Tag archive
Dal prompt singolo ai grafi di lavoro, fino a sistemi che ottimizzano se stessi: una mappa pratica...
Qwen3-14B vs Llama-3.2-3B on real function-calling tasks. JSON validity, schema correctness, multi-turn handling. The smaller model won on cost and reliability; the bigger model won on accuracy. Here are the numbers.
The shift from generating the whole function to an agent that reads, searches, edits, and runs with tools: the ReAct loop and why the agent builds its own context instead of receiving it in the prompt.
Stop parsing prose with regex. Learn how to make an LLM return clean JSON on a schema you control, and how to let it call your functions safely with t
Spring AI released a fix on 21 August for a bug where a tool absent from the request could still be...
Small language model vs LLM: Bengaluru's Kinetic-4B beats Claude Haiku 4.5 at tool calling with 82.33% accuracy and 2.5x lower p95 latency.
ADS required capability names to contain a dot. OpenAI, Anthropic and Google all reject a dot in tool function names. No conformant name was usable as a tool. How we found it and what ADS-2 changed.
Master tool calling in Spring AI to create applications that can dynamically execute functions and interact with external services.
From actual runaway logs of tool-calling agents, such as opening the same page 5 times in 3 seconds or automatically creating files in response to streaming lyrics, we’ve organized 7 guard implementation patterns that prevented recurrence. These include same-call limits, explicit request gates, precedent prompts, and billing safety nets, all summarized in a copy-paste format for easy implementation.
The Power of API Integration An agent without APIs is limited. Connected to APIs, it's...
Six patterns for reliable AI agent tool calling in 2026, with a side-by-side Anthropic vs OpenAI function-calling comparison and strict-mode rules.
This week, AI Gateway became the de facto routing layer for serious agentic workloads—Meta and OpenAI...