Conductor

Play with the Future

Conductor is building a new way to create, verify, and resolve claims on the internet.

How It Works

1. Make a Claim

You provide a claim and our bot disambiguates it and identifies authoritative ways to verify the claim.

2. Generate a Runbook

If it meets required criteria, we create a verification runbook for the claim.

3. Verify On Demand

Our agent executes the runbook automatically on the resolution date (or on demand) and resolves to an outcome with cited evidence.

4. Attest Onchain

Once resolved, the agent packages the outcome, cited evidence, and reasoning into a signed onchain attestation on Base.

5. Make something happen

Because the attestation lives onchain, any smart contract or app can consume it instantly—enabling prediction market resolution, conditional payments, bounties, and use cases we can't yet imagine.

FAQ

What if the AI agent gets it wrong?

It can. Agents can make mistakes and hallucinate. We’re building this to explore ways to mitigate these risks and make agent verification extremely reliable.

Can the rules change after a claim is created?

No.

What happens if the data source goes down?

The agent returns INCONCLUSIVE. Runbooks can specify fallback sources, but if none are reachable, the system won't fabricate a result. You can re-run verification later when the source is available.

Why Base and not another chain?

Low gas costs, fast finality, and EVM compatibility. The contract is a simple registry — it can be deployed on any EVM chain.

What can I build on top of this?

We are building this to find out.