What Is Agentic AI? A Complete Guide
Agentic AI is AI that acts, not just answers. It plans, uses tools, and executes goals on its own. A clear guide to how it works, real examples, and the risks.
Rerun Blog12 min read
tool calling
254 stories
Building a Chat Agent with Function Calling
Level: Advanced Time to complete: 20 minutes Components Used: InMemoryDocumentStore, SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder, InMemoryEmbeddingRetriever, ChatPromptBuilder, OpenAIChatGenerator, Agent Prerequisites: You must have an OpenAI API Key and be familiar with…
Haystack by deepset10 min read
API discovery platforms and marketplaces for AI agents in 2026
A researched map of how AI agents and the teams building them find and call APIs at scale outside of MCP: public marketplaces, unified-API platforms, and OpenAPI-driven agent tool generation, and where each one stops short of governing who gets to call what.
Elva Blog14 min readJSON mode explained: when schema enforcement beats prompting
JSON mode vs structured output: how constrained decoding works, when 3% failure rates become a real cost, and which enforcement approach your pipeline needs.
LLMTest Blog5 min read
Granite 4.2 LLMs: How They're Built
TL;DR: Granite 4.2 is our first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. These models are post-trained from Granite-4.1 base models.
Hugging Face Blog21 min read
Granite 4.2 brings native reasoning to enterprise agents
IBM’s new open Granite models are designed for agentic AI, combining reasoning, tool use, coding, instruction following, and speech capabilities.
IBM Research Blog5 min read
Hybrid AI in Word with OpenRouter Free Models: Complete Setup Guide
Last Updated on August 25, 2026 Use Free AI Models Directly in Microsoft Word What if you could use multiple AI models directly from Microsoft Word without being […] The post Hybrid AI in Word with OpenRouter Free Models: Complete Setup Guide appeared first on GPTLocalhost.
GPTLocalhost Blog6 min read
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe.
Import AI (Jack Clark)18 min read
The CPU Comeback Is Upon Us
Earlier this year, leaders at Amazon Web Services delivered a new mandate to their engineers: They need to conserve CPU cycles at all costs. AWS has reportedly experienced an explosion in wait times for CPU server capacity as AI workloads strain the company’s cloud infrastructure.
IEEE Spectrum AI6 min read
Crusoe is now a Pydantic AI model provider
Crusoe Managed Inference is a native model provider in Pydantic AI. One model string gives you streaming, tool calling, and structured output across the open model catalog.
PydanticAI Blog5 min read
Best AI Models for Agentic Tool Use - August 2026
TL;DR Claude Opus 5 tops independent SWE-bench Verified tracking at 96% - though Anthropic's own launch materials skip that benchmark entirely for custom evals Qwen3.
Awesome Agents Newsletter Blog11 min readCheapest LLMs for function calling in 2026: ranked by reliability
GPT-4o-mini, Gemini 2.5 Flash, DeepSeek V4-Flash, and Haiku 4.5 ranked on schema errors, retry costs, and multi-turn reliability for function calling in 2026.
LLMTest Blog8 min read
Hooks in the Claude Agent SDK: every event, measured
The programmatic hooks you pass in options.hooks, not the shell hooks in settings.json — and the difference matters, because by default both fire in the same run. We registered a callback on all 31 events and ran it until we had the thing nobody publishes: the measured firing order.
Backgrind Blog19 min read
Top 5 Open Weight Models That Matter to Developers in 2026
Explore the best open weight models for coding in 2026. Compare Kimi K3, GLM 5.2, DeepSeek V4 Pro and Flash, and MiniMax M3 across benchmarks, pricing, model size, and developer use cases.
Cline9 min read
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure.
Microsoft Research Blog7 min read
Run DeepSeek V4 Flash locally or in the cloud (US-hosted)
DeepSeek V4 Flash is now available locally and in LM Studio Bionic, hosted on US-based servers with Zero Data Retention by default.
LM Studio Blog3 min read
Building an agent on the Claude Agent SDK
Claude Code as a library — and the field almost everyone misreads. We ran the same agent twice: allowedTools is an auto-approve list, not a sandbox, and the first run called Bash despite Bash not being on it.
Backgrind Blog11 min read
Under the Hood: Serving Kimi K3
How DigitalOcean served Kimi K3 on day 0: GPU selection (B300/MI350X), vLLM tuning, and the OpenAI-compatibility fixes for tool calling, streaming, and reasoning.
DigitalOcean Blog14 min read
Showing 180 of 254 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts