DAPPOS launches xBubble, low‑prompt AI agent

DAPPOS launched xBubble, a low‑prompt AI agent designed to convert short user requests into finished deliverables such as images, videos, websites, documents and scheduled tasks. The company described the product as a way for users to state a goal and receive a completed output without learning prompt engineering or assembling AI toolchains.

xBubble is built on two core systems. Bubble Engine generates and tests task‑specific standard operating procedures (SOPs). It uses AI coding agents to produce multiple solution variants, assemble test harnesses, combine candidate models and tools, and evaluate outputs against examples and quality criteria. The highest‑performing approach becomes a reusable SOP that the system can dispatch for similar requests.

Bubble Pilot is the runtime dispatch layer. It reads a user’s request, identifies the task type and routes it to a matching SOP. If no SOP fits, Pilot falls back to a general‑purpose agent. Recurring fallback patterns are flagged so Bubble Engine can develop dedicated SOPs for those tasks.

xBubble ships with more than 10 core capabilities organized into two modes. Bubble Computer is an end‑to‑end project workspace: when Pilot detects multi‑step work, the platform spins up a sandbox, loads specialized skills on demand and coordinates steps such as research, drafting, asset generation and verification within a single run. Bubble Personal runs in a local‑environment mode that can access local files, browsers, apps and schedules to manage calendars, organize photos or collect market data overnight. Personal uses sandboxed execution: installations and system‑level changes occur inside cloud containers that are destroyed after the task finishes, while only explicitly authorized actions execute on a user’s machine.

The product supports a fast mode for simple daily tasks and a work mode that uses tested SOPs for stable, professional results. Supported task types include voice dictation, text‑to‑speech, talking avatars, deep research, slide and document creation, fact checking, scheduled tasks, poster, image and video creation, and website development.

In a statement, the DAPPOS team wrote, “Powerful AI no longer requires users to learn AI. xBubble inverts the relationship. We have AI learn AI, and we have AI use AI, so users don’t have to. The system evolves faster than any user can, and leverages AI more effectively than they can.”

xBubble is available now. DAPPOS plans to expand Bubble Engine’s coverage to handle more complex tasks; the company expects a larger share of requests will be routed to task‑optimized execution paths, which should reduce response times. The platform keeps heavy compute and operations deemed risky in the Bubble Cloud while returning clean results to users.

DAPPOS is an AI startup focused on lowering the barrier to advanced AI tools for general users and professionals. The company has raised more than $20 million from investors including Polychain, Binance Labs, Sequoia China, IDG Capital and OKX Ventures.