Overdue invoices past 60 days climbed from your ~$61K baseline to $87K, concentrated in 9 accounts. Three of those are on payment plans that haven't posted in 30+ days.
An agent watches one thing and acts on it. Not a workflow, just a standing watch that usually does nothing and acts the moment it should.
An agent does what you'd do, and only what you've authorized.
It acts on the same governed metrics as your dashboards, and every action is logged and traceable.
It alerts and recommends on its own; anything that changes data is yours to approve.
Point a new agent at a throwaway channel and watch its judgment before it touches anything real.
It remembers what it already flagged and waits before acting again, so it won't alert you about the same thing twice.
It reconciles your journal entries and cash movements against your payment processor and bank data, and flags the gaps before month-end. The P&L on your board deck ties out to the cash that actually landed, so you never present a number you have to walk back.
When your AR aging breaks its trend, it tells you which invoices are overdue, which contacts are slipping, and how much cash is at risk. It lines up the follow-up for you to approve before an overdue invoice becomes a collections problem.
When T&E spend spikes or a purchase order lands outside normal ranges, it surfaces the line items, the employees or vendors involved, and the account impact. You see the anomaly the day it posts, not when you're reviewing the quarter.
Beyond alerts and write-backs, an agent can run arbitrary Python, so it can do whatever the task actually requires: call an API, kick off a job, reshape the data, or wire into your own tooling. The action space is yours to define.
You could rig one of these with a cron job and a Slack webhook in an afternoon. The watching is the easy part. Here's what you'd own forever, and don't, here:
Every Xero object, modeled and query-ready the moment you connect.
It runs on your real Xero org (partial reconciliations, manual journals, multi-currency messiness and all), not a tidy demo.
A message in the channel you choose, with the context and a button to act on it.
A summary in the inbox of the people who need to see it.
A payload to your own systems, to wire the agent into whatever you already run.
A flag written back to your warehouse for everything downstream to pick up.
Kick the question to Fi to investigate the why and propose the fix.
Expose it to your own agents and tools over MCP, and drive it from your stack.
Run it in your own VPC or fully self-hosted. Everything it does is pure SQL and Python you can inspect.
Fi is your AI analyst. It helps you build and customize everything in Definite, including the agents that watch and act.
Your AI analyst. Ask questions in plain English, and let it help you build and customize everything in Definite, including your agents.
Meet Fi →The watchers and actors. Once you've built one, it runs on its own, keeping an eye on what matters and acting the way you would.
Autonomous agents →