Sequence Agentic - Money movement for AI agents
by•
Sequence is the financial execution layer for AI agents.
Unlike read-only tools, your agent uses the Sequence API to send, split, and route real money across all your bank accounts, cards, apps, and loans. Scoped API keys mean agents never hold your credentials, server-side spending limits keep you in control, and full audit trails log every action. The infrastructure is battle-tested in production on regulated rails, moving north of $3B. One-call integration from Claude, n8n, Zapier etc.
Replies
How does scoped key isolation actually work when an agent needs to move funds between two of my accounts that share a login, do you set up separate sessions per task or is it one persistent auth context with per-call limits layered on top?
@abanaltmgzpk You have three guardrail systems you can use:
Agent-key scope: in advance, setup multiple keys per-task. Each key contains his set of source and destination accounts, with his amount limitations (which can both be set on the key, or limited by using a sub-account for source, only funding it as much as you want to allow the agent to use). Give each agent a key according to his job-to-be-done. Connect each agent only with the key you want it to have.
Configuration scope: use our rules framework to set up a deterministic configuration. This configuration allows money movement, in a simple "if-else" framework. There you can give statements like "only move money if my checking account balance is above 500$", or "pay for my card debt upto 300$ a month", or "top up the emergency funds sub-account up to 400$". Give your agent only the ability to trigger these rules, so it cannot go crazy.
How does the audit trail handle things like partial failures when a split payment has 4 legs and leg 3 fails halfway through?
@nurgldurmalgvw When you trigger a split payment, the rule runs asynchronously, creating a "rule execution" entity. You can track the rule execution, getting a report of all payment legs and their statuses.
If a payment failed, the consolidation is a business decision, and it is up to you to decide what to do about it. We send notifications, and our API provides full visibility for you to make these decisions.
Finally got my agent to split rent across three cards without me babysitting it. The audit trail alone sold me on trusting it with anything beyond pocket money.
Finally got tired of copy pasting routing numbers and this just handled it from my agent in seconds. Scoped keys feel genuinely safe compared to the screen scraping hacks I've been patching together.
Scoping each API key to specific accounts and limits feels like the right move for letting agents touch real money, and the audit trail is a nice touch. Honestly impressed it just plugged into my n8n flow with no fuss.
finally got my cursor agent to actually move money between accounts, the scoped keys and spending limits make it feel way safer than i expected
The scoped keys and server-side limits make this feel more realistic than asking an agent to please behave around money. Approved invoice payments, vendor reimbursements, and tax-bucket transfers seem like narrow first use cases where audit trails can stay clean. Which workflow are you seeing customers most comfortable handing to an agent first?
finally a way to stop babysitting my bots every time they touch a card. the scoped keys and audit trail actually feel like they were built by someone who got burned before.
how does the auth model actually work in practice, like can my agent move money between two banks I own without me re-approving each transfer or is there a manual confirm step every time?
@hediyesarimkkz Depends on the scope you gave your agent for transfers. You can do both.
Putting the spend limits in the key server-side instead of in the prompt is the right call — the scoped-key answer above is the only thing that actually holds when an agent's reasoning goes sideways. The operator edge case I'd want pinned before wiring an agent to live money is retries: if an agent fires a transfer, times out, then retries, is there an idempotency key so it doesn't double-send? And for an in-limit but wrong transfer, is there any reversal/clawback window, or is it final on execution?
@hazy0 We have idempotency tokens and recommend using them just for this case.
Reversal process is according to standard banking timing limitations, and can currently be done via our support.
That's the reassuring answer on idempotency — glad it's a first-class token and not a client-side dedup hack. The reversal path is where I'd still want more than support-ticket recourse for an agent moving money 24/7: is there a programmatic hold window where a transfer above a threshold sits pending for a configurable delay before it settles, so an automated check or a human can cancel it via API before funds actually move? Chasing a clawback after execution doesn't really scale for autonomous spend.