The AI Supplier PO Chasing Agent: How It Keeps Deliveries Honest in Odoo and MYOB Acumatica

Updated 13 October 2026: added the short answer, an At a glance agent spec, four question headings and a captioned table of who does what; the Odoo section now reflects Odoo 20 (released 24 September 2026), including the AI Purchase module in its Enterprise source; the MYOB Acumatica section now cites MYOB’s current AI feature list in place of the 2025 preview announcement; the Acumatica business events example was corrected to the one Acumatica actually published; the ABS figure was re-sourced to the 25 June 2026 release; “Goes well with” was added. The worked example and Bill’s quote are unchanged.

An AI supplier PO chasing agent reads your open purchase orders, drafts follow-up emails for unconfirmed or overdue lines, reads the suppliers’ replies and proposes new receipt dates. A buyer approves every send and every date change. As at 13 October 2026, Odoo 20 ships a scheduled receipt reminder and MYOB Acumatica ships business events. Neither lists a feature that reads the reply.

At a glance

• Who it is for: purchasing managers, buyers and owners of Australian wholesale, distribution and manufacturing businesses on Odoo or MYOB Acumatica whose promised dates drift without anyone updating the system.
• Problem it solves: supplier chasing gets done late and in a rush, and the reply that changes a delivery date sits in an inbox while the ERP still shows the old one.
• Platforms: Odoo 20 and Odoo 19 (Purchase, Inventory) and MYOB Acumatica (purchase orders, business events). The agent is built alongside either platform and reads through its API under its own login.
• Trigger: a morning run over open purchase orders and the purchasing inbox, plus any supplier reply that arrives during the day.
• Inputs read: open PO lines with promised and expected receipt dates, supplier email threads, the sales orders and production orders waiting on each line, and each supplier’s delivery history.
• What the agent drafts: follow-up emails specific to the order, proposed receipt date changes with the supplier’s sentence quoted underneath, and a ranked list of late orders by what is waiting on them.
• Approval gate: a buyer approves, edits or deletes every email before it sends and every date change before it lands in the ERP.
• Audit trail: each draft keeps the PO lines it read, the supplier sentence it relied on and the buyer’s decision, logged under the agent’s own credentials.
• Typical cycle time: the queue is ready before the buyer starts; the review in the example below takes about half an hour for forty open POs.
• What it never does: send an email on its own, change a receipt date without approval, cancel or amend a PO, or contact a supplier who has already replied.
• Typical cost: a pilot or proof of concept from $5,000 ex GST, per the AI agents for ERP in Australia hub as at 13 October 2026; the agent’s login is a paid seat on both platforms.
• Typical timeline: discovery 1 to 2 weeks, sandbox pilot 2 to 6 weeks, drafts-first go-live 1 to 2 weeks, per the same hub page.
• Last verified: 13 October 2026 against Odoo’s 20.0 purchase source, the Odoo 20 Enterprise source (AI Purchase module), MYOB’s AI feature page, Acumatica’s business events write-up and the ACMA’s guidance on outsourced messaging.

Somewhere in your ERP right now there’s a purchase order (PO) with a promised date that quietly passed last Tuesday. Nobody changed it, the supplier never confirmed it, and the first person to find out will be whoever picks the sales order that needed that stock. Chasing suppliers is the least glamorous job in purchasing, which is exactly why it gets done late, in a rush, at the end of the week.

The appetite for handing this work to software is real. MYOB reports that nearly four in five (78%) wholesale distribution businesses plan to adopt or expand the use of AI in their ERP, and the ABS release of 25 June 2026 found 12% of Australian businesses used AI in 2024-25. Supplier chasing comes up in those conversations constantly, partly because everyone hates the job and partly because the cost of skipping it is a stockout with a customer’s name on it.

What does an AI supplier PO chasing agent actually do?

An AI supplier PO chasing agent is a program that reads the open purchase orders in your ERP, works out which lines are unconfirmed, overdue or at risk, drafts the follow-up emails to those suppliers, reads the replies, and proposes the date changes so your system reflects what the supplier actually said. In a drafts-first design, that’s where its authority ends. A buyer approves every email before it sends and every date change before it lands, the same way we build every agent pattern in our AI agents for ERP in Australia practice.

The reading is the point. Plenty of tools can fire a reminder on a schedule. The chasing job is only half done when the email goes out; the other half is understanding “should be on the truck end of next week, the 40-footers are held up” and turning it into a proposed new receipt date, a flagged short shipment and a note on the record. That’s judgement work, and it’s the part language models are now good enough to draft, though not to own.

What do Odoo and MYOB Acumatica already do without an agent?

Before you buy an agent, switch on what you already pay for. Here is the state of each platform as at 13 October 2026, with shipped and not-shipped kept apart.

Odoo

Odoo 20, released on 24 September 2026, keeps the receipt reminder on the vendor record that Odoo 19 has: tick it and Odoo emails the supplier a set number of days before the expected receipt date, asking them to confirm the exact date. It’s part of the standard purchase module (the field is right there in Odoo’s 20.0 source code), and together with the purchasing module’s RFQ and 3-way matching workflow it covers a decent share of the routine chasing.

Odoo 20 Enterprise also adds a module called AI Purchase. We read it in the Enterprise source on 13 October 2026, and it is small: it installs one sample prompt in the AI composer, a plain-language lookup of the latest purchase order from a named vendor. It contains no skill that chases a supplier, reads a reply or changes a receipt date. So Odoo 20 lets a buyer ask about purchase orders in plain language, and the chasing itself is still the scheduled reminder. An outside agent can read purchase orders through the Odoo 20 MCP server; that post covers who the connection runs as and how to keep writes behind a person.

MYOB Acumatica

MYOB Acumatica comes at it through business events, which watch a generic inquiry and act when a condition is met, with no code. Acumatica’s own write-up gives a purchasing example: email the purchasing manager seven days before goods are due so they can confirm delivery with the vendor. The same mechanism can run on a schedule over late purchase orders.

On the AI side, MYOB’s AI page lists eight features as at 13 October 2026, including AP Bill Entry for incoming supplier bills, Anomaly Detection across supplier invoices and transactions, and AI Automation for workflows such as approvals, document processing and notifications. None is described as following up suppliers or reading their emails. Our MYOB Acumatica AI guide covers what each feature does.

Where both stop

Both are useful, both shipped, and both run on a rule. They send on a schedule and they don’t read the answer. If the supplier replies “we can do half of it Thursday”, that email sits in someone’s inbox until a person deals with it. Anything that reads supplier replies and proposes date changes is wiring you add, not a feature you switch on.

Where the agent layer starts: reading the replies

The agent’s job begins where the reminders stop. Each morning it reads the open PO list and the purchasing inbox, and prepares three kinds of drafts.

• Chaser drafts. For unconfirmed or overdue lines, it drafts a follow-up in your tone, specific to the order: line numbers, quantities, the date you were promised. Suppliers with a reply already sitting in the thread don’t get chased again, which is the mistake a dumb schedule makes every time.
• Date change drafts. Where a supplier has replied, it extracts the new commitment and proposes the updated receipt date against the right lines, with the sentence it relied on quoted underneath so the buyer can check its reading in five seconds.
• Risk flags. It ranks what’s left by consequence, not by age: which late orders have sales orders or production waiting on them, which suppliers have a habit of optimistic promises, and which delays are worth escalating from a polite chaser to a phone call.

Those proposed dates matter well beyond purchasing. Your reordering logic runs on lead times, and stale receipt dates quietly poison it. A replenishment agent drafting purchase orders from bad dates just automates the shortage. Chasing is the pattern that keeps the rest of the data honest. Once a corrected date is in the ERP, the inventory exception agent is the one that works out what a late container does to stock across your warehouses.

“The email is the easy bit. The judgement is knowing which three of your forty late orders will actually hurt you this week, and reading what the supplier really committed to, which is usually less than the sentence sounds like. That’s what the agent drafts. What it never does is decide on its own that a date moved.”

Bill Alvarez, Practice Manager, Auboros

A Thursday 4pm run, approval gates included

Here’s the shape of it in a wholesale business running about forty open POs. The buyer opens the queue the agent prepared. First, eleven chaser drafts: nine approved as written, one reworded because the supplier relationship is delicate, one deleted because that supplier phoned this morning. That’s gate one, and it took about eight minutes.

Next, four date change proposals from replies received overnight. Three quote the supplier’s sentence cleanly and get approved. On the fourth the supplier wrote “next week” on a Friday, and the agent guessed the earlier Monday; the buyer corrects it to the following Wednesday and approves. Gate two. Nothing touched the ERP until she did.

Last, one escalation flag: a supplier twelve days late on the order feeding your biggest customer’s backorder, with a drafted note to the account manager referencing the past three late deliveries. The buyer approves the note and decides to ring the supplier herself as well. Gate three. Half an hour, ten supplier emails, four date changes, one phone call. The agent did the reading; the buyer did the deciding.

Can an AI agent email suppliers without approval in Australia?

It can, technically. We’d tell you not to let it, and the accountability rules are part of the reason. Emails to suppliers are business correspondence, but the ACMA’s position on electronic messages is blunt: businesses cannot outsource their obligations under the spam and telemarketing laws, so if the agent sends it, your business sent it. And if a chaser ever drifts into promoting your products, you’re into Spam Act territory with its consent and unsubscribe rules, so keep the drafts factual and about the order. Your supplier contacts are also people: names, direct emails and mobile numbers are personal information under the Australian Privacy Principles, whether a person collected them or an agent did.

Inside the system, the guardrails are the usual ones and they’re not optional. The agent runs under its own named account with read access to purchasing and draft rights only, every draft and decision is logged, and the approval gates sit on both sends and date changes. We’ve written up the full control set, permissions, audit trails and the 10 December 2026 privacy policy deadline in our guide to AI agent governance.

What goes wrong, and how do you start?

The failure mode that keeps us disciplined is the hallucinated commitment: the agent records a delivery date the supplier never actually gave. It’s why every proposed change carries the quoted sentence it was based on, and why a buyer reads it before it lands. The second is over-chasing, because a reminder sent to a supplier who already answered damages the relationship at machine speed; suppression rules and the approval gate catch it. The third is optimism laundering, where “should be fine” becomes a confirmed date. Language models make mistakes, and the design has to assume it.

Start read-only. Run the agent for two weeks drafting into a queue nobody sends from, and compare its reading of the inbox against what your buyers actually did. If it earns trust, switch on approved sends and approved date changes, and nothing more. The same rule we apply to channel sync agents applies here: an agent with unattended write access isn’t faster, it’s just wrong in more places at once.

Goes well with

• The AI replenishment agent: once receipt dates can be trusted, the agent that drafts the next purchase orders from them.
• The AI accounts payable agent: what happens when the supplier’s bill arrives and has to match the order and the receipt.
• What an AI agent costs to run in Australia: the seats, tokens and review time behind the pilot figure above.

Late deliveries finding you before your system knows?

Auboros builds drafts-first supplier chasing agents over Odoo and MYOB Acumatica from Brisbane, working across Queensland and beyond. We start with the reminders your platform already ships and add the agent only where it earns its place.

If your buyers spend Friday afternoons chasing suppliers, book a free consultation. We’ll tell you plainly whether the native tools get you most of the way there.