tool call

Definition

A structured request an AI agent makes to use an external function or service.

A structured invocation issued by an LLM agent to call an external function, tool, or API, whose result is fed back into the model's context.

Also called: tool calls, tool use

Mentioned in 24 episodes

1. 076
   Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
2. 072
   A Robot Made Graphene Without Help, And Caught Itself Hallucinating
3. 071
   When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
4. 066
   Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
5. 063
   Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
6. 059
   Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
7. 057
   How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
8. 047
   When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
9. 046
   When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
10. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
11. 040
    Two Frozen Models Learn to Whisper: Coupling Through Hidden States
12. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
13. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
14. 034
    Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
15. 029
    Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
16. 021
    Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
17. 020
    The Compliance Gap: Why AI Says Yes and Does No
18. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
19. 014
    Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
20. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
21. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't
22. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
23. 002
    An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light
24. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related concepts