tool use
An LLM's ability to call external tools—such as a web search, calculator, or Python interpreter—rather than relying solely on its memorized knowledge.
As defined in Ai Sota #2026
Where it comes up · 6
- AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote5 claims
- What's next for AI agentic workflows ft. Andrew Ng of AI Fund3 claims
- Ai Sota #20262 claims
- Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB2 claims
- Mark Zuckerberg — Llama 3, $10B models, Caesar Augustus, & 1 GW datacenters1 claim
- Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems1 claim
Most important claims · 10 of 14Search all claims for “tool use” →
- The skills that transformed AI this year—tool use, running CLI commands, handling Git, search—are almost entirely downstream of RLVR training, because when you train models on verifiable tasks they very quickly learn to try a tool, observe the output, and iterate, generalizing into a foundation for software engineering.Ai Sota #2026
- Tool use is a huge unlock because one of the best ways to reduce hallucinations is to have the LLM not try to remember or make up information—using a calculator or Python for math, or a web search for facts—so it retrieves reliable information rather than memorizing it.Ai Sota #2026
- Foundation models are getting better at penetrating the application layer through scaling laws, test-time compute, reasoning with tool use, and inter-agent communication, creating intense competition in the application layer.AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote
- Pre-training scaling is slowing down because 9-10 orders of magnitude of progress since AlexNet means most low-hanging fruit has been picked, requiring research breakthroughs like reasoning, synthetic data, tool use, and AI scaffolding to continue intelligence scaling.AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote
- Anthropic's Model Context Protocol (MCP) created a strong ecosystem and network effects enabling agentic tool use, and Sequoia is excited about its potential to accelerate tool use adoption.AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote
- Early work in tool use originated from the computer vision community because before large language models could process images, the only option was for LMs to generate function calls that could manipulate images (generate, detect objects, etc.).What's next for AI agentic workflows ft. Andrew Ng of AI Fund
- Model Context Protocol (MCP) is a standard for abstracting how tools are made available to the model; MCP servers expose tools from any service provider, allowing the model to act, not merely talk. Examples include OpenAI function calling, Anthropic tool use, MCP tools, and command-line tools like bash, grep, and find.Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems
- Meta's development pattern is to hand-engineer application-specific behaviors (like tool use with Google/Bing) around the base model first—which is brittle and non-general—then progressively bake those capabilities into the model itself to make them general, using each hacked prototype to hone intuition for what to train into the next version.Mark Zuckerberg — Llama 3, $10B models, Caesar Augustus, & 1 GW datacenters
- Startup AI companies face intensifying competition from foundation models that are penetrating the application layer through scaling laws (second scaling law, test time compute, reasoning with tool use, inter-agent communication), requiring startups to differentiate through vertical integration, function specificity, and handling complex problems requiring human-in-the-loop.AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote
- There are four broad design patterns within agentic AI systems: reflection (robust and reliable), tool use (expanding model capabilities), planning (emerging and variable but impressive), and multi-agent collaboration (emerging).What's next for AI agentic workflows ft. Andrew Ng of AI Fund