Multiplayer agentic engineering — Arjun Singh, Superconductor
Superconductor uses AI agents that participate in meetings and Slack channels to capture ideas directly from conversations without requiring manual note-taking about what needs to be done.
A bot listened to a four-hour meeting, identified a customer request for clearer criteria for when work is complete, opened an issue itself, and implemented the suggestion. The company runs the agents in isolated cloud environments where they cannot accidentally access production databases, and people from support and growth can trigger actual work without needing a developer environment. Over one month, they used 10.5 billion tokens and ran 3,300 agent sessions for approximately $10,000.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago