Execution lifecycle
The required Mattheus lifecycle from user intent through receipt and position updates.
Short answer
Every AI-prepared execution moves through intent, structured action, adapter payload, preview, checks, simulation, policy validation, approval, signing, broadcast, receipt tracking, and portfolio updates.
Manual approval required
Execution-capable workflows must show a preview, pass checks, and wait for user approval before signing or broadcast.
Block on failed checks
Failed balance, allowance, liquidity, simulation, policy, address, signer, or receipt tracking checks block execution.
Who This Is For
Anyone implementing or auditing Mattheus execution-capable flows.
Before You Begin
- A Mattheus account for live integration
- A supported protocol/action for execution-capable flows
- Configured policy and approval settings for live actions
Answer engine brief
Mattheus overview
Mattheus is a private AI trading workspace for researching markets, testing reproducible strategies, reviewing portfolio context, and preparing governed actions. Developers can connect through REST APIs, SDKs, and MCP while account authority, policy checks, and approvals remain separate.
Does Mattheus require approval before execution?
Yes. An interactive request requires an exact short-lived one-time approval confirmed with fresh wallet reauthentication. API-key automation requires a separately activated, scoped agent session. Both paths still require wallet or signing readiness and policy checks.
Which markets are documented?
The active launch documentation covers Hyperliquid market data, paper trading, and gated Live workflows. Each page states whether an example is read-only, simulated, paper, or eligible for approval-gated Live execution.
How does policy-gated execution work?
Execution-capable requests are preview-first and must pass wallet readiness, protocol certification, feature gates, idempotency, configured policy controls, and either an exact interactive approval or a bounded API-key agent session before any live action.
Can users revoke permissions?
Users should be able to revoke supported scoped permissions and API keys. Documentation should keep stop, cancel, revoke, and policy rejection paths clear before users approve live execution.
Example
What this example does
Follow this example in order. Read the expected result below before connecting it to a live account or execution-capable workflow.
Plain-language walkthrough
- 1
Step 1
User expresses intent.
- 2
Step 2
AI converts intent into a structured execution action.
- 3
Step 3
Protocol adapter builds the transaction or order payload.
- 4
Step 4
System generates a preview.
- 5
Step 5
System validates balances, allowances, liquidity, routes, and market availability.
- 6
Step 6
System simulates the transaction or order where applicable.
- 7
Step 7
Policy controls validate configured limits.
- 8
Step 8
Approved-address and allowed-contract validation passes.
- 9
Step 9
User manually approves the exact preview.
- 10
Step 10
Signing happens only after approval.
- 11
Step 11
Backend broadcasts or submits the action.
- 12
Step 12
Receipt, fill, or order status is recorded.
- 13
Step 13
Portfolio and positions update.
- 14
Step 14
User can stop, cancel, or revoke where the protocol supports it.
Expected result
Common errors
- Preview rejected: balances, allowance, liquidity, route, simulation, policy, or approved-address checks did not pass.
- Approval required: an interactive request has no approved, unexpired, exact one-time approval artifact, or an API-key request has no active scoped agent session.
- Approval mismatch: execution must reject if the payload changed after the preview was approved.
- Approval unavailable: approval state could not be verified or consumed atomically, so execution remains blocked.
- Policy blocked: configured limits blocked the action before signing or broadcast.
Safety note
The AI can prepare and explain actions, but approval, policy, and signing boundaries remain mandatory for execution-capable workflows.