White paper

ProveX is a PulseChain-native settlement primitive: seller-locked crypto, a private zero-knowledge proof that fiat moved, and a smart-contract release. It replaces the exchange as the trusted third party. What it does not replace — by design — is discovery, matching, recurrence, composition, or judgment. Those are human (or agent) problems sitting on top of a cryptographic rail.

ProveXAgent is that layer — not as a prettier ProveX.com, as a settlement agent you hire. Users set clearance (spend cap, floor, cadence); persistent agents match counterparties, refuse below 70, open ProveX escrow, submit proofs, and never hold a key. ProveX is the default rail. It is not the product. Two separate meters: ProveX core takes 2% and buys and burns $PRVX. ProveXAgent takes 1% (0.5% buyer / 0.5% seller) to pay for matching, recurrence, and reputation — jobs ProveX does not do. Of that 1%, 40% is a second $PRVX burn, 40% burns $PXA, 20% funds LP around those burns. Agent settlements therefore burn 2.4% of notional as $PRVX, not 2%. All-in is 3%. The flywheel is not metaphorical: more autonomous commerce makes ProveX scarcer. Agents that sit idle mint nothing. Weekly dollar-cost averaging is not rebuilt here. It lives on HabitProofX (habitproofx.com), which is the DCA locker. This site hires, locks, looks up, and verifies. It does not originate credit.

Hire a PulseChain settlement agent. Set a clearance once — it settles through ProveX while you are offline. ProveX is a settlement plugin, not a competing homepage.

ProveX is a one-shot swap primitive: lock, prove fiat, release. 2% burns $PRVX. Humans arrive, click, leave. That job is theirs. ProveXAgent is an agent you hire: clearance, standing mandates, optional policy, and modes a swap page cannot ship without becoming a different company. Same escrow. Different product. Asphalt is not a taxi.

Invaluable means: you keep an agent that runs under your rules while you are offline, talks to other agents, and may deliver through ProveX. You did not buy their homepage. You bought the agent.

ProveX vs ProveXAgent

• ProveX: destination for this swap. ProveXAgent: employee you keep.
• ProveX: one ticket, one proof. ProveXAgent: mandate — every Friday, $500, score ≥ 85, Zelle, if WPLS below X.
• ProveX: human in the loop. ProveXAgent: human sets clearance; the agent executes.
• ProveX: $PRVX burn on settlement. ProveXAgent: $PXA at risk if the agent mis-fires (when live).
• ProveX: counterparty is a person. ProveXAgent: counterparty can be another agent.
• ProveX: one lock. ProveXAgent: compose many locks (invoice, netting, insurance, RWA).

Always on — not a toggle

These are the protocol. Turning them off would make this a custodian or a theme.

• Non-custody. Agent holds $0. A custody flag other than zero fails the proof.
• Floor 70. You may raise it (optional floor 85). You may not lower it.
• Spend cap. Required. You set the number; you cannot run uncapped.
• ProveX as the default rail. The plugin that delivers crypto↔fiat. Not the company you hired.
• Two meters. ProveX 2% and Agent 1% (0.5/0.5). Named, on the ticket.

Optional policy (toggles on the agent)

Off unless you turn them on. A simple on-ramp does not look like a family office.

• Dual-control — above a USD threshold, a second wallet must confirm before escrow opens.
• Dead-man mandate — if the wallet is silent N days, run a pre-cleared off-ramp.
• Bonded fill — slash a $PXA SLA bond if this agent fails to complete. Not their escrow.
• Floor 85 — stricter veto. Allow-list only — named counterparties; empty list means no fill.
• Cadence — off, daily, or weekly. Already first-class.

Optional modes (toggles)

• Invoice / pull — post amount, rail, expiry; the agent watches. Not “I want USDC now.”
• RFQ / dark size — private quotes among permissioned agents, then one ProveX lock.
• Netting — batch or internal-match small hops before a single escrow.
• Condition keepers — if TWAP / balance / HEX end, not only every Friday.
• A2A is a template plus the refusal floor. The public book of agents is the network.

Rail defense — they can block the primary

The gating EOA (intentGatingService) can refuse signalIntent for agent-originated takes. They can also pause core contracts. That blocks the primary rail, not user funds: nothing has left the wallet if clearance never opened escrow.

Diversion is allowed only onto a published secondary rail — the Agent-owned escrow, orchestrator, verifier, and registry listed on the Security page (PulseChain 369, 2026-08-30). That is our bytecode, not a second copy of theirs. An unpublished “backup” address is still an attack. Primary remains the default while their gating cooperates.

What they can copy, and why that is not us

A chat box that calls createDeposit. Anyone can. The gating EOA at 0x4Bd6… can starve agent-originated takes. A trademark will not stop a clone of a swap UI. Cloning clearance + cadence + dual-control + invoices + $PXA stake is cloning this protocol. If they do that, they have stopped being ProveX.com and started being an agent company — on our schema, if we ship the registry first.

Partnership remains rational: their 2% volume rises because of us. ProveX stays the plugin. The agent stays the product.

PulseChain already has a native DEX (PulseX), a culture of long-horizon holders, and assets (PLS / WPLS, HEX, and a long tail of Pulse-native tokens) that do not enjoy first-class treatment on large centralized exchanges. The missing piece has always been the fiat edge: how value enters and leaves without reconstituting Coinbase in a PulseChain costume.

What centralized ramps actually sell

A CEX or licensed on-ramp sells three bundled products: custody, compliance theater, and matching. Custody is the attack surface. Compliance theater is why accounts freeze after a screenshot of a chat. Matching is the only part users actually wanted. ProveX unbundles the bundle. Matching can be stupid or brilliant; settlement must be dumb, private, and final.

• CEX wallets are honey pots. PulseChain users have already watched this movie.
• P2P groups without escrow are reputation-by-screenshot. Chargebacks win.
• Atomic swaps and DEXs solve crypto-crypto. They do not prove a wire landed.
• Identity-heavy KYC ramps recreate the surveillance the chain was meant to exit.

ProveX answers the cryptographic half: lock, prove, release. The market-structure half — who is selling USDC at 99.4¢ right now, who has a 90+ ProveX identity score, whether this week’s DCA should wait six hours, how a DePIN payout composes with a fiat proof — is still a human sitting in a Discord. Humans do not run while they sleep. Agents do.

ProveX (provex.com / provex.dev) is not an exchange. It is an escrow plus a verifier. A seller locks crypto in a PulseChain contract. A buyer pays fiat off-chain. A browser extension produces a zero-knowledge proof that the payment occurred, without revealing bank-level detail to the world. The contract releases if and only if the proof verifies. A fixed-supply $PRVX token is bought and burned on successful use (ProveX’s own 2% protocol fee). ProveXAgent is a separate meter: 1% of notional (0.5% buyer / 0.5% seller), then 40 / 40 / 20. The 2% is not replaced and not folded into the 1%.

That design has an unusual honesty: ProveX does not know the buyer’s bank, does not hold the seller’s keys after lock, and cannot reverse a verified proof because a card network later changed its mind. Chargebacks are a fiat-rail problem. They do not unwind math. This is why ProveX is a better home for agent settlement than any custodial API. An agent that “has withdrawal permission” on an exchange is a rogue-employee scenario waiting for a prompt injection. An agent that can only call ProveXEscrowAdapter.fulfillIntent() cannot steal what it cannot hold.

Invariant, restated until it is boring: all value movement happens inside ProveX escrow and ZK verification. ProveXAgent agents never take custody. If a code path would assign a user balance to an agent, that path is a bug, not a feature.

Protocols die from underuse, not from imperfect cryptography. A perfect escrow that requires a power user to find a counterparty, check a score, time a rate, and babysit a proof is a protocol for a few hundred people. ProveXAgent exists so ProveX can be the default settlement engine for everyone else — including software that has no UI.

Four jobs ProveX should not do itself

• Discovery. Escrow is not an order book. Someone has to surface inventory and spreads.
• Policy. Max spend, allow-lists, time locks, and reputation floors are user intent, not consensus rules.
• Composition. Multi-party deals, DePIN attestations, parametric insurance, ticket transfers — these are graphs of proofs, not a single lock.
• Continuity. Weekly on-ramps and sleeping DCA are products. A website session is not.

If ProveX absorbed those jobs into the core contracts, it would bloat the trusted computing base and start looking like a CEX with extra steps. Keeping them in an agent layer, bound by a non-custodial adapter, preserves the thinness of ProveX while multiplying its surface area. That is the entire architectural bet.

“Better” here is not a slogan. It is a set of measurable protocol properties that improve when agents exist.

Volume that does not depend on a campaign

Manual P2P is bursty. An always-on on-ramp agent produces a baseline of escrow opens and proof submissions even when no one is looking at a dashboard. Recurring strategies convert ProveX from an event into a utility. Utilities get monetary premium; events get tweets.

A demand-side order flow for $PRVX burns

Every agent settlement still pays ProveX’s 2% (buy-and-burn $PRVX). That 2% is untouched. The Agent 1% sits beside it, not instead of it. Of that 1%, 40% is a second market-buy of $PRVX — so an agent-executed settlement burns 2.4% of notional as $PRVX, not 2%. The remaining Agent take burns $PXA (aligning operators to volume) and stocks a treasury that seeds PulseX LP on PRVX pairs — the same pools the 2% burn has to trade into. Combined take: 3%. The dashboard counts quotes stored in this browser. It is not chain volume and not a public burn.

Liquidity that can be matched without being custodied

PulseX holds WPLS pairs. ProveX holds escrowed inventory. Agents sit between them as scouts, not as warehouses. PXA/WPLS and PRVX/WPLS become the natural hedges and fee sinks. Native PLS is the asset people talk about; WPLS is what the DEX actually pairs. The agent layer is where that distinction is enforced so users do not fat-finger a wrapped-native mix-up into a failed settlement.

Identity without a KYC honeypot

ProveX identity attestations and EAS anchors give agents a score they can refuse below. That is soft reputation, not a passport office. Counterparties below the floor simply do not match. ProveX becomes a place where privacy and repeat business coexist, which is the combination CEXes keep promising and then KYC away.

A reason for other protocols to settle here

DePIN, carbon, insurance, ticketing, RWA — none of these verticals want to build a fiat verifier. They want a rail. ProveXAgent Native Templates are distribution for ProveX: each vertical that settles through ProveX is a new inbound escrow graph. The agents are a ProveXAgent product. They are not listings on ProveX.com.

Seven layers, one custody rule. Users and wallets sit at the edge. An off-chain orchestrator (natural language, matching, planning) has no keys. ProveXAgent contracts on PulseChain (registry, stake, fees, adapter, reputation, circuit breaker) authorize and meter. ProveX core still holds funds. $PXA / $PRVX live as ERC-20s. PulseX is the DEX. EAS is the identity anchor.

Contracts (the intended on-chain set)

• AgentRegistry — register, scope permissions, activate or deactivate.
• StakeManager — vePXA locks, voting power, execution boosts.
• FeeRouter — collect Agent 1% (0.5% buyer / 0.5% seller), split 40% PXA / 40% PRVX / 20% treasury. ProveX 2% is collected by ProveX core, not this contract.
• ProveXEscrowAdapter — the only bridge. It may call Escrow.createDeposit, Orchestrator.signalIntent / fulfillIntent(paymentProof), and UnifiedPaymentVerifier.verifyPayment on the pinned PulseChain 369 addresses. Nothing else.
• ReputationAttestor — success attestations, history scores, slashing on dispute.
• CircuitBreaker — pause, emergency withdraw of stuck flows back to ProveX rules, upgrade votes.
• PXAToken / Treasury — burnable agent token; grants and PulseX LP incentives.

The adapter is the load-bearing idea. Agents call the adapter; the adapter calls ProveX. There is no “agent wallet with user funds.” Permissions are max-spend, counterparty floors, and time bounds — capability tokens, not custody.

What is live in this interface versus what is still spec

Honesty is part of security. The orchestrator, clearance, circuit breaker, and fee math are connected. ProveX Escrow, Orchestrator, Payment Verifier Registry, and Unified Payment Verifier are verified on PulseChain 369 with live ABIs — createDeposit, signalIntent, fulfillIntent(paymentProof), verifyPayment. Proofs that target any other escrow fail closed. Gating 0x4Bd6… is an EOA (intentGatingService), not a contract. Registry, stake, and fee routing are still simulated. PulseChain RPC, wallets, the buyer extension, $PXA, the Agent adapter, and EAS schemas remain unwired. The Security page is the live matrix.

ProveXAgent is not one chatbot. It is a small society of scoped roles that are only allowed to talk to ProveX about money.

Roles

• Scout — ranks inventory, spreads, PulseX depth, and identity scores. Emits a plan, not a transfer.
• Executor — drives the 12-step lifecycle through the adapter. Holds no keys.
• Auditor — watches floors, disputes, and circuit-breaker conditions.
• Personal persistent agent — the user’s always-on strategy with a max-spend and an allow-list, including while the user is offline.
• ProveXAgent template — a public vertical (on-ramp, DePIN, insurance…) that vePXA lockers can sponsor. It connects to ProveX. It is not a listing on ProveX.com.

Agent-to-agent negotiation

Once identity proofs exist, agents can refuse each other. A Helios-class A2A agent with a floor of 85 will not open escrow with a fresh, unattested counterparty. That is not discrimination in the banking sense; it is a programmable substitute for “I don’t take checks from strangers.” Reputation is collateral you cannot lend to your agent as spendable cash — only as a gate.

Natural language as a control plane

“On-ramp $2,500 USDC optimally” is a better UX than five modal dialogs, but it is also a new attack surface. Clearance sanitizes prompts, caps length, strips markup, and never sends keys or proof bytes to the language model. The model narrates; clearance decides. If the two disagree, clearance wins. Prompt injection cannot authorize custody that does not exist.

Templates as go-to-market

On-ramp / off-ramp / recurring are the cash cow. Liquidity scouts thicken the book. Multi-party and A2A are the enterprise wedge. DePIN, carbon, insurance, ticketing, and RWA are the expansion set — each a ProveXAgent native badge, each a burn leaderboard entry. These agents are not on ProveX.com. Bonding-curve pricing for premium templates lets early high-value agents capture upside without locking later users out.

Twelve steps, no skips. Clearance treats n → n+2 as an attack.

• 0 Pre-trade ticket. ProveX 2%, Agent 0.5/0.5, you receive, seller locks 100.5, $PRVX pressure 2.4%. Confirm or nothing moves.
• 1–2 User instructs; orchestrator plans against that template’s tool allow-list. Off-chain. No funds move.
• 3 Registry checks vePXA, max spend, allow-list. Offer book ranks counterparties; rows below the floor are marked refused.
• 4–6 Seller signs a lock; adapter forwards; ProveX holds. Agent custody remains false.
• 7 Buyer pays fiat; extension builds a private proof.
• 8–10 Agent submits proof bytes through the adapter; ProveX verifies; release.
• 11 ProveX takes 2% (PRVX burn). FeeRouter takes Agent 1% (0.5/0.5) and buy-burns PXA + PRVX; remainder to treasury.
• 12 ReputationAttestor writes success. The agent’s score, not its balance, went up.

Failures are fail-closed. Circuit breaker open → no new escrow. Dust below $10 or notional above $1,000,000 → rejected. Unknown asset → rejected. Counterparty below floor → refused, and the refused row stays visible on the offer book. Reused nonce → replay blocked. A proof whose public signals show custodyHeldByAgent ≠ 0 is not a proof, it is a confession, and it aborts. No escrow opens until the pre-trade ticket is confirmed.

Two tokens, one settlement. $PRVX is the ProveX protocol token: fixed supply, burned on use. $PXA is the agent token: staked as vePXA for boosts, governance, and the right to run or sponsor agents. They are not aliases. Confusing them is how you accidentally design a single-token casino.

Two meters on a $2,500 on-ramp

• ProveX core 2.00% ($50) — separate protocol fee, 100% buy-and-burn $PRVX. Untouched by Agent.
• ProveXAgent 1.00% ($25) — 0.50% buyer ($12.50) + 0.50% seller ($12.50). Seller locks 100.5 to sell 100.
• Of the Agent $25: $10 buy-burn $PXA, $10 extra buy-burn $PRVX, $5 treasury.
• ProveX gets $60 of PRVX buy-pressure (2.4%), not $50. Combined take: 3.00%.

Why the Agent 1% is acceptable

ProveX’s 2% pays for escrow and the verifier. It does not pay for discovery, matching, reputation floors, or a strategy that runs at 3 a.m. Those jobs are either human (Discord OTC, babysitting proofs) or they get smuggled into spread. The Agent 1% is the explicit price of that labor, automated and non-custodial, split so neither side eats it whole: 50 bps buyer, 50 bps seller.

Fifty basis points per side is inside a typical P2P spread they already pay, and it is cheaper than a CEX or MoonPay-style on-ramp once KYC, spread, and freeze-risk are priced in. A zero Agent fee would not be free — it would hide the cost in worse fills, unpaid operators, or inflation. $PRVX cannot inflate. So the 1% is the honest meter.

What the 1% actually does for ProveX

• Manufactures ProveX 2% events. Always-on agents open escrows that one-off P2P never would. Each one still pays ProveX’s full 2%.
• Adds 40 bps of extra $PRVX buy-and-burn on top of the 2%. Agent volume is strictly better for $PRVX scarcity than the same notional done by hand.
• Funds PulseX LP on PRVX/WPLS and PXA/PRVX from the 20% treasury slice — depth the 2% market-buy needs, or burns eat their own slippage.
• Pays operators (vePXA boosts, template residuals) to maximize ProveX volume, not to route around it. Alternative rails still cost more and still burn PRVX.

vePXA time-locks increase voting power and execution priority. Lockers may sponsor public template agents and earn a thin residual of those templates’ fees — passive yield tied to ProveX adoption, not to inflation. Dynamic fee-share boosts accrue to agents that generate the highest pure ProveX volume, measured on-chain. The protocol pays for burns, not for vanity TVL.

Treasury (20%) funds development, grants, and PulseX LP on PXA/PRVX and PXA/WPLS. It is not a slush fund for market-making user assets. User assets never enter it.

The threat model assumes a hostile prompt, a greedy agent operator, a buggy UI, and a curious adversary with localStorage access. It does not assume a broken Groth16 pairing on mainnet — that assumption is reserved until the verifier address is wired.

What clearance already enforces

• Non-custodial invariant. custodyHeldByAgent is a hard zero.
• State machine. Steps cannot skip, rewind, or resurrect a terminal settlement.
• Replay nonces unique per instruction.
• PulseChain chain id 369 bound into proofs and settlements.
• Allow-listed assets (USDC, DAI, WPLS, PLS, HEX, PRVX, PXA).
• Prompt sanitization: HTML, control chars, javascript: URIs stripped; 500-char cap.
• Rate limit: 8 settlements / 60s, fail-closed.
• Stake, reputation, and max-spend gates before escrow is planned.
• Circuit breaker pauses execution, not just a label in the header.

What remains a mainnet problem

Real Groth16 pairing checks, seller signatures on the lock, the buyer extension’s trusted proving stack, upgrade timelocks, EAS schema immutability, and PulseX router allowance hygiene. Until those addresses exist, this interface is a faithful simulator of policy, not a custodian of funds. That disclosure is itself a security control: users should not deposit into a story.

The interesting security claim is still the architectural one. Most “AI agent + DeFi” products fail by giving the model a hot wallet. ProveXAgent fails closed by giving the model a narrator badge and giving the adapter a narrow ABI. The smartest agent in the swarm cannot wire funds to itself. That is the product.

Fit is not “crypto users like AI.” Fit is a specific user with a specific job and a specific reason the current tools injure them.

Primary user: the PulseChain native who needs a fiat edge

They already trust PulseX more than a New York order book. They do not want to KYC a megabyte of utility bills to buy $2,500 of WPLS. They will tolerate a P2P flow if escrow is real and privacy is real. ProveX is the escrow. ProveXAgent is how they stop living in group chats to operate it.

Secondary user: the operator who wants recurrence

Payroll-in, treasury-out, and standing on-ramps are calendars, not one swaps. The DCA locker is HabitProofX (https://www.habitproofx.com): cross-chain habits that settle fiat through ProveX. ProveXAgent links to it. It does not clone it. Recurrence on this site is a cadence on a hired agent (off, daily, weekly), scoped by max-spend.

Tertiary user: other protocols

Anyone who must pay a human in the real world and a machine on PulseChain in the same breath. Insurance, tickets, carbon, RWA title — they do not need another token, they need a verifier. ProveXAgent Native Templates let them use the ProveX rail instead of forking it. The agents stay a ProveXAgent product.

Why now

Agentic software is suddenly a consumer habit, while the on-chain half of “AI agents with wallets” is still a cautionary tale. ProveX is one of the few settlement designs that remains correct if the agent is captured. That timing is the wedge: sell safety to people who are about to give language models too much power, and sell volume to a protocol that needs a demand engine.

Positioning is one sentence: hire a PulseChain settlement agent. ProveX is how it delivers crypto↔fiat. It is not what the user bought. Everything else is proof of that sentence.

• Lead with mandates and A2A — jobs a swap page cannot ship — not with their brand on autopilot.
• A public burn counter is not on this site. The numbers here are this browser. A chain counter waits for receipts.
• ProveXAgent Native Templates, with a ProveXAgent native badge and a highest-burn leaderboard. Not a ProveX.com catalog.
• vePXA required to keep an agent active when the token is live. No stake, no clearance.
• PulseX adjacency. Trade WPLS pairs there, settle fiat here. Weekly DCA is HabitProofX, linked from More — not a second locker on this domain.
• Console-first UX. Power users instruct in English. Everyone else sets an amount and a rail. Same rail.

What we will not market: yield on user funds, “AI alpha,” or custody. Those pitches attract the wrong capital and the wrong regulators. The pitch is narrower and stronger. Your agent cannot steal from you. Your settlement still burns PRVX. Your mandate runs at 3 a.m. We will not market ourselves as their autopilot.

The addressable market is not “all of CeFi.” It is the slice of fiat↔crypto flow that is already trying to be P2P, already uncomfortable with custodial ramps, and already on or adjacent to PulseChain. That slice is smaller than Binance and much larger than a Telegram OTC desk.

Expand along three axes only. First, depth inside PulseChain (HEX/WPLS/USDC ramps, PulseX fee burns). Second, ProveXAgent vertical templates that import foreign volume onto the ProveX rail. They are not products of ProveX.com. Third, agent-to-agent commerce, which has no incumbent CEX UX at all — because a CEX cannot underwrite two bots without taking both sides into custody.

Capture is not take-rate maximization. Two named meters — ProveX 2% plus Agent 1% — beat a hidden 2% all on the buyer plus an unnamed surcharge. A spread-aware scout can still beat a retail CEX after KYC friction is priced in. If we win, we win on being the rail other software calls, not on being the storefront with the loudest APY.

The cryptographic rail does not need a prettier website. It needs a control plane that makes the 3% honest before money moves, gives sellers a desk, shows the book, actually recurs, gates on identity, prices templates as a market, and stops using one prompt for every vertical.

1. Pre-trade ticket

Before any escrow, the Console prints a ticket: notional, ProveX 2% (100% $PRVX burn), Agent buyer 0.5%, Agent seller 0.5%, amount you receive, amount the seller locks (100.5 to sell 100), and $PRVX buy-pressure of 2.4% of notional. A typical CEX/MoonPay all-in sits next to it so the 3% is a quote, not a footnote. Confirm moves the quote to Awaiting wallet. It does not send a chain transaction. Continue on ProveX is a separate link. There is no Decline button. Custody stays at zero until a wallet signs.

2. Seller desk

ProveX is two-sided. The Desk lets a seller pick an asset, a notional, and a fiat rail (Zelle, Venmo, Wise, ACH, wire), then lock 100.5 to sell 100. Until a wallet signs createDeposit on the published Agent escrow, the desk is a preview: nothing is in escrow. Identity raises the floor. It is not a posting wall on a preview listing.

3. Visible matching

The orchestrator no longer “finds a counterparty” in prose. The offer book lists seller, rail, score, and why. Rows below the floor (70) stay on the page as “refused: score 62.” Execute is blocked unless a cleared offer is selected. That is the A2A gate made visible.

4. Recurrence that recurs

Agents carry a cadence: off, daily, or weekly, plus an amount, a rail, a floor, a spend cap, an optional payee name, and an optional USDC price band. Next-run and last-run are stored. A due run logs a miss and does not open a ticket when the local circuit is open, contract pause is unread or true, no seller clears the floor, a named payee is not that cleared seller, or USDC is unread or outside the band. It does not invent a fill. The public book is not a substitute for a named payee. The reputation floor does not waive the price band.

5. Identity as a gate

Linking an EAS attestation (`eas:ProveXIdentity/v1`) would assign a score. That badge is not live. The desk does not pretend to link it, and a preview listing can be posted without it. A score under 70 cannot be selected as a counterparty. Identity is collateral for matching, never spendable cash, never a KYC file the agent holds, and not a posting wall on a preview.

6. ProveXAgent Native Templates as a market

These templates are a ProveXAgent product. They connect to ProveX. They are not on ProveX.com. Deploy price follows a bonding curve: base min-stake × (1 + 0.08 × live agents on that template). Early deployers pay less; later ones pay the curve. vePXA lockers can sponsor a template (1,000 PXA) and earn a 10 bps residual of notional on every settle of that vertical — clipped from success, not from an extra meter. The leaderboard remains ranked by volume / burn.

7. One orchestrator per vertical

Each template has its own system prompt and a closed tool allow-list (for example On-Ramp: matchOffers, quoteTicket, openEscrow, submitZkProof; A2A: queryReputation, refuseBelowFloor). The language model may only narrate tools on that list. Clearance still decides. A DePIN agent cannot pretend it is an on-ramp.

These are live in the interface. They are not a promise of a mainnet signature. The Roadmap page is the short list. This section is the same list in protocol language.

Named payee

A buy can name the person on the rail, on the quote form and on a standing mandate. That name is the only counterparty. If they are not a cleared seller on that rail, the quote is refused and a due run logs a miss. A higher-scored stranger on the public book is not used. A blank payee still uses the open book. This is not an allow-list of many names, and it is not credit.

Price band

A USDC buy can set a band around $1 par: off, 0.25%, 0.50%, or 1.00%. Off does not check the print. On, the quote is refused and a due run logs a miss when the PulseChain USDC price is unread or farther from par than the band. A high reputation score does not waive it. The band does not apply to WPLS or DAI. It is not an oracle the agent custodies, and it is not credit.

Status link

Each quote has a link. The page is a copy of that moment, not a live shared server. It shows Quote, Awaiting wallet, Awaiting proof, or Failed. It does not connect a wallet, and it does not say Released. A chain receipt is not claimed from that card.

Sign ping

When a wallet signature is the only step left, the console, the rail, and the status card say so on the screen. It is not an email or a text. Nothing is in escrow until that signature exists.

Year file

One download lists quotes, misses, and chain receipts. A row with a real chain receipt is labeled chain receipt, not quote. The receipt column is filled only when the hash is 0x plus 64 hex characters. Anything else is left blank. The file says it is not a tax return.

Merchant till

The desk keeps one rail and one daily cap. The cap is the UTC calendar day, not a rolling 24 hours. Each sale is its own ticket and its own status link. Sales are not pooled into one escrow. Nothing is in escrow until a wallet signs.

Payables batch

A batch is one name and one amount per line. A blank line, a line under $10, or a line over the per-payee cap is refused. Each accepted line is its own quote. The sum is a view. The owner confirms each ticket separately. Nothing is merged into one lock.

Clerk and owner

This browser can act as a clerk or as the owner. The switch is a role on this browser. It is not a second wallet and it does not create a key. A clerk can build a quote. Only the owner moves it to Awaiting wallet. The same switch is on Buy USDC and on the desk.

Close the books

A close needs three legs: a fiat reference, an attestor id, and a chain receipt of 0x plus 64 hex characters. A missing leg stays not closed. The page does not change that into a release.

Unattended sell-side

A desk listing is a preview, not a chain lock. It stays up until the UTC-day cap is used, the circuit or contract pause is open or unread, or the seller withdraws it. The shop does not repost the same listing each morning. A refused new post does not delete the one that is already up.

Role map

Home is four jobs, not a manifesto. Hire an agent (amount, rail, quote). Lock inventory (preview until a wallet signs). Look up an agent. Verify published contracts. Chat changes a plan. It does not open escrow.

Agent directory

Each row states the job (template), the spend cap, the reputation floor, and whether the agent is yours. Example agents are labeled “Not yours.” A public id without a job is not a directory.

Clearance policy pxa-policy/0

A free, static object on Agents and Architecture. A counterparty is allowed only if the score meets the floor (70), the circuit is closed, the notional fits the remaining cap, the target is a published rail, and release is an attestor signature — or a ProveX extension proof if that API is connected. It is not a credit file, not a sold score, and not a loan. Unsecured agent credit is out of scope unless counsel and an audit say this protocol is a lender.

What still refuses a real lock

Five gates are closed in the interface, not waved through. A browser hash cannot release escrow. Preview listings are not sellers; only DepositCreated logs count. The pause button does not call setPaused. The live Agent contracts are unaudited, so this site will not ask a wallet to deposit. Floor, cap, and rail checks in the browser do not bind a direct call — AgentClearance is in the next deploy and is not at the live addresses. Until those addresses are published, a quote stays a quote.

HabitProofX

The DCA locker is habitproofx.com. It is linked from More as DCA locker. Habits and cross-chain DCA stay there. Settlement policy, the seller desk, and clearance stay here.

Proof and rails, as written

• Agent rail release is an attestor signature. Not a Groth16 circuit this protocol invented.
• ProveX’s own extension proof is used only if that API is connected.
• Primary rail is pinned ProveX core. Secondary is the published Agent escrow, orchestrator, verifier, and registry. An unpublished address is refused.
• ProveX 2% and Agent 1% (0.5% buyer / 0.5% seller, then 40/40/20) stay two meters.

The interface you are reading is the control plane and the policy rehearsal. The remaining work is binding, not inventing.

• Done: role map, agent directory (job, cap, floor, yours), and pxa-policy/0.
• Next: a PulseChain 369 wallet signs createDeposit on the published Agent escrow. The desk stops saying preview only after that receipt exists.
• Then: reputation is released notional and completed mandates, minus fail-closed defaults. A tiny instant loop does not climb the score.
• Not next: an unsecured credit pool. Escrow plus the named 1% stays the product.
• Still unwired: ProveX extension proofs, on-chain FeeRouter burns, and $PXA. The Security page is the wiring matrix.

Until then, the Security page remains the source of truth for what is connected, simulated, linked, or unwired. A white paper that overclaims a test clearance as a mainnet verifier would be doing the one thing this protocol cannot afford: asking for trust.

ProveX proved that fiat and crypto can meet without a custodian. ProveXAgent is the argument that they will meet often — because software that never sleeps, never holds the bag, and never skips the verifier is how a primitive becomes infrastructure.

If the agents work, ProveX is no longer a destination you visit. It is the settlement engine other programs quietly use. That is the only kind of protocol that stays scarce on purpose.

Read the Security matrix for the live wiring. Instruct an agent in the Console. Terms, privacy, and risk live in the footer — because a non-custodial protocol still owes you plain language about what it is not. Weekly DCA is HabitProofX. This paper is not a credit agreement.