Subagents are one of the most useful additions to the Claude Code / Claude Agent ecosystem: they let you break complex workflows into smaller, specialist AI “teammates”, preserve main-thread context, and safely limit tool access. This article explains what subagents are, how to create and invoke them (CLI, filesystem, and SDK), the design principles you […]
Claude Haiku 4.5 landed as a deliberate play in the “fast, cheap, still very smart” lane: Anthropic positioned it to give Sonnet-level coding and agentic performance at substantially lower cost and with faster latency, making it an attractive choice for subagents and high-throughput tasks. This makes Claude Haiku 4.5 ideal when you want a model […]
In October 2025 Anthropic launched Claude Code on the web and mobile support, positioning it as a direct competitor to other cloud coding agents and making agentic workflows accessible to Pro and Max subscribers without a terminal., bringing its agentic coding assistant out of the terminal and into an in-browser experience that can clone your […]
Claude’s new Skills feature—recently rolled out by Anthropic—lets teams and developers teach Claude repeatable, sharable capabilities: think of compact, versioned “toolkits” (folders with instructions, scripts, and assets) that let Claude reliably perform domain-specific tasks such as generating brand-aligned slide decks, producing Excel workbooks with formulas, or safely executing small code snippets. This article explains what […]
Anthropic this week unveiled Claude Haiku 4.5, a latency-optimized “small” member of its Claude 4 family that the company says delivers near-frontier reasoning and coding performance while running dramatically faster and cheaper than its mid- and top-tier siblings. According to Anthropic, Haiku 4.5 matches much of the practical developer performance of the company’s Sonnet model […]
Agno has been evolving rapidly into a production-grade AgentOS—a runtime, framework and control plane for multi-agent systems—while CometAPI (the “all models in one API” aggregator) announced official support as a model provider for Agno. Together they make it straightforward to run multi-agent systems that can switch between hundreds of model endpoints without rewriting your agent […]
Anthropic’s Claude Sonnet 4.5 arrived as a focused update for coding, agentic workflows, and “computer use” — the kinds of tasks that require long context, tool-handling, and robust safety controls. At the same time, modern developer IDE- and code-assistant platforms like Cursor let you plug in the best available models and run them directly over […]
OpenAI’s Sora 2 has changed how creators think about short-form video: it generates moving, lip-synced, physically realistic clips from text and images, and — crucially — gives developers programmatic access via an API (with a higher-quality “Pro” tier). Below I will bring a guide: what Sora 2 is, the API parameters you must care about, […]
GPT-OSS is unusually well-engineered for accessibility: the gpt-oss-20B variant is designed to run on a single consumer GPU (~16 GB VRAM) or recent high-end laptops using quantized GGUF builds, while gpt-oss-120B—despite its 117B total parameters—is shipped with MoE/active-parameter tricks and an MXFP4 quantization that lets it run on single H100-class GPUs (≈80 GB) or on […]
DeepSeek released an experimental model called DeepSeek-V3.2-Exp on September 29, 2025, introducing a new sparse-attention mechanism (DeepSeek Sparse Attention, or DSA) that targets much lower inference costs for long-context workloads — and the company simultaneously cut API prices by roughly half. This guide explains what the model is, the architecture/feature highlights, how to access and […]
