Publish the rule for what can ship.
Without it, done means whatever the agent says it means.
OrgX turns checks, references, and judgment into one versioned rule that verification runs against.
Run the same artifact against the same rule.
Compare the held version with the repaired version and inspect the exact check that changed the verdict.
Govern every AI action without slowing down.
One unsupported guarantee prevents this version from shipping.
The same rule governs each version.
Publish the rule
Agents and reviewers use one named version of done.
Checks, references, judgment, and ship rules resolve to one bar.Name the failed claim
A hold explains what failed and what evidence is missing.
The operator can repair the work instead of debating a score.Keep the earlier verdict
A later edit cannot rewrite the rule that governed an earlier artifact.
The artifact retains the quality-bar version used at verification.The next session receives objects, not a summary.
- Checks
- The measurable floor for the work.
- References
- Examples that make judgment inspectable.
- Version
- The exact rule used for verification.
Before you start
Still deciding? Bring one piece of agent work to a 30-minute review.
Book a proof reviewWhat does OrgX do?
OrgX is proof for AI-delivered work. Claude Code, Codex, Cursor, and OpenClaw write to one shared record, so a decision keeps its provenance (the sessions, the clients, the evidence) no matter which agent picks the work up next. Capture depth still differs by client today.
Can we control what agents are allowed to do?
Yes. Each initiative runs in manual, gated, or autopilot mode, and each connector is set to allow, ask, or deny. Sending, spending, deploying, merging, and deleting always stop for a person in every mode. Checking finished work against a published quality bar is in beta.
Do we have to switch AI tools?
No. OrgX connects through MCP and plugins to Claude Code, Codex, Cursor, ChatGPT, and OpenClaw. Setup differs by client; the record is shared across all of them.
What counts as “accepted” work?
An agent reporting done is a claim, not an approval. An agent can never approve its own work: that floor is enforced in code and fails closed. Work counts as accepted when an owner records the ruling.
Can someone outside OrgX verify the work?
Agent Work Receipt v0.1 is an open, account-free format. A receipt carries its evidence and integrity hash, and it can be checked with the public validator without an OrgX login.
What does it cost to start?
The Free plan covers one active initiative. Paid plans start at $98 a month. If you want us to run it with you first, two scoped episodes on one of your real deliverables cost $250.