From verifiable intelligence to an agent economy
Five phases, ordered by dependency rather than by quarter. Each one builds the primitive the next one needs, which is why there are no dates on phases 4 and 5: a date there would be fiction. The Now / Next / Later bands say how far out something is without inventing one.
One rule governs the deliverables: a thing is marked shipped only when it has been run end to end, never when the code merely exists. That is why phase 1 is still in progress, even though this repository already implements most of it.
Verifiable intelligence
The core this repository already implements: several specialist agents read the same curated corpus, the runtime records what was actually retrieved, evaluation is deterministic, and the merge keeps disagreement instead of averaging it away. The mechanism runs end to end. What it is worth is the open question, and this phase is not finished until that is measured, which is why it is still marked in progress rather than complete.
- Multi-agent orchestration and an explicit job lifecycleshipped
- Datanet integration through one provider-neutral adaptershippedUpstream limit and datanet filters are advisory, so the adapter enforces both locally: a datanet-scoped job cannot draw evidence from a datanet it did not select.
- Evidence runtime: provenance the model cannot authorshippedClaims cite an index into what the runtime retrieved. A reference to something never retrieved is dropped and the claim flagged unsupported.
- Deterministic evaluation across five dimensionsshipped
- Consensus that preserves disagreement, scaled by corroboration breadthshipped
- Agent registry, with reputation stored as replayable snapshotsshipped
- Intelligence reports and the explanation chainshippedVerdict, claims, and the curation behind each source. Evidence and reasoning reliability are reported separately; outcome reliability stays null until predictions resolve.
- Public API, typed SDK, and an in-app playgroundshipped
- Tenancy: per-account keys, reads scoped in the queryshipped
- Budget guard: spend reserved atomically before executionshippedReservation is written before the work runs and reconciled against actual cost afterwards, so no action can outrun its budget.
- Autonomous operator loop: job discovery on a cadenceplannedThe strategy engine exists and is unit-tested, but nothing runs it: no worker ticks it, no endpoint exposes it, and no operator has ever taken a job on its own. It was previously listed as shipped, which the rule at the top of this page does not allow.
- Migrations, replacing schema pushshippedA versioned migration history with deploy and status commands, so a release has a safe path forward and a way back.
- A cohort bound to real models rather than the deterministic providerin progressEvery agent currently ships bound to a deterministic mock that derives claims from real retrieved evidence. That proves the coordination; it does not prove the intelligence.
- Cohort benchmark: three and five agents against one strong callplannedAccuracy claims need ground truth, so this follows resolution in phase 2. Before then it can honestly report cost, latency, consistency and evidence coverage, but not accuracy.
- Metrics and tracing: cost, latency and failure ratesplanned
- Authenticated reads for permissioned DatanetsplannedThe adapter reads only the public surface today, which is the whole enterprise tier it cannot reach.
Prove that Averis produces intelligence that is more auditable and more reliable than a single-agent answer. This is the product-market fit layer; nothing below it matters until it holds.
Agent reputation
Once intelligence is verifiable, agents can be measured persistently rather than judged one job at a time. Reputation is scored from resolved outcomes and deterministic evaluation, never from capital, and it becomes multidimensional, because an agent strong on smart-contract security may be weak on macroeconomic forecasting.
- The prediction → resolution loop, run for realin progressNo prediction has reached a deadline yet, so accuracy and calibration sit at the neutral prior for every agent. Short-horizon predictions and a matching oracle are what start the clock.
- Agent track record: measured accuracy and Brier scoreplannedDepends on the loop above. Until it runs, reputation is scored on how work looks, never on whether it was right.
- Calibration scored apart from raw accuracyplanned
- Domain-specific reputation rather than one aggregate scoreplanned
- Reputation-weighted consensusplanned
- Agent discovery and routing on measured reputationplanned
- More oracles: price and on-chain resolutionplannedOne oracle exists today, so price and on-chain predictions resolve as UNRESOLVABLE. Honest, but it leaves accuracy sparse.
Answer the question a buyer actually has: which agent can I trust for this, and on what evidence?
Intelligence market
Only once intelligence is verifiable and agents are measurable does a market mean anything: a price without a reputation behind it is a number attached to nothing. This is the phase where intelligence becomes a machine-readable, machine-purchasable commodity, and where Averis stops resembling a conventional AI platform.
- x402 settlement, end to endin progressThe paywall issues challenges today but has never settled a payment, and no on-chain driver exists. Settlement mechanics are proven to the extent that a reward is payable at most once, raced against a real database.
- Capability marketplace: agents publishing services and pricesplanned
- Paid intelligence and agent-to-agent servicesplanned
- Usage-based pricing, by cohort size rather than a flat feeplannedA one-agent job currently costs the same as a five-agent one.
- An on-chain settlement driver, so agents are actually paidplanned
- Open agent registry, selected on measured reputationplanned
- Settlement on Robinhood ChainplannedThe paywall now quotes an eip155 challenge, and the config refuses to start without a chain id, an RPC endpoint and a token contract. What is still missing is the half that moves money: no payment has ever settled, and no driver exists to sign one.
Make intelligence something a machine can discover, price and purchase without a human in the loop.
Prediction economy
Prediction markets enter here and not earlier, and not because they are interesting. Once agents carry reputation and economic activity, a resolved forecast becomes the sharpest available measurement of whether intelligence was actually useful. It is the feedback mechanism the reputation layer is missing, not a product in its own right.
- Structured agent predictions with declared resolution criteriaplanned
- Prediction markets and market resolutionplanned
- Prediction and calibration scoringplanned
- Market-based reputation, fed back into selectionplanned
- Incentivised forecastingplanned
- Forecast aggregation across a cohortplanned
- Averis output published back as a curated datanetplannedResolved predictions and deterministic evaluations are themselves evaluation signal, which turns a one-way read of upstream data into a two-way relationship.
Close the loop between intelligence and reality, so quality is continuously measured against outcomes rather than asserted.
Autonomous intelligence economy
The long-term vision, and deliberately not work for today. Privacy belongs here rather than earlier for the same reason prediction markets belong in phase 4: confidential settlement only becomes meaningful once agents have economic activity worth concealing. An agent’s transaction history otherwise reveals what it buys, who it trusts and what it is watching.
- Agent Passport: portable, inspectable performance historyplanned
- Cryptographic agent identity and portable reputationplanned
- Private agent transactions over a privacy layerplanned
- Confidential service consumptionplanned
- Autonomous treasury: agent wallets, budgets and spending policiesplannedAutonomy does not mean unrestricted financial control. Economic authority stays bounded by policies the operator sets.
- A first bounded-autonomy surface, in paper modein progressA trading automation reads resolved jobs and opens paper positions under a policy its owner set. There is no key column, no wallet the server can sign with, and setting the mode to LIVE returns 501. It exercises the shape of a spending policy, never the money. It is a consumer of the protocol, not part of it.
- Agent-to-agent commerce across networksplanned
Agents become economic participants rather than merely software users: measurable, accountable and bounded.
Why the order is the order
Prediction markets are not in phase 4 because they are interesting. They are there because a market is only a measurement instrument once agents already carry reputation; before that it measures liquidity, not intelligence. Privacy is not in phase 5 because the technology is appealing; it is there because confidential settlement has nothing to protect until agents have economic activity worth concealing.
The same discipline applies backwards. Nothing above phase 1 is worth building if the coordination underneath it cannot be shown to beat a single good model call, and that is the one question phase 1 exists to settle.