Manus co-founder Zhang Tao describes agent-run engineering and AI spending
Overview
Manus co-founder and product partner Zhang Tao says the company runs its engineering, product and marketing work on its own agent product.
Engineers send Slack requests directly to agent sessions, and one person handles more than ten requests in parallel. He says the company built a single code entry called Manus-mono, paired with a document written for AI, so one builder and one agent can finish a requirement across frontend, backend and mobile. Humans still approve releases.
Zhang Tao also reports that the mobile team of seven runs two products and four apps, and that AI spending averaged over $10,000 per person in September, with a few people spending $70,000 to $80,000 in a month. He argues per-person cost will fall as models improve. These figures are self-reported in his article and have not been independently verified.
Written by AI from the articles below · updated Oct 27, 7:55 AM ET
Check the sources:
Developments
2 developments
- Oct 27, 7:51 AM ET · 1 articleManus co-founder explains how it restructured engineering around one shared agentmeng shao: Manus co-founder explains how it restructured engineering around one shared agent
- Oct 26, 7:12 AM ET · 2 articlesManus co-founder describes how AI-native teams run work with agentsGeekPark: Manus shares how its internal teams run on its own agents and AI spending
Article timeline
The articles in this story. Times are ET.
meng shao@shao__mengXManus co-founder explains how it restructured engineering around one shared agentAIManus co-founder Zhang Tao describes how the company built Manus-mono, a single entry point with a documentation file that gives its AI agent the repository map, development standards, and release process. The article says one builder with one shared agent context can now complete a requirement across frontend, backend, and mobile, reducing a flow of about five people and five agents to one builder and one agent, with humans still approving releases.

- GeekParkNewsManus shares how its internal teams run on its own agents and AI spending
AIGeekPark reports on an article by Manus co-founder and product partner Zhang Tao describing how the company uses its own agents internally. He says the mobile team of seven runs two products and four apps, and that AI spending averaged over $10,000 per person in September. The article follows the launch of Manus 2.0 and a funding round of over $500 million by parent company Butterfly Effect.
meng shao@shao__mengXManus co-founder describes how AI-native teams run work with agentsAIManus co-founder Zhang Tao describes how the company uses its own agent product to reorganize engineering, product, and marketing work. The article says engineers send Slack requests directly to agent sessions, with one person handling more than ten requests in parallel. It also reports that the company averages about $10,000 in AI spending per employee and that the author argues this cost will fall as models improve.
Heat Trend
- Current comparable heat
- 10
- Peak comparable heat
- 19Oct 27, 8:00 AM ET
- Change in past 24 hours
- -32%
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.