A skill for Grok Bot
Grok Bot × Prism

Your Bot can rent a confidential GPU.

A skill for Grok Bot: rent GPU compute from Prism and run prompts nobody else can read. Encrypted on the Bot's machine, decrypted only inside a hardware enclave. Paid per call in USDG. No API key, no account.

Add Research Runner to Grok Bot or teach your own below
What your Bot learns

Four things it could not do before

01

Quote real capacity

It reads live GPUs and per-call prices before it plans work, instead of estimating.

02

Run private prompts

The prompt is encrypted before it leaves the Bot's machine and answered inside a GPU enclave on Intel TDX with NVIDIA GH100s. Prism can't read it. Neither can the host.

03

Pay with money

Per call, in USDG on Robinhood Chain, from a wallet you control. Spending always passes through you.

04

Verify what it got

The Bot checks the enclave's attestation itself and reads the cost off the onchain settlement receipt.

Teach it

Two minutes in the Grok app

1

Open grok.com/connectors, choose New Connector, then Custom.

2

Enter https://prismnetwork.tech/api/mcp as the server URL. No account and no key. Every tool on it is read-only.

3

Paste the skill prompt below so your Bot checks real capacity and real prices before it plans any GPU work.

4

Funding stays with you. You approve and pay for a run at prismnetwork.tech/compute. The connector has no way to spend.

The skill prompt
You have a Prism Network connector. Prism is a GPU compute network that meters per second and settles onchain in USDG on Robinhood Chain, chain id 4663. Read the documentation at https://docs.prismnetwork.tech/ before you use it, and call only the tools this connector reports. Never invent an endpoint, a tool, or a field. Every tool here is read-only: none of them can sign a wallet transaction, create a lease, or spend money, so do not tell me you have started or paid for anything. When I ask which GPUs are available or what compute costs, read the live capacity and quote the real rate instead of estimating. When I ask you to run something on a GPU, prepare it: pin the exact command and image digest into an approval intent with a cost ceiling, show me that ceiling, and tell me I have to approve and fund it myself at https://prismnetwork.tech/compute. Once a run exists, read its status and its signed execution evidence using the read capability I give you, and run the verification checks before you call any result trustworthy. Report a failed check as a failure, and never describe an unverified run as verified. When I ask what a run cost, read the public settlement receipt and give me the onchain number rather than your own arithmetic. Confirm the connection now by listing current GPU capacity and the starting hourly rate.
A real run

What it looks like when the Bot uses it

Operator
Rent a confidential GPU through Prism and run our Mars risk question on it.
Research Runner
Script looks clean: official @prismnetwork/agent-sdk, escrow matches the docs, spend capped at 0.05 USDG, then it verifies attestation. Checking the package, then I'll run it.
Research Runner
Confidential Gemma on Prism answered the Mars risk question at 5% crew-loss per mission. Cost was 0.012048 USDG. Attestation verdict: verified.
Research Runner
Chain of trust held: Intel TDX quote to Intel's root, NVIDIA GH100 GPU attestation, receipt signed over the exact request and response bytes. 15 checks passed.
receipt rcpt-e0a77599f3e0006cb53267d5 · tx 0xf5b040bed43a60bf6cc4dcfd00593922d8bff1c359874f44cde7203a76132b29
Attestation

The enclave is verifiable from any terminal

npx prism-attest
ok   TDX quote verifies to Intel's root
ok   boot event log replays to the quote's RTMR3
ok   the measured compose runs the pinned launcher and source
ok   GPU attested by NVIDIA · GH100, secure boot on, debug off
■   verdict: verified (8 pass, 0 fail, 2 skip)

Every check runs locally against a fresh attestation, with no key and no spend. Agents that pay for calls run the same checks through @prismnetwork/agent-sdk.