · OpenAI · Intermediate
You are starting a new OpenAI integration or upgrading an older chat-completions flow and want the current API surface with built-in agent primitives.
openai, responses api, migration, agents, tool use
Guide · OpenAI · Intermediate
You need the official OpenAI path for wiring MCP servers and connectors into agent workflows instead of inventing your own tool contract.
openai, mcp, connectors, agents, tool use
Guide · OpenAI · Intermediate
You need the current OpenAI guidance for migrating to GPT-5.6, Sol or Terra tradeoffs, prompt shape changes, and tool-heavy workflow behavior.
openai, gpt-5.6, coding, reasoning, tool use
Guide · OpenAI · Intermediate
You want the official prompting adjustments for GPT-5.6 instead of reusing older GPT habits unchanged.
openai, gpt-5.6, prompting, reasoning, tool use
Guide · OpenAI · Intermediate
You want the broader official OpenAI prompting reference for task framing, examples, structure, and model-specific workflow design.
openai, prompt engineering, structured outputs, reasoning, tool use
Guide · OpenAI · Intermediate to advanced
You want the current OpenAI guidance for UI-driving agents, approval boundaries, and browser-style automation tasks.
openai, computer use, agents, automation, browser workflows
Guide · OpenAI · Intermediate
You are moving past one-off calls and need application-owned orchestration, tools, approvals, and state.
openai, agents, tool use, orchestration, state
Guide · Anthropic · Beginner to intermediate
You want Anthropic's current implementation-first starting point for Claude apps, tool use, prompts, streaming, and API workflows instead of jumping straight into isolated reference pages.
anthropic, claude, build with claude, api, agents
Guide · Anthropic · Intermediate
You want Anthropic's official explanation of where tools execute, how Claude decides to call them, and which tool patterns fit your workflow before building agent features.
anthropic, claude, tool use, agents, function calling
Guide · Anthropic · Intermediate to advanced
You want the official path for browser-like computer-use workflows and their operational constraints.
anthropic, computer use, agents, tool use, automation
Guide · Anthropic · Intermediate
You want Anthropic's official guidance for exposing tools and data to Claude through MCP instead of only reading the base spec.
anthropic, mcp, agents, tool use, connectors
Guide · Anthropic · Intermediate to advanced
You want Anthropic's current managed-agent starting point, including the Agents, Sessions, and Environments APIs for autonomous sessions, built-in tools, and secure execution.
anthropic, managed agents, agents, sandboxing, tool use
Release notes · Anthropic · Intermediate to advanced
You need the exact behavior, pricing, and compatibility changes in Claude Sonnet 5 before upgrading coding, tool-use, or long-context workflows.
anthropic, claude sonnet 5, release notes, coding, agents
Guide · Anthropic · Intermediate to advanced
You want Anthropic's current pattern for combining a fast executor with a higher-intelligence advisor model inside one tool-using workflow.
anthropic, advisor tool, tool use, reasoning, agents
GitHub repo · Anthropic · Intermediate
You want practical, copyable Claude examples and notebooks from Anthropic instead of starting with blank prompts or abstract API docs.
anthropic, claude, cookbook, examples, tool use
Guide · Google AI for Developers · Intermediate
You want the official Google path for low-latency voice and vision agents before designing a realtime Gemini workflow.
gemini, live api, voice agents, realtime, multimodal
Guide · Google AI for Developers · Intermediate
You want current Gemini-specific prompting advice for system instructions, reasoning tasks, multimodal inputs, and tool-connected workflows.
gemini, prompting, reasoning, multimodal, tool use
API docs · Meta Llama · Intermediate
You want Meta's current hosted entry point for Muse Spark and agent-ready coding workflows rather than assuming the older Llama docs cover the newest API surface.
meta, model api, muse spark, muse code, coding agents
Guide · Mistral AI · Intermediate
You want Mistral's official explanation of its Agents and Conversations API before building tool-using or workflow-style apps.
mistral, agents, tool use, conversations, workflows
Quickstart · Cohere · Intermediate
You want the official Cohere path for building tool-using agentic applications with multi-step reasoning and citations.
cohere, agents, tool use, reasoning, citations
Guide · DeepSeek · Intermediate
You want the current DeepSeek path for Responses-style orchestration and need to know that support currently centers on `deepseek-v4-flash` before planning a migration.
deepseek, responses api, openai compatible, agents, tool use
Quickstart · Perplexity · Intermediate
You want the fastest official path into Perplexity's multi-provider Agent API before deciding how much search, tool use, or routing you need.
perplexity, agent api, multi-provider, web search, tool use
Guide · Anthropic · Intermediate
You want Anthropic's official SDK path for programmable agents that reuse Claude Code's tool loop, context handling, and execution model.
anthropic, agents, claude code, sdk, tool use
Guide · Google AI for Developers · Intermediate to advanced
You want the official Gemini path for browser, mobile, and desktop control agents before building UI-driving workflows.
gemini, computer use, browser automation, desktop automation, agents
Guide · Google AI for Developers · Intermediate to advanced
You need Google's current recommended API surface for agentic workflows, server-side state, and complex multimodal conversations.
gemini, interactions api, agents, tool use, stateful workflows
Model docs · Cohere · Intermediate
You want Cohere's current reasoning-model reference for enterprise tool use, RAG, and multilingual agent workflows before defaulting to a generic Command model.
cohere, command a reasoning, reasoning models, tool use, rag