The AI Lead Qualification Agent: How It Works in Odoo and MYOB Acumatica

An AI lead qualification agent reads each new enquiry, checks it against your CRM and ERP history, scores it against criteria you wrote down, and drafts the first reply. Then it stops and waits for a salesperson to approve. That last part is the whole design, and it’s the part most vendor demos skip. With 12% of Australian businesses now using AI, and 22% of medium-sized ones per the ABS, sales teams are a common starting point, because lead handling is repetitive, time-sensitive and mostly reading.

We’ve already covered how calls and meetings become CRM records and how emailed purchase orders become draft sales orders. This post is about the step before both: deciding which of this morning’s enquiries deserve a salesperson’s attention, and in what order.

What an AI lead qualification agent actually does

The agent has four jobs, and none of them involves sending anything.

• Read. The web form, the email thread, the trade show list, the missed-call transcript. It pulls out who’s asking, what they’re asking for, and how urgent they sound.
• Check your own records first. Before it looks anywhere else, it queries your CRM and ERP. Is this an existing customer? What have they bought? Are they on credit hold? Half of qualification is history you already own, sitting in systems your reps don’t have time to cross-reference at 7am.
• Score against explicit criteria. Your rules, written down: industry, region, order size signals, product fit. Not a vibe. If you can’t explain why a lead scored 80, the score is noise.
• Draft. A first-touch reply in your voice, a routing recommendation, and a one-paragraph note on why. All of it lands in a queue.

Then a person opens the queue, approves, edits or bins. The agent proposes. The rep decides. That split matters more here than almost anywhere else, because the thing being handled is a stranger’s first impression of your business.

Scoring already shipped. Qualification is the judgement layer

If you run Odoo, part of this already exists and has for years. Predictive lead scoring is always active in Odoo CRM: a statistical model that learns from your historical won and lost opportunities and assigns each new lead a probability of success. It’s useful, it’s free with CRM, and you should switch on the optional variables that fit your pipeline.

But it’s statistics, not judgement. Predictive scoring won’t read the enquiry, won’t notice the sender is an existing debtor sixty days overdue, and won’t draft a reply. It ranks what’s in the pipeline based on what fields the record carries. An agent sits on top of that layer and does the reading. The two stack well: the model supplies a probability, the agent supplies the context and the draft, and a person supplies the decision.

What’s shipped today in Odoo and MYOB Acumatica

Here’s the current state, labelled honestly.

Odoo 19, shipped. We verified this in the v19 Enterprise source code. Odoo ships an AI lead-creation topic for its agents: the website or livechat assistant can collect a visitor’s name, email and phone, confirm the details, and create a CRM lead, with strict instructions to do it exactly once and never to promise follow-up until the record actually exists. That’s inbound capture with sensible guardrails, live today. Odoo’s documentation also confirms agents act within the signed-in user’s access rights, which is the permission model you want. What Odoo doesn’t ship yet is the outbound half: scoring against your written criteria and drafting replies is wiring you add through its agent tools or an external agent over the API.

MYOB Acumatica, preview. The CRM handles lead records, assignment rules and pipeline today, all deterministic. The AI layer, AI Studio, is in technology preview in the 25 R2 release, built with AWS and Anthropic with data processed in local data centres. In the preview, agents run when a user asks and can’t create records on their own. General availability is planned for 26 R1 with no committed ANZ date, and globally, Acumatica’s 2026 R1 shipped its AI Assistant under managed availability in March 2026. Global features typically reach the ANZ product 6 to 9 months later.

The fair comparison. Microsoft is ahead of both here. The Sales Qualification Agent in Dynamics 365 reached general availability in October 2025 and runs in two modes: research-only, and research-and-engage, where the agent contacts prospects itself. It’s a capable product. We’d still tell you to run the first mode and not the second, for reasons the next two sections cover.

A Monday morning, worked through

This is the pattern as we’d build it for a Queensland wholesaler, drawn from what actual prospects keep asking us for.

Twenty-two leads arrived over the weekend: web forms, a trade show spreadsheet, four plain emails. By 7:30am the agent has matched six to existing accounts in the ERP. Two are current customers asking about a product they already buy, so it flags them for the account manager rather than the new-business queue. One is a customer on credit hold, flagged with a note to sort the account before anyone quotes them something new. The rest get scored against the written criteria, and eleven get a drafted reply. One enquiry the agent can’t confidently read, so it escalates with “a human should look at this” instead of guessing.

At 8am a rep opens the queue with coffee. Nine drafts approved as-is, two rewritten because the tone missed, one binned because the agent scored a student research project far too generously. Nothing was sent before a person hit approve, and the rep’s whole part took less time than the first two leads would once have.

“The agent is good at the reading and the arithmetic, and it never gets bored on lead eleven. What it doesn’t own is your reputation. The moment drafts start sending themselves, you’ve handed a stranger’s first impression of your business to a system that can’t be embarrassed.”

Josh Craig, Director, Auboros

The Australian rules your first-touch drafts have to follow

This is where the approval gate stops being a preference and becomes protection.

Commercial emails and SMS in Australia sit under the Spam Act, and the ACMA’s rules are specific: you need consent, express or reasonably inferred, you must identify your business, and every message needs an unsubscribe that works, actioned within five business days. Someone who emailed you asking about a product has plainly invited a reply. A trade show list from two years ago is a different story, and it’s exactly the kind of list an over-eager automation will happily work through. The ACMA is also clear that you can’t outsource the obligation: if your agent sends it, your business sent it.

Privacy runs alongside. A lead’s name, email and behaviour are personal information under the Australian Privacy Principles, and that doesn’t change because an agent did the collecting or the enriching. We covered the broader control set, permissions, audit trails and the December 2026 disclosure deadline, in our guide to AI agent governance.

Failure modes worth designing for

We run agents over our own operations, drafts-first, and the failure modes are predictable enough to plan around. Research errors are the big one: two businesses share a name, and the agent confidently attributes the wrong size and industry to your prospect. That’s why the draft carries its reasoning, so a rep can see the error before it shapes a reply. Score inflation is the quiet one: agents reward enthusiasm rather than fit, and a keen student can outscore a terse procurement manager. Written criteria and a monthly look at what the agent got wrong keep the scores honest. Language models make mistakes. The design assumes it, which is why nothing sends itself.

Where to start

Start read-only. Two weeks of the agent scoring and drafting into a queue nobody sends from, while your reps work normally. Compare its calls with theirs. If it earns trust, switch on approved sends. If a vendor suggests skipping straight to autonomous outreach, ask them who answers to the ACMA when it goes wrong, because it won’t be them. Odoo users should also look at what Odoo CRM already does out of the box before adding an agent to it, and our AI agent services page covers how we scope this pattern, drafts-first, with role-scoped permissions.

---

Thinking about pointing an AI agent at your lead queue?

Auboros builds drafts-first qualification agents over Odoo and MYOB Acumatica from Brisbane, with the scoring criteria written down and a rep approving every send. If you’d like to see what the pattern looks like on your pipeline, book a free consultation. We’ll tell you honestly whether your lead volume justifies it.