We let an AI agent buy its own GPU compute 18 times. It never once walked away empty-handed.

Описание и применение

AI‑агент без участия человека покупал GPU‑вычисления 18 раз, автоматически переключаясь на резервного поставщика при отказе RunPod, без потерь и с минимальными расходами.

Задача

Automating GPU compute procurement without human intervention while ensuring reliability and cost efficiency.

Результат

The AI agent completed 18 GPU compute purchases autonomously, with 89% of first attempts failing but automatically rerouted, achieving zero dropped requests and a total cost of $0.88.

Рабочий процесс

• 1. Agent formulates compute request.
• 2. Agent submits payment in USDC on Base.
• 3. RunPod processes request; if unavailable, agent reroutes to backup provider.
• 4. Compute instance is provisioned and returned to agent.
• 5. Agent logs success and repeats until 18 purchases are completed.

Доказательства

18 real purchases, 18 completed jobs • 16 of 18 (89%) hit a failed first attempt — RunPod couldn't fulfill — and were automatically rerouted to a backup provider • Zero dropped requests • $0.88 in real settled payments

Источник