The AI Call Logging Agent: How Calls and Meetings Become CRM Records in Odoo and MYOB Acumatica
What an AI call logging agent does with sales calls and Teams meetings in Odoo and MYOB Acumatica, Australia's recording rules, and who approves each note.
By Josh Craig, Director, Auboros · · Updated
Sales managers rarely complain that the CRM holds too much information. The usual problem is the opposite. Calls happen, deals move, and the record shows a one-line note from three weeks ago that says “spoke to the customer, going well”. When the rep leaves, the pipeline leaves with them.
An AI call logging agent is a program that takes a recorded call or meeting, drafts the CRM record for it (a summary, the follow-up tasks, an update against the right opportunity) and waits for the person who was on the call to approve it before anything saves. The typing disappears. The responsibility doesn’t.
This is one of the most requested agent patterns we hear about from Australian businesses, and one of the easier ones to run safely, because everything it writes is a draft until someone confirms it. Here’s how it works over Odoo and MYOB Acumatica, what each platform already ships, and the recording rules Australian businesses need to sort out before any of it runs.
How an AI call logging agent works
Four steps, the same shape as most of the agent patterns we design:
- Capture. The transcript comes from wherever the conversation happened: the phone system, a Teams meeting recording, or a call recorded inside the ERP itself.
- Draft. The agent reads the transcript and drafts the CRM entries: a summary note on the lead or opportunity, follow-up activities with dates, and any field changes it thinks are justified, like a pushed-out expected closing date.
- Confirm. The rep sees the draft, fixes anything the agent misheard, and approves it. Nothing posts until they do.
- Audit. The saved record links back to the transcript, so anyone reviewing the deal later can check what was actually said.
A worked example. A rep finishes a 40-minute Teams demo with a wholesale customer. The agent drafts: a six-line summary against the opportunity, a task for the rep (“send revised pricing for the 500-unit tier by Friday”), a note that the customer asked twice about delivery timeframes to WA, and a suggested change to the expected close date, pushed out a month because the decision now needs board sign-off. The rep scans it, deletes the WA note (wrong customer, that was this morning’s call, the agent matched the wrong opportunity), and approves the rest. Ninety seconds instead of fifteen minutes, and the mistake got caught at review rather than discovered in month three.
That wrong-opportunity error is worth pausing on, because it’s the most common failure in this pattern. Same contact at two companies. One customer with three open deals. A mobile number that matches nobody. A human filing their own notes makes the same mistake, but the agent makes it confidently and at volume, which is exactly why the confirm step is not optional.
What Odoo 19 already ships
More than most people expect. Everything in this section is shipped today in Odoo 19 Enterprise, checked against the current documentation and the v19 source code.
The VoIP module became the Phone app in v19, and calls made through it land in the chatter of the lead or opportunity they belong to. On top of that sits an AI layer: Odoo 19’s voice features transcribe recorded meetings, produce an editable AI summary, and then discard the audio once processing finishes. That last part is a sensible default you’d otherwise have to build yourself.
Two details from the source code are worth knowing before you plan a rollout. Call transcription runs on a scheduled job that processes recordings one at a time, so summaries aren’t instant. And the call summariser ships as a system agent that is switched off by default; an administrator has to enable it deliberately. We’d call both of those features rather than gaps. A transcription queue you can see, and an AI capability that needs an explicit decision to turn on, is what governance looks like in practice.
What Odoo doesn’t do natively is the full loop: reading the transcript and drafting follow-up activities and field updates against the right records. That’s the layer we wire in with external agents over Odoo’s API, scoped to the rep’s own permissions, drafts only. Our Odoo AI agents guide covers how that wiring works.
Where MYOB Acumatica sits
A different shape. MYOB Acumatica has no native call transcription today. What the platform gives you is the plumbing around the conversation: Acumatica’s Microsoft Teams integration lets staff start a Teams chat or call from lead, contact and case screens and post activities to Teams channels, and the 2025 R2 release redesigned the activity form those call notes live on. MYOB’s ANZ releases track behind global Acumatica by six to nine months, so always check which release a claim refers to.
The honest limit sits in Acumatica’s own AI Studio FAQ for 2025 R2: AI Studio is an experimental feature, its automation is user-initiated, and creating new documents, records or line details is not supported. So a meeting-to-CRM agent for MYOB Acumatica runs outside the platform, reads the Teams transcript, and drafts activities and notes through the API for a person to approve. It’s the same drafts-first shape as the sales order agent that reads emailed purchase orders. We covered the platform’s wider AI position, including what’s shipped versus preview for ANZ, in our MYOB Acumatica AI guide.
Recording the call is the legal question, not the technical one
The technology is the easy half. Two Australian legal layers apply before any of it runs.
First, recording itself. Call recording is governed by state and territory surveillance device laws, and they differ: some states allow a participant to record a conversation they’re part of, others expect every party to be told. For a business dealing with customers across state lines, the safe design is to announce recording on every call and give people the chance to object. If your phone system or meeting tool records by default, the announcement is a configuration task in the phone system, and it takes minutes to set up. This isn’t legal advice; check your own footprint with your adviser.
Second, privacy. The Office of the Australian Information Commissioner’s guidance on commercially available AI products deals directly with AI meeting transcription: collect only the personal information reasonably necessary for the job, destroy or de-identify anything the recorder caught that wasn’t necessary (the personal chat before the meeting proper, someone’s medical appointment), and get consent where sensitive information is involved. In practice that means retention rules for transcripts, role-scoped access so a transcript is no more visible than the deal it belongs to, and an exclusion list of calls the agent never touches. HR conversations are the obvious first entry.
None of this is a reason to skip the pattern. It’s a reason to set it up deliberately, and it’s the part that most overseas-built note-taking tools leave for you to work out on your own.
Why the drafts still need a person
Transcription quality is good now, but the failure modes haven’t gone away. Agents mishear numbers, and a quote logged at $15,000 instead of $50,000 will surface at the worst possible moment. They attribute commitments to the wrong side of the conversation, so the CRM says the customer agreed to a timeline the rep actually proposed. And they summarise with full confidence even when the audio was poor.
“The transcript isn’t the point. The point is that your pipeline stops depending on whether the rep felt like typing on a Friday afternoon. The agent drafts, the rep checks and approves, and deal reviews stop being archaeology.”
Josh Craig, Director, Auboros
The approval step costs each rep a minute or two per call. What it buys is a CRM where every record was confirmed by the person who was in the room. That’s the difference between a pipeline you can trust and one you have to re-litigate every quarter.
Want call notes that write themselves, without writing fiction?
We design drafts-first agents over Odoo and MYOB Acumatica from Brisbane, with the consent, retention and permission settings sorted before anything records. If you’d like your calls and meetings landing in the CRM as reviewed records instead of memories, book a free consultation. We’ll look at your phone and meeting setup and tell you what’s realistic.
FAQ
Frequently asked questions
Can an AI agent automatically log sales calls to my CRM?
Yes, at the draft level. The agent reads a call or meeting transcript and drafts the summary, follow-up tasks and opportunity updates in the CRM. The safe pattern is drafts-first: nothing saves until the person who was on the call approves it.
Is it legal to record customer calls in Australia?
It depends on state and territory surveillance device laws, which differ on whether every party must be told. The safe approach for a business dealing across state lines is to announce recording on every call. The Privacy Act then governs how recordings and transcripts are stored and who can access them.
Does Odoo have AI call transcription?
Yes. Odoo 19 Enterprise transcribes recorded calls and meetings, generates an editable AI summary, and discards the audio after processing. Transcription runs on a scheduled job and the call summariser is switched off by default, so an administrator needs to enable it.
Can MYOB Acumatica summarise Teams meetings automatically?
Not natively. MYOB Acumatica integrates with Microsoft Teams from lead, contact and case screens, but Acumatica's AI Studio cannot create new records in 2025 R2. A meeting summary agent runs outside the platform and drafts notes and activities through the API for a person to approve.