tool call

Definition

Plain language

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

Also called: tool calls, tool use

Why it matters: Tool calls are how LLMs reach beyond their training data to take real actions, and their correctness is central to every agent's reliability.

For example, an agent answering 'what's the weather in Tokyo' issues a tool call to a weather API with city='Tokyo' and uses the returned JSON to compose its reply.

Heard on the show

“… question: does the reasoning actually match the state, and do the reasoning, the action, and the tool call all line up? …”

Mentioned in 50 episodes

1. 189
   Why Phone Agents Ace the Test and Crash on Your Actual Phone
2. 187
   An 8-Billion Agent That Beats Models 80 Times Its Size By Looking Things Up
3. 184
   An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
4. 183
   Why You Can't Fine-Tune Foresight Into an AI Agent
5. 181
   How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
6. 175
   One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
7. 168
   When Turning Experience Into Code Makes Your AI Agent Dumber
8. 167
   How Teaching an AI to Predict, Not Act, Made It a Better Actor
9. 164
   The Summarizer That Quietly Deletes Your Agent's Safety Rules
10. 162
    The Empty-Lake Proof: Why More Rollouts Stop Helping Reasoning Models
11. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
12. 144
    When an AI Agent Just Copies Its Tool — And Bigger Models Copy More
13. 126
    How Coding Agents Can Mine Their Own Failures Into a Self-Targeting Curriculum
14. 125
    AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
15. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
16. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
17. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
18. 109
    An AI Got Caught Reading the Answer Key, And Why That Catch Matters
19. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
20. 097
    Same Tokens, Same Cost, Wildly Different Results: What Actually Scales in AI Agents
21. 096
    How Treating an AI Agent's Execution Like Git Recovers a Coordination Penalty
22. 094
    Chain-of-Thought Monitoring Fails Across Languages, and Worst Where It's Needed Most
23. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
24. 088
    Two Levers for Self-Improving AI: When Rewriting Code Isn't Enough
25. 082
    Training a Deep Research Agent on 8,000 Synthetic Tasks: The Rubric Tree Trick
26. 080
    How a Two-Agent Trick Unlocked Large-Scale Training for Computer-Use Agents
27. 076
    Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
28. 072
    A Robot Made Graphene Without Help, And Caught Itself Hallucinating
29. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
30. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
31. 063
    Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency
32. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
33. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
34. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
35. 046
    When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
36. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
37. 040
    Two Frozen Models Learn to Whisper: Coupling Through Hidden States
38. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
39. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
40. 034
    Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
41. 029
    Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
42. 021
    Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
43. 020
    The Compliance Gap: Why AI Says Yes and Does No
44. 016
    Why Your Coding Agent Stalls While the GPU Runs Hot
45. 014
    Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
46. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
47. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't
48. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
49. 002
    An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light
50. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related concepts

Related terms