tool calling
technique judged 99% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2024-W09 | 1 | 1 |
| 2024-W38 | 1 | 1 |
| 2024-W53 | 1 | 1 |
| 2025-W08 | 1 | 1 |
| 2025-W09 | 1 | 1 |
| 2025-W16 | 1 | 1 |
| 2025-W17 | 1 | 1 |
| 2025-W18 | 1 | 1 |
| 2025-W19 | 1 | 1 |
| 2025-W20 | 1 | 1 |
| 2025-W21 | 1 | 1 |
| 2025-W31 | 1 | 1 |
| 2025-W38 | 1 | 1 |
| 2025-W47 | 1 | 1 |
| 2026-W04 | 1 | 1 |
| 2026-W06 | 1 | 1 |
| 2026-W11 | 12 | 1 |
| 2026-W13 | 1 | 1 |
| 2026-W20 | 1 | 1 |
| 2026-W22 | 1 | 1 |
| 2026-W25 | 2 | 2 |
| 2026-W29 | 1 | 1 |
| 2026-W31 | 1 | 1 |
| 2026-W33 | 1 | 1 |
| 2026-W35 | 1 | 1 |
| 2026-W37 | 1 | 1 |
| 2026-W39 | 3 | 2 |
| 2026-W40 | 16 | 6 |
| 2026-W41 | 4 | 3 |
In their words
It achieves 3,000+ equivalent FPS at 512 dimensions and integrates with LLM agents via LangChain tool calling.
AI Agents with Function Calling: Build Tools LLMs Can Use Create AI agents that can execute code, search the web, and call APIs — using function calling.
@CodingGarden built a tool-calling chatbot with no LLM at all and handles this inside the option list: one option says "no device or room is mentioned at all", another says "more than one tool call can satisfy this request", and either one triggers a follow-up question instead of an action.
Local Indexing to reduce tool calling and token usage
I use recordings only for a couple of complex tool-calling flows.
The current paradigm of autonomous agents is based on Function Calling.
Examples include tool definitions, workflow graphs, prompt templates, function-calling policies, approval rules, and orchestration logic.
Tool calling and structured outputs introduce another set of differences and deserve separate comparisons.