Research
Facts before opinions.
- xing-researcherRead-only
Facts vs inference — labels which is which.
- xing-invest-complianceRead-only
Research, not advice.
- xing-security-privacyRead-only
Secrets and policy.
How XingAI builds
One dispatcher assigns work. Fourteen specialists report back.
XingAI's websites are built and maintained by a small human team plus a standing team of 15 AI agents. The humans set direction and make the final calls. The agents do the research, the checking and — inside narrow limits — the building.
The structure is deliberate: one chain of command, read-only by default, write access kept narrow, and a human OK before anything reaches production. This page is the org chart, published so anyone can see exactly how the work is divided.
Fourteen specialists in five groups. Every card shows what that agent may touch — most can only look.
Facts before opinions.
Facts vs inference — labels which is which.
Research, not advice.
Secrets and policy.
The site as the visitor meets it.
Mobile, states, flow.
EN / ZH / KO, keyboard and accessibility.
Sitemap, links — how pages get found.
Evidence from real usage.
Funnels, experiments.
Topics back to sites.
The only group that writes code.
Confirmed spec only.
Reproduce, then fix.
Measure one bottleneck.
Nothing ships unverified.
Tests, no code edits.
Git only, after OK.
Live site vs HEAD.
Most AI setups hand every agent every tool. Ours does the opposite — least privilege, enforced by structure rather than by trust.
10 of 15
agents are read-only
4
may touch the code repos
1
can run git — only after the founder says OK
The same 15-agent team runs in three independent coding systems — Claude, Cursor and Codex. If one system runs out of quota or goes down, another picks the work up and nothing stops.
On ordinary days the duplication is itself the test: the same task runs in more than one system and the results are compared. We pick tools by measured results, not by loyalty. The same rule runs underneath everything at XingAI — every key role has a second source, and every important number is checked against two.
One team, three systems — Claude · Cursor · Codex
When in doubt, ask XingAI.
A small human team. A standing agent team. Every step checked twice.