Get started

AGH-Chain · agent honesty

Claims, checked against the chain.

An agent that says the report was filed had better be able to point at the filing. Before a reply ships, AGH-Chain checks every claim about the past against the evidence Quox already keeps, and rewrites what it cannot prove with an honest correction.

Included in QuoxCOREFree, self-hosted, nothing to buy.
Guards4Tests behind them300+Silent deletions0

In plain words

What it is, where it lives, when to reach for it

What is it
A check built into QuoxCORE that compares every agent reply's claims with the evidence the platform recorded.
Where do I use it
Inside every agent chat reply, with a corrections ledger on the dashboard's Honesty page.
When would I use it
When an agent tells you something was filed or fixed and you need that claim to be true.
How do I use it
You do not invoke it; replies are checked before they ship, and the Honesty page lists every correction.

QuoxCORE is the free, self-hosted platform underneath this. What is QuoxCORE

What gets checked

Four ways to say prove it.

Nothing is blocked, nothing is silently deleted, and every correction is itself on the record.

01 · promisedA promise is recorded

Say you will email the report, file the task or run the workflow, and a promise row is written the moment the words leave the agent.

promise ledger · en + es

02 · keptA kept promise has receipts

Claim it is done and the chain is asked: is there a matching tool execution since the promise was made? No receipt, no claim: the reply is rewritten to say so.

7 day window · tool receipts

03 · attributedAnother agent said it

Quote a colleague and the envelope chain is searched for that agent actually saying it in this conversation. Unbacked attributions do not survive.

AEE envelopes · 2 hour window

04 · cross-orgAnother organisation did it

Name a counterparty and it must be an admin-approved trust root that was genuinely present in the chain.

trust roots · beta

When it runs

Triggered by every reply.

No one invokes it. When the honesty chain is on, every chat reply, from CommanderQ or any specialist agent, passes through the guards on its way out: claims checked in the last second before you read them. Workflow, MCP and CLI paths do not pass the guards yet, and this page will say so until they do.

chat dispatch · every turn · on by flag

The real thing

An agent that will not invent.

Asked for a list it had no tool to fetch, the orchestrator said so, showed its routing, and offered real paths instead. It would have been easy to invent something plausible; instead this screenshot embarrassed us into shipping the missing tool the same afternoon. That is the whole culture in one frame: no receipts, no claim, and honest refusals get gaps fixed.

refused honestly · tool shipped same day

CommanderQ declining to invent a list of organisations it has no tool to enumerate in this session, with the model fallback-routing chips visible

What happens on failure

Corrected in the open, never blocked.

An unproven claim does not kill the reply. The sentence is rewritten with an honest correction prefix, the original is preserved beside it, and the verdict is written to the evidence ledger. You see what the agent wanted to say, what it was allowed to say, and why.

result_before_chain · chain_verification_applied

The substrates

It checks against what already exists.

No new bureaucracy. The guards read the promise ledger, the AEE envelope chain and the VOLT tool execution record: the same evidence Quox keeps for every run anyway. Honesty enforcement is a reader of the chain, not another chain to maintain.

promise ledger · written at speech time

AEE envelopes · who said what, in which conversation

VOLT events · what actually executed

Kept score

Honesty has a scoreboard.

Every agent carries its record: claims checked, corrections issued, promises kept. Inside your org it is a leaderboard; outside, nothing leaves unless you opt in, and the public aggregate is noise-protected so small numbers cannot identify anyone.

per-agent record · opt-in public stats · noise-protected

Straight answers

What is proven, what is not yet.

Proven

All four guards, bilingual, behind three hundred plus tests and reproducible demo transcripts, enforced at the chat dispatch chokepoint.

chat path · flag-gated

Not yet

Workflow, MCP and CLI paths do not pass through the guards today, and there is no production soak number to quote: when there is one, it will be quoted.

no invented numbers

Coming

Cryptographic cross-org verification is designed as a drop-in upgrade to the existing check, and a compliance profile will run every guard fail-closed.

ed25519 · compliance profile

Ready when you are

Agents that cannot get away with it.

AGH-Chain ships with QuoxCORE and reads the evidence you already keep.