AI product
Hyperagent is an AI agent platform presented by Airtable founder Howie Liu that deploys a fleet of agents to research, draft, build, deliver, and maintain outputs such as websites, videos, presentations, documents, and dashboards using an organization's data, tools, and working style. Agents run in dedicated computing environments with access to real browsers, shells, files, and connected software; their execution can be inspected as searches, decisions, and generated artifacts. The platform supports always-on agents with scheduled or heartbeat wake-ups, agent-to-agent orchestration, human approval steps, and learning through generated memories and skills. Agents can be invoked from Slack, email, or Telegram, through webhooks, or on a schedule, and are managed from a central command center.
4 uses taken from transcripts — each links to the moment in the video.
A team of agents that maintains open-source projects by labeling and reproducing issues, finding fixes, and opening draft pull requests. It works around the clock and only involves a human when a merge needs approval.
An AI agent platform that lets users create persistent, autonomous agents for tasks such as web research, lead generation, personalized websites and sales pages, outreach, marketplace monitoring, marketing, and business operations. Agents can browse the web through virtual computers, use tools, run on schedules, coordinate with sub-agents, and produce finished artifacts such as web pages, dashboards, and maps.
A platform for building teams of AI agents that can create marketing assets, conduct research, write code, open pull requests, and route questions to the right people. Its Workspaces feature lets teams share agents, skills, and memories while allowing agents to hand off jobs to humans.
An agent platform from Howie Liu (within Airtable) that lets users employ always-on agents with heartbeat wake-ups, agent-to-agent orchestration, human approval steps, and agents that learn from feedback — demonstrated running a landscaping business end to end. Agents run in a sandbox VM where they can write code and manipulate files.
4 in the library.