NEW RUNTIME

Topic hub

Tool use

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about tool use.

Retrieval answer

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about tool use. Tool use is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.

Last 14 days

Latest on this topic

9 items on Tool use published in the last 14 days, newest first. Showing the newest 8.

  1. DiffuSpace releases Clover-35B-A3B-Preview, an open-weight 35B MoE diffusion language modelField note

  2. Vercel AI SDK adds a Web Fetch Tool that works with any function-calling model.Field note

  3. Vercel releases @ai-sdk/tool-web-fetch 1.0, a first-party web fetch tool for any tool-calling model in the AI SDKField note

  4. Mistral Advances AI for Engineering with NVIDIAField note

  5. Meta released Muse Glimmer 30B , an open-weight agentic model under Apache 2.0.Field note

  6. Meta released Muse Glimmer 30B , an open-weight agentic model under Apache 2.0.Signal

  7. Simon Willison released llm-tools-datasette 0.1.1 to fix a compatibility break introduced when LLM moved toField note

  8. But Meta isn't the only company seeking to claim its piece of the US open source ecosystem.Field note

Field notes

What should readers understand next?

1 notes

  1. Agent APIs Need Fewer Magic Tricks and More Facts

    Agent-first APIs should return explicit fields, precise errors, raw facts, and traceable metadata so models can repair tool calls deterministically instead of guessing world state.

Raw signals

What changed recently?

6 signals

  1. Pydantic AI loads capabilities only when needed

    A capability can bundle instructions, tools, model settings, and hooks while exposing only a compact description until activation.

  2. DoorDash Assistant Builds the Cart Instead of Giving Advice

    The assistant combines retrieval, personalization, and transaction tools so the product result is an editable action state, not prose.

  3. Agent Evals Become a Discipline Separate from Model Evals

    Reliable agents require evaluation of trajectories, tools, state, recovery, and outcomes rather than grading only the final answer.

  4. Google Search Adds Agentic Action to Discovery

    Search is extending from retrieval and answers into tasks, tool use, and guided execution inside a familiar high-traffic interface.

  5. A Personal Agent OS Emerges from Small CLI Tools

    A suite of narrow command-line adapters gives an agent composable access to messaging, media, GitHub, search, and local systems.

  6. Voice Agents Move from Conversation to Tool-Using Work

    OpenAI's voice stack combines low-latency speech with tool calls and state, making voice a working interface rather than a novelty chat.

Next reads

Read next

Open the graph
  1. 01related materialAgent APIs Need Fewer Magic Tricks and More FactsContinue through the Tool use topic.
  2. 02related materialPydantic AI loads capabilities only when neededContinue through the Tool use topic.
  3. 03related materialDoorDash Assistant Builds the Cart Instead of Giving AdviceContinue through the Tool use topic.
  4. 04related materialAgent Evals Become a Discipline Separate from Model EvalsContinue through the Tool use topic.
  5. 05related materialGoogle Search Adds Agentic Action to DiscoveryContinue through the Tool use topic.
Who read this page?Machine requests, hidden until opened

Loading the privacy-safe route aggregate…

Open the JSON contract