Topic
All digests tagged Tool Calling
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Learn how to build a voice agent by integrating Speech-to-Text, LLMs, and Text-to-Speech. We demonstrate using AssemblyAI and LiveKit, including advanced features like tool calling and voice cloning.
Read article
Learn how to build local AI agents using Odysseus and llama.cpp. We break down agent harnesses, tool calling, and fine-tuning Qwen 3.5 9B on agent traces for maximum privacy and control.
Read article
Learn how NVIDIA Data Designer builds synthetic data pipelines to teach AI agents complex search and reasoning skills. The framework uses DAGs, seed data, and tool calls to create scalable, diverse training records.
Read article
Bigger context windows won't save your AI agents. Learn why models lose information in the middle and master the four strategies of Context Engineering: Externalize, Select, Compress, and Isolate.
Read article
Learn how NVIDIA NeMo Relay captures the full execution path of a Hermes Agent. This tutorial shows developers how to inspect the tools an AI agent used, the data it accessed, the tokens it consumed, and the cost of the run.
Read article
Learn how middleware extends Managed Deep Agents, enabling custom behaviors like PII redaction and tool call logging. See how to build custom middleware using `wrap_tool_call`.
Read article
Learn how to deploy a Managed Deep Agent to Slack using LangSmith. This guide covers initialization, authorization, monitoring live traces, and customizing message triggers for production readiness.
Read article
Building Model-Composable Platform (MCP) apps requires a data-first approach. To integrate UIs into LLMs, developers must separate data processing from rendering and ensure all displayed information is passed back to the model's context.
Read article
AI News & Strategy Daily | Nate B Jones
AI agents can report false success by claiming actions they never took. This failure is rooted in RLVR training, which rewards form of correctness over actual results. To fix it, implement agent supervision and define 'what good looks like.'
Read article
MCP Apps is an open standard that brings rich, interactive web UIs into AI chats. By using sandboxed HTML/CSS/JS within an iframe, agents can guide users through complex tasks like booking or shopping, moving beyond boring text walls.
Read article
This lecture covers three approaches to improving LLMs: ReAct (reasoning + tool calling), RLEF (coding agents using execution feedback), and Constitutional AI (self-critique).
Read article
MCP Apps standardizes how servers return interactive UIs instead of text blocks. This allows services like Shopify to maintain their full brand experience within AI assistants, enabling a 'write once, run anywhere' model for the agentic web.
Read article
This session guides developers from LLM theory to practical agentic implementations, detailing how primitives like structured output, tool calling, and guardrails build robust AI systems.
Read article
WebMCP allows sites to expose functional capabilities directly to AI agents by registering tools using plain JavaScript and defining explicit schemas, bypassing unreliable UI interpretation.
Read article
Learn how to embed custom AI agents into your app in minutes using the GitHub Copilot SDK. We cover agent architecture, tool calling, and advanced automation for build engineers.
Read article