> For the complete documentation index, see [llms.txt](https://docs.bloxchain.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bloxchain.app/developers/ai-prompts.md).

# AI prompts

Copy-paste context for coding agents (Cursor, Claude, etc.) working on Bloxchain integrations.

## System context (short)

```
You are integrating with Bloxchain Protocol — governed Ethereum smart accounts.

Rules:
- Authorization is ON-CHAIN (RuntimeRBAC, SecureOwnable, GuardController). SDK and UI cannot bypass denial.
- Transactions use EngineBlox TxRecord lifecycle: request → (timelock) → approve → execute.
- Meta-transactions: approvers sign EIP-712 off-chain; Broadcaster submits on-chain.
- Pin @bloxchain/sdk and deployed contracts to the same Protocol release tag.

Canonical docs: https://docs.bloxchain.app (llms.txt for index).
Imported API: /protocol/api-reference, /protocol/runtime-rbac, /protocol/guard-controller.
```

## Task: read contract state

```
Task: Read Owner, Broadcaster, Recovery, and pending TxRecords for Account at {ADDRESS} on {CHAIN}.

Use @bloxchain/sdk wrappers: SecureOwnable, RuntimeRBAC, GuardController.
PublicClient only for reads. Match ABI to the Protocol release tag we deployed.

Reference: /protocol/secure-ownable, /protocol/runtime-rbac, /developers/sdk-core-patterns
```

## Task: submit a governed transfer

```
Task: Request an outbound transfer through a registered operation schema.

1. Confirm wallet has REQUEST permission on the operation (RuntimeRBAC).
2. Target must be on GuardController allowlist.
3. Call request path; wait for releaseTime if timelock applies.
4. Separate wallet approves; execute per schema (or Broadcaster meta-tx path).

Do not skip timelock on delayed approval paths. Meta-tx approval paths do not enforce releaseTime.

Reference: /introduction/operational-model, /protocol/meta-transactions, /protocol/best-practices
```

## Task: security review

```
Task: Review this integration for Bloxchain security invariants.

Checklist:
- Least privilege per role; Owner/Broadcaster/Recovery not reused as day-to-day operators
- SDK + contract versions pinned to audited tag
- Allowlists minimal; schemas registered before production
- Meta-tx: correct EIP-712 domain (verifyingContract = account address), nonce handling
- No trust in off-chain policy or app backend for authorization

Reference: /security/security-model, /security/security-review-guide, /protocol/best-practices
```

## Task: Console parity

```
Task: Replicate a Console workflow in the SDK.

Map UI areas to on-chain actions:
- Roles/Members → RuntimeRBAC role grants
- Permissions → function permission bitmaps per role ([Permissions](../platform/configure/permissions.md))
- New request / Approve → TxRecord phases
- Security settings → SecureOwnable protected roles

Console guides: /platform/start
```

## Upstream protocol docs

When the portal paraphrases, prefer imported pages under `/protocol/*` for facts. Advance pin: [Releases — protocol documentation pin](/resources/releases.md#protocol-documentation-pin).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.bloxchain.app/developers/ai-prompts.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.