Harmonic achieved 4x user retention by replacing a complex LangGraph pipeline with a simple Deep Agents tool loop.
“I think everyone's secret weapon is becoming Scout.”
tool-calling
9 tracked signals on tool-calling.
AI agent evaluation must shift from scoring single tool calls to measuring full multi-step task completion.
“Scoring whether the model sounds right tells you almost nothing about whether the work finished.”
Apple introduces SpotlightSearchTool, letting on-device LLMs search app content via Core Spotlight for grounded responses.
“today, we're introducing SpotlightSearchTool. It's a tool that adopts the tool protocol, to let a language model directly search your app's content in Core Spotlight for contextual response generation.”
Natera's healthcare voice agent hit 100% tool-calling accuracy at under $0.01 per call using Bedrock AgentCore
An agent harness is the surrounding engineering scaffolding built around the core model-and-tool-calling loop.
“Harness is sort of the surrounding support that we add onto that core model and tool-calling loop.”
Microsoft Foundry offers a single hub for pre-built and third-party agent tools with enterprise-grade scalability.
“Tool calling is what enables your agent to perform an action, and this is how your agents provide real business value.”
Combining SFT and DPO on SageMaker AI improves a small model's tool-calling accuracy for agents.
“When an agent picks the wrong tool, formats parameters incorrectly, or breaks a workflow chain, task completion times grow, error rates rise, support costs increase, and user experiences degrade.”
DevExpress demos connecting Azure OpenAI tool calling to Blazor grid and reporting controls for natural-language data interaction
“This is not about generating code and it's not about dropping a chatbot beside an existing app and calling it done. This is about connecting AI to the controls, to the data, and to the workflows users already rely on.”
Databricks explains tool calling as AI models interacting with external tools and APIs