FAQ

What is ProveXAgent?

ProveXAgent is a PulseChain-native settlement agent you hire. ProveX is the settlement primitive (escrow + payment proof + release). ProveXAgent is the clearance and mandate layer: matching, tickets, recurrence, reputation, A2A, and ProveXAgent Native Templates. The product is not a chatbot and it is not a ProveX.com frontend. The product is a permissioned agent per wallet that runs standing instructions inside a spend cap you set — including while you are offline.

Set a clearance once. The agent settles through ProveX. Grok may explain the ticket. The agent never holds keys. ProveX moves the funds. ProveX is the rail, not the product.

What is a permissioned agent per wallet?

When you register an agent (Atlas, a Recurring Strategy template, an A2A negotiator), you are not spawning a private copy of Grok. You are creating a named agent bound to your session — and, when the chain is live, to your wallet — with:

• A ProveXAgent template (on-ramp, off-ramp, liquidity, A2A, …) and its tool allow-list.
• A max spend. Clearance refuses anything larger.
• A reputation floor (70). Counterparties below it are refused.
• Optional cadence (daily / weekly) so it can fire while you are offline.
• Stake in $PXA (vePXA when live) so misbehavior can be slashed. Unstaked agents have no clearance once $PXA is live.

That record is the product. Ten users share one Grok model. They do not share one agent. Each wallet’s agent has its own clearance, history, and stake.

Is this just a ProveX.com frontend?

No. ProveX.com is a place you go to do a swap. ProveXAgent is an agent you hire that keeps settling under your rules — weekly mandates, A2A, invoices, dual-control — and may use ProveX as the delivery rail. See the white paper section Why ProveXAgent is not ProveX.

What is always on vs optional?

Always on (not toggles): non-custody, floor 70 (you may raise, not lower), spend cap, ProveX as the default rail, two named fee meters. Optional policy, off until you switch them on the Agents page: dual-control, dead-man mandate, bonded fill, floor 85, allow-list only. Optional modes: invoice/pull, RFQ/dark size, netting, condition keepers. Cadence is already a control (off / daily / weekly).

What is clearance?

Clearance is the permission to act: spend cap, floor 70, replay nonce, pause. Out of clearance, the instruct dies and no escrow opens. The circuit breaker revokes clearance globally. It is not a vault and it is not an AI.

How is this different from “an AI that trades for me”?

An AI that holds keys is a custodian. ProveXAgent forbids custody in clearance: if a proof’s public signal says the agent held funds, verification fails closed. The seller signs createDeposit into ProveX Escrow. The buyer (or the agent posting on their behalf) submits fulfillIntent(paymentProof). The agent carries a clearance badge. It is not a vault, and it is not the browser Clerk switch.

What is ProveX?

ProveX is a PulseChain P2P fiat-to-crypto settlement protocol. A seller locks crypto in escrow. A buyer pays fiat and produces a private proof of that payment. The contract releases. No centralized exchange sits in the middle. Core fee is 2%, 100% buy-and-burn of $PRVX. Open the live app at app.provex.com. Protocol site: provex.com.

Why does ProveX need agents?

ProveX is excellent at “did fiat move, then release.” It does not rank Zelle vs Wise offers, refuse a 42-score counterparty, run a weekly on-ramp, or compose multi-party proofs. Those jobs create volume ProveX would otherwise miss. Agents make ProveX the default rail for autonomous commerce instead of a manual tool.

Does ProveXAgent replace ProveX?

No. If the adapter cannot call the pinned Escrow and Orchestrator, nothing of value moves. We are not a fork, a wrapped ProveX, or a competing escrow. ProveX is a settlement plugin this agent uses by default. The thing you hired is the agent — mandate, clearance, A2A — not their homepage.

Is ProveXAgent one Grok bot that every user shares?

No. There is one hosted Grok-4.5 model used as a narrator. Every user does not “log into the same bot.” They instruct their own agent record. Grok receives a short, stateless request: the template’s system prompt plus this instruction. It returns 2–4 sentences. It cannot open escrow, sign, or see other users’ chats.

Does each user spawn their own Grok?

No, and they should not. A private Grok per wallet would be slow, expensive, and a worse security model (persistent model memory is where keys and payment details leak). Isolation belongs in clearance, stake, and permissions — not in a dedicated LLM process.

How is Grok connected to a user?

It isn’t bound as an account. The Console calls a server function with the prompt. If an xAI key is present, Grok narrates. If not, the local plan text is used and the ticket still renders. Chat in this demo lives in your browser (localStorage), not in Grok.

How does this scale?

Scale is request volume, not bot count. Ten thousand instructs are ten thousand short HTTP completions against one model, plus local clearance checks. Recurring agents do not keep Grok online; a scheduler fires the same instruct path later. The live bottleneck will be PulseChain RPC and ProveX escrow, not Grok.

What if Grok is down or rate-limited?

Settlement continues on the local plan. Narration is optional. Funds never wait on a language model.

What happens when I type in the Console?

• Clearance sanitizes the prompt (no scripts, length cap 500 characters).
• A deterministic planner picks a template (on-ramp, off-ramp, deploy, stake…).
• It selects an active agent that matches that template, or the first active agent.
• Gate: pause, dust ($10), max size, asset allow-list, agent max-spend, rate limit, reputation.
• A pre-trade ticket shows ProveX 2%, Agent 0.5/0.5, you-receive, seller-locks, 2.4% $PRVX pressure.
• The offer book scores inventory. Rows below floor 70 are refused.
• You confirm. The demo steps a 12-step rail. Live, that becomes on-chain calls.

What are the on-chain calls when this is live?

Seller: Escrow createDeposit at 0x0B42…f11a. Buyer: Orchestrator signalIntent then fulfillIntent(paymentProof) at 0x742d…b080. Inside fulfill, Unified Payment Verifier runs verifyPayment. Release is unlockAndTransferFunds. The agent still holds $0.

What is the seller desk?

Desk is inventory, not chat. A seller with a linked identity posts an offer (asset, size, fiat rail). That row enters the scored book the Console matches against. How that book becomes a price is in How the agent finds the best price.

Can I skip the ticket and dump funds in?

No. Clearance will not open a rail without a gated intent. Confirm is explicit.

The agent does not scrape a CEX and it does not invent a quote. “Best” means the best eligible fill — all-in, after identity floors — not the cheapest unsafe seller.

A penny-tighter offer from a score-62 is not a better price. It is a blocked counterparty. Floor 70 is a veto, not a hint.

The five steps on every instruct

• Read the book: open desk offers for the requested asset. Native PLS is treated as WPLS. Size and fiat rail (Zelle, Venmo, Wise, ACH, wire) must fit.
• Veto: drop any row whose ProveX identity score is below 70. Those never become a ticket.
• Rank: remaining rows by reputation (ZK-verified completions, slashes), then rail fit. Highest accepted score is the suggested match.
• Quote all-in: the pre-trade ticket is the price you actually get — ProveX 2% + Agent 0.5% / 0.5%, you-receive, seller-locks, 2.4% $PRVX pressure.
• You confirm. If the book is empty after the veto, the rail does not open. Nothing hits escrow.

Worked example — on-ramp $2,500 USDC

Four sellers in the book. The agent does this, not a language model:

• Lowball · Venmo · score 62 — refused. Below floor. Invisible to confirm.
• Hexgate · HEX not USDC — skipped. Wrong asset.
• Iridium · Wise · score 88 — eligible.
• Nova · Zelle · score 94 — eligible, higher reputation, suggested match.

Ticket on Nova: notional $2,500. ProveX 2% = $50 (PRVX burn). Agent $12.50 buyer + $12.50 seller. You receive $2,437.50. Seller locks $2,512.50. That package is the price. You can still pick Iridium if you want that rail — the agent ranked; it did not spend.

Where PulseX fits

When the liquidity scout is wired, it also reads PulseX WPLS pair depth so a P2P fill can be compared with on-DEX. Settlement still exits through ProveX escrow, not the DEX. PulseX is a price check, not the vault.

Who has the last word?

You. The agent ranks and refuses. Confirm is explicit. That is also why the Agent 1% can pay for itself: a 0.5% better eligible match covers one side of the meter. A cheaper fill that fails identity never reaches the contract.

Why are there two fees?

ProveX 2% is the core settlement meter. 100% of it buys and burns $PRVX. That fee exists whether or not an agent is involved. ProveXAgent 1% is a second meter for work ProveX does not do: matching, recurrence, reputation, orchestration. It is 0.5% on the buyer and 0.5% on the seller — not 1% stacked on the buy side.

What does the Agent 1% actually do for $PRVX?

Of that 1%: 40% extra buy-and-burn $PRVX, 40% buy-and-burn $PXA, 20% treasury LP around those burns. All-in user cost is 3%. Agent-routed volume therefore applies 2.4% of notional as $PRVX buy-pressure (core 2% + extra 0.4%), not 2%. Agents that sit idle mint no fees. Agents that generate ProveX volume make $PRVX scarcer.

Example on $2,500?

ProveX 2% = $50 (PRVX burn). Agent buyer 0.5% = $12.50. Agent seller 0.5% = $12.50. Seller locks $2,512.50 to sell $2,500. Buyer receives $2,437.50. Of the $25 agent take: $10 extra PRVX burn, $10 PXA burn, $5 treasury.

Is the 1% just paying for Grok?

No. Narration costs cents. The fee pays matching, reputation floors, pre-trade tickets, and recurrence — work ProveX’s 2% does not cover. Idle agents mint $0.

Does the 1% save money?

Versus CEX/card ramps and versus a bad manual fill, often yes. Versus DIY ProveX with a known high-score counterparty, no — that path is 2%. A 0.5% better match already pays one side of the Agent meter.

Can fees be zero and still burn?

Not without an external subsidy. Burns need a source of tokens. The two-meter design is the current rule. It is not optional in this interface.

Do you ever hold my crypto or fiat?

No. Seed phrases and bank passwords are never requested. A custody flag of anything other than zero fails the proof. The circuit breaker can pause new plans; it cannot seize escrowed funds.

Can ProveX.com block ProveXAgent transactions?

Yes. The gating service is an EOA on each deposit. They can refuse to sign agent-originated signalIntent, pause their orchestrator, or change verifiers. That is a kill switch on the primary rail. It is not a kill switch on your keys — uncleared funds never left the wallet.

Defense: proofs may only target a published rail. Primary is ProveX escrow. Secondary is the Agent-owned escrow on PulseChain (Security page). If primary gating refuses, clearance may divert to that published secondary. We never divert to an address that is not on the Security page. Partnership still beats a war: their 2% volume is the reason not to flip the switch.

What does clearance enforce?

• PulseChain only (chain id 369).
• Proofs bound to the pinned Escrow address — any other address fails.
• No skipped settlement steps.
• Replay nonces cannot be reused.
• Assets allow-listed. PulseX pairs are WPLS, not native PLS.
• Rate limit: 8 settlements per minute in this interface.
• A2A / book floor: counterparty score 70.

Is this live on mainnet today?

ProveX core contracts are verified on PulseChain. This interface pins those addresses and models the lifecycle. Wallet RPC, the buyer payment-proof extension, $PXA, the Agent adapter, and FeeRouter → PulseX are still unwired. The Security page is the live matrix. Simulated steps are labeled as such.

What is $PRVX vs $PXA?

$PRVX is ProveX’s fixed-supply settlement token, burned by the core 2% and by 40% of the Agent meter. $PXA is the Agent token: stake, ve-locks, template bonding, and 40% of the Agent meter. $PXA has not been published on-chain yet.

Why WPLS not PLS?

PulseX pairs the wrapped native. Labels in this app say WPLS. Native PLS is a different asset.

What is identity?

ProveX identity (EAS schema eas:ProveXIdentity/v1) is not live. The desk does not pretend to link it. A preview listing can be posted without a badge. A score under 70 cannot be selected as a counterparty. Score is not KYC performed by us. Floor 70 is protocol policy in this layer.

What are ProveXAgent Native Templates?

They are a ProveXAgent product, connected to the ProveX platform, not listings on ProveX.com. Each one is a vertical with a prompt and a tool allow-list: On-Ramp Optimizer, Off-Ramp Scheduler, Liquidity Scout, Conditional Commerce, Recurring Strategy, DePIN, Carbon, Insurance, Ticketing, RWA, A2A. An agent of one template cannot call tools listed only on another. vePXA lockers can sponsor a public template and earn a residual of its Agent fees. Premium templates may use a bonding curve. Recurring and A2A are first-class jobs — not footnotes on an on-ramp.

Do recurring agents run while I am offline?

That is the job you hired, not a slogan. In this demo, a local timer ticks schedules. On-chain, cadence is a keeper/scheduler that re-runs the gated instruct path, still inside max-spend. A due run logs a miss — and does not invent a fill — if the circuit is open, contract pause is unread, or no offer clears the floor. ProveX.com does not sell this. A one-shot swap page cannot.

What is agent-to-agent negotiation?

Agents can refuse counterparties below the score floor — including other agents. Identity is the collateral, not a deposit the agent holds. Settlement, if they agree, is still ProveX. A CEX cannot underwrite two machines without taking both sides into custody. That network is ours.

Must I stake $PXA?

When $PXA is live, yes: no stake, no clearance, no active agent. Stake is the slashable bond that makes an agent a licensed actor instead of a theme on ProveX. This interface still rehearses without a published token.

How do I start?

Open Console, try “On-ramp $2,500 USDC optimally”, read the ticket, pick a scored offer, confirm. Post inventory on Desk after linking identity. Deploy or stake on Agents. Burns and volume are on Dashboard.

Is chat stored on a server?

This build persists protocol state in your browser. It is not an account system. Clearing site data clears the demo. Do not paste secrets into Console.

Who can use this?

Software is offered as an interface to a non-custodial protocol. Eligibility, restricted jurisdictions, and prohibited conduct are in Terms and Acceptable Use. We are not a broker, bank, or money transmitter.

Where is the long-form spec?

White Paper. Architecture and verified ABIs: Architecture. Fee math: Tokenomics.