Acc.VIAutonome — no-code AI-agent deployment platform

AI-agent frameworks like ElizaOS demand Docker, Kubernetes, and YAML fluency to deploy. Autonome had to let non-technical operators configure and ship persona-based agents from a browser — built from zero as a new product surface inside the Wizard frontend.

• Founding frontend engineer — built and supported the UI flows for configuring AI agents, including response tuning and input configuration to tailor how agents respond to users.
• Shipped the framework-discovery gallery (AgentFrameworksSection) — a multi-row Swiper carousel adapting to viewport and template count, with dynamic featured-template assignment so new frameworks like AgentKit-TS can be promoted without component changes.
• Wired up the Eliza framework end-to-end in the UI — character-schema capture, settings-form validation, and a BNB-flavoured template with a custom Yup validator for the agent's web3 private key, catching invalid input before it reaches the runtime.
• Contributed across the new-agent deployment flow and the per-agent metadata editor so operators deploy and manage agents without touching Docker, Kubernetes, or YAML.
• Improved the environment-variables dialog with select-field support so framework authors can declare env vars that pick from a fixed set — cutting whole classes of misconfiguration.
• Tightened the shell with floating Telegram and FAQ buttons, and reinforced cross-cutting design-system primitives (FormSelectField clearable prop, DateRangePicker granularity) consumed across the Wizard surface.

• Live at apps.autono.meme — operators go from framework choice to a chat-ready agent in roughly five minutes.
• New agent frameworks can be promoted into the gallery without component changes.
• Validation at the form boundary keeps invalid agent configuration out of the runtime entirely.