The AI Credit Management Agent: How It Works Inside Odoo and MYOB Acumatica

Updated 21 September 2026: added the short answer, an At a glance agent spec, five question headings and a captioned table of the payment-behaviour signals the agent watches; the MYOB Acumatica section now names the credit verification rules, dunning letters and Manage Credit Holds forms from MYOB’s own documentation instead of the global Acumatica marketing page; the Odoo 19 section adds the WhatsApp follow-up channel and the read-only Ask AI agent; “Goes well with” added. The worked example, the guardrails and Bill’s quote are unchanged.

An AI credit management agent reads aged receivables, payment history and open orders in Odoo or MYOB Acumatica, spots customers whose payment behaviour is changing, and drafts the reminder, the credit-limit recommendation and the call sheet. A person approves every send and every hold. Both platforms ship rule-based credit controls today; the agent is the judgement layer above them, like all our AI agents for ERP in Australia.

At a glance

• Who it is for: finance and credit teams on Odoo or MYOB Acumatica with a few hundred to a few thousand trade debtors, usually wholesale, distribution or B2B services, where the aged receivables report keeps growing and the chasing isn’t keeping up.
• Problem it solves: the aged trial balance tells you who is overdue today. It doesn’t tell you which customer has drifted from paying in 30 days to paying in 60 while doubling their orders, and that trend is what precedes most bad debts.
• Platforms: Odoo 19 Enterprise (follow-up levels, payment terms, the read-only Ask AI agent); MYOB Acumatica 2025.2 and 2026.1 (credit verification rules, dunning letters, Manage Credit Holds, Anomaly Detection); any external agent connected through the platform’s API under its own user account.
• Trigger: a scheduled overnight run after the day’s receipts are reconciled, plus an on-demand run before the weekly credit meeting.
• Inputs read: open customer invoices and their due dates, receipts and part payments, each customer’s days-to-pay history, open sales orders and their value, credit limits and current credit status, disputes logged against invoices, and the notes from the last follow-up.
• What the agent drafts: a risk flag with the evidence behind it, a reminder email written for that customer and those invoices, a credit recommendation (reduce the limit, ask for a part payment before release, or hold), and a prioritised call sheet for the credit controller.
• Approval gate: the credit controller reads, edits, approves or rejects each draft in the ERP. Nothing reaches a customer and no account changes status until a named person has looked at it.
• Audit trail: every recommendation is stored with its inputs, its reason, who approved or rejected it and when, alongside the ERP’s own chatter or document history, so the question “why did this account go on hold in March” has an answer in June.
• Typical cycle time: the controller’s review of the overnight drafts, usually before the first customer calls. How long that takes depends on how many accounts trip a signal, which is the first number a pilot measures, so we leave the figure out until your data supplies it.
• What it never does: send a reminder, place or lift a credit hold, change a credit limit or payment terms, write off a debt, contact a customer by phone, or log in as an administrator.
• Typical cost: a single scoped agent pilot typically starts from a few thousand dollars ex GST for discovery and sandbox build, per our AI agents for ERP in Australia page.
• Typical timeline: 4 to 10 weeks from discovery to a drafts-first go-live, per the same page.
• Last verified: 21 September 2026 against Odoo’s 19.0 follow-up documentation, MYOB Acumatica’s Customers form reference, MYOB Acumatica’s Manage Credit Holds form reference and the ACCC and ASIC debt collection guideline.

Chasing late payments is nobody’s favourite job, and it’s one of the first places Australian businesses ask us about AI agents. The work is repetitive, the data already sits in the ERP, and doing it badly shows up as a cash flow problem within a quarter.

The word drafts matters. In every design we build through our AI agent services, the agent proposes and a person approves. Nothing reaches a customer, and no account goes on hold, until a human has looked at it. This post covers what a credit management agent actually does, what your ERP already handles without any AI, and the guardrails that keep automated collections on the right side of Australian rules.

What does an AI credit management agent actually do?

Think of the agent as a credit officer’s assistant that never gets bored of the aged receivables report. Five jobs, roughly in order of value:

• It watches behaviour, not just balances. An aged trial balance tells you who is overdue today. The agent tracks the trend underneath: a customer who has drifted from paying in 30 days to paying in 55 over six months is a bigger risk signal than a single invoice a week late.
• It flags risk early. Part payments where full payments used to arrive, a broken payment promise, orders growing faster than the payment record justifies. These patterns are visible in ERP data long before an account lands in the 90 day column.
• It drafts the follow-ups. Instead of a template blast, the agent writes each reminder with context: the invoices involved, the customer’s history, what was agreed last time. A person reads, edits and sends.
• It recommends credit decisions. When a customer trips a risk threshold, the agent drafts the recommendation: reduce the limit, ask for prepayment on the next order, or place the account on hold. The decision stays with a human, because a wrong hold blocks a real order from a possibly loyal customer.
• It prepares the credit call sheet. Each morning the credit controller gets a prioritised list: who to call, what they owe, what they said last time, and a suggested talking point. That’s an hour of report wrangling replaced with judgement work.

What does your ERP already do without AI?

Here’s the part most AI content skips: a good share of credit control is already built into the ERP you own, and it isn’t AI at all.

Odoo 19 ships follow-up levels that schedule payment reminders by days overdue, escalate through email, WhatsApp, SMS or post (the WhatsApp, SMS and letter channels use in-app purchase credits), attach the overdue invoices, and can run automatically once the level is set to Automatic. Each level can also schedule an activity for a responsible user, and the chatter keeps a record of every reminder sent. That’s shipped functionality today, no AI involved. The Ask AI agent that ships with Odoo 19’s AI app can answer questions about overdue customers from search and grouping tools, and it changes nothing; we cover what it can and can’t do in our guide to AI agents in Odoo.

MYOB Acumatica’s credit control is on the customer record. The Customers form carries a credit verification rule per customer: Days Past Due, Credit Limit, Limit and Days Past Due, or Disabled, with the limit and the allowed days past due set alongside, and a parent account’s credit policy can be shared across its child accounts. Overdue invoices feed dunning letters, and the Manage Credit Holds form places customers who have received the final dunning letter on credit hold, which stops new sales orders, and lifts the hold once they’ve paid. Overdue charges can be calculated on top. On the AI side, MYOB’s AI features page lists Anomaly Detection, which learns what normal looks like across transactions and flags the unusual ones, and an AI Assistant that answers plain-language questions about customers and invoices; both read and flag, neither chases. Our MYOB Acumatica AI guide covers the full list and the version each feature landed in.

If none of that is switched on in your system, start there. A surprising share of “we need AI for collections” conversations turn out to be “nobody ever configured follow-up levels” or “every customer is set to Disabled”. The agent belongs on top of a working process, not instead of one.

Where does the agent earn its keep?

Rule-based dunning treats every overdue invoice the same. Day 7 gets email one, day 14 gets email two, day 30 gets the stern letter. That works until it doesn’t: your biggest customer gets the same stern letter as a habitual non-payer, over a $180 invoice they’ve already disputed.

The agent’s job is the judgement layer. Here’s a worked example from the pattern we design for wholesale and distribution businesses.

Overnight, the agent reads the aged receivables, payment history and open orders from the ERP under its own read-only login. It notices a customer whose average days to pay has moved from 32 to 61 across the last five invoices, while their order volume has nearly doubled. Exposure is growing while payment performance is falling, which is the pattern that precedes most bad debts.

By 7am, the credit controller has three drafts waiting: a reminder email referencing the specific invoices and the customer’s usual payment pattern, a recommendation to ask for a part payment before releasing the two open orders, and a note for the account manager, since the growth story might justify a different conversation. The controller softens the email, approves the part payment condition, rejects the hold, and it’s all done before the first coffee. The agent wrote everything. It sent nothing and decided nothing.

“The aged receivables report never tells you the story. The agent’s job is to read five reports at once and say: this account has changed. A person still decides what to do about it, and that’s how it should be.”

Bill Alvarez, Practice Manager, Auboros

One practical detail for Odoo sites: the agent’s login is a real internal user with an API key, and on Odoo’s pricing that means a paid seat on the Custom plan, the one that includes the external API. Budget for it, scope it to customer, invoice and payment data, and never give it the administrator group. On MYOB Acumatica the agent uses the REST API under its own user, with the API licence tier decided by call volume. Our post on MCP for ERP covers how to scope the key on each platform.

Is it legal to use AI for debt collection in Australia?

There is no ban on using AI in collections, but collections is regulated conduct, which is a concrete reason to keep humans in the loop and not a nice-to-have.

• Debt collection conduct rules. The ACCC and ASIC publish a joint debt collection guideline covering how, and how often, debtors may be contacted. An unsupervised agent firing reminders on a loop could cross lines a person wouldn’t. Draft and approve keeps contact frequency and tone under human control.
• Privacy. Payment histories are personal information when your customers are sole traders or individuals, so the Australian Privacy Principles apply to how that data moves through any AI workflow; the OAIC’s guidance on commercially available AI products is the place to start. From 10 December 2026, privacy policies must also disclose the kinds of substantially automated decisions that significantly affect people, and a credit decision is a textbook example. One more reason the agent recommends and a person decides.
• Approval gates on anything that acts. Credit holds, limit changes and every outbound message pass through a person. A clumsy reminder is embarrassing; a wrong credit hold stops a genuine order and sours a relationship you spent years building.
• An audit trail. Every recommendation the agent makes, and every approval or rejection, gets logged. When someone asks in June why a customer went on hold in March, there’s an answer.

How do you start without betting your ledger?

The rollout pattern we use for reconciliation agents applies here almost unchanged.

Run the agent read-only for the first month, observing and reporting, so you can judge its risk flags against what your credit controller already knows. Test in a sandbox before it touches production data. Scope its ERP login to customer, invoice and payment data and nothing else, the same role-scoped permissions approach we recommend for every agent. Then switch on drafting, keep every approval human, and review a sample of its recommendations weekly. Record the agent, its owner, its permissions and its approval gate in your AI agent register before it runs for the first time.

None of this waits on vendor roadmaps. Our own practice runs the read, analyse, draft pattern with external agents working through each platform’s APIs under scoped logins, and the same pattern feeds the virtual CFO agent when the question moves from “who do we chase” to “what is our debtor exposure doing this quarter”.

Goes well with

• How to scope an agent’s ERP login and approval gates, for the permissions question that comes next.
• The AI reconciliation agent, which clears the receipts the credit agent depends on.
• MCP for ERP: how an agent connects to Odoo or MYOB Acumatica, for the “how does it actually plug in” question.

Thinking about a credit management agent for your business?

We design drafts-first credit control agents over Odoo and MYOB Acumatica from Brisbane, with role-scoped access and human approval on every send and every hold. If the aged receivables report keeps growing and the chasing isn’t keeping up, book a free consultation. We’ll tell you what’s worth automating and what your ERP already does out of the box.