Realtime AI News
Spider Networks launches KUKURI, a pick-and-edit rule library for AI agents
Spider Networks has launched KUKURI - Agent Rules Hub, a web service that packages ready-made instruction sets for AI agents and chat-based tools, letting users pick, edit on-site or stitch together rules instead of writing prompts from scratch. The library spans coding, design, sales, customer support and education, ships in eight languages, and starts at $7 a month after a free tier.
Spider Networks has launched KUKURI - Agent Rules Hub, a web service that provides instruction libraries for AI agents and chat-based AI tools, according to IT Brief Asia. The product is aimed at anyone who wants more control over how an AI system responds and carries out tasks, not just at software developers.
The core idea is organisation by purpose. Users can take an existing instruction as it is, edit it directly on the site, or pull fragments from several instructions to build a version suited to their company or personal workflow. That assembly approach lowers the barrier compared with writing a full prompt or system instruction from zero.
The library leans heavily on non-technical work. Reported examples include website design, sorting incoming email, writing sales emails, drafting responses to customer complaints and producing notices for parents from schools, alongside programming and other technical tasks. Any instruction can be used unchanged or adapted to a specific case.
Delivery covers both kinds of tooling. Finished instructions can be downloaded as files for Claude Code, Codex and Antigravity, while users of ChatGPT, Gemini, Claude and Muse can copy the text into each product's settings. That positioning as a model-agnostic rule layer means KUKURI does not depend on a single vendor.
Commercially, the service is available in eight languages — Japanese, English, Chinese, Spanish, German, Portuguese, French and Korean — with a free plan and paid plans starting at $7 per month. For a tool aimed at office workers and educators, that sits well below most enterprise AI software.
Spider Networks frames the launch around agents moving beyond engineering. It points to the spread of Claude Code and Codex in software development and to a newer wave of personal AI agent products that create entry points for non-technical users. The friction it targets is real: many people do not know what belongs in an instruction file, or end up repeating the same prompts every time they start a task.
CEO Takaya Tanoura said the aim was to lower the barrier for people new to configuring AI systems, arguing that even beginners can steer agents and ChatGPT toward their own purposes simply by choosing behaviour rules. He also noted that the quality of these instructions strongly affects how well the AI performs, yet deciding what to write is not easy.
Two items remain on the roadmap. Spider Networks is considering letting users' own agents connect directly to KUKURI through MCP to search, retrieve and edit instructions, and it is weighing a business plan for larger-scale corporate use. If the MCP link ships, KUKURI stops being a template shop and becomes a rule backend agents can call.
The launch reflects a shift in the AI software market from model access toward defining reusable behaviour. As more organisations put agents into routine processes, the advantage goes to whoever can make rules stable, maintainable and handover-ready — the difference between experimenting with AI and embedding it in the business.
Why it matters
KUKURI turns instruction-writing into a buyable, editable asset aimed squarely at the configuration gap that opens when agents move from engineering teams into office work. If the MCP integration lands, it becomes a callable rules layer rather than a prompt-template site.
Nearby Updates
All11/19, 08:42
Nadella explains why Microsoft asked 60,000 employees to leave: reorganization, not replacement
Microsoft CEO Satya Nadella said the buyouts offered to 60,000 employees in October were meant to give people agency during an AI-first reorganization, not to replace engineers with AI. He pointed to an 11-person Cowork team that builds a software factory rather than the product itself.
11/19, 08:26
1,500 entries and 20-plus hour-long films: an AI film contest puts the one-person crew on stage
RunningHub's global AIGC long-form film competition has wrapped, drawing more than 1,500 entries, over 80% of them series or feature-length projects and more than 20 running past 60 minutes. The grand prize winner took 1 million yuan in cash, while a finalist has entered theatrical development.
11/19, 07:45
Nadella: Much of Critical Infrastructure Is 'Unpatchable' as AI Raises the Stakes
Speaking at The New York Times' DealBook Summit, Microsoft CEO Satya Nadella said much of America's critical infrastructure runs on firmware and cooling equipment that cannot be patched yet sits on the internet. He downplayed the recent Outlook outage and warned that AI both finds vulnerabilities faster and shrinks the window between a fix shipping and an exploit landing in the wild.
11/19, 07:17
Nadella Says He Still Has Confidence in Nvidia After Huang's Exit
Microsoft CEO Satya Nadella said he remains confident in Nvidia after Jensen Huang stepped down last week, praising interim chief executive Colette Kress as someone he has known for years. He called Huang's departure tragic and said his contacts inside the company are unchanged.