Agentic ERP

SMEs shopping for an ERP face an awkward choice. Legacy ERPs carry deep business logic but are hard to use and have no meaningful AI. Modern online tools are easy to use but lack ERP depth such as double-entry accounting or inventory valuation, and building from scratch costs too much. On top of that, frontline teams talk to customers in LINE and voice notes, so the information never reaches a system. The brief: an ERP with real depth across sales, purchasing, stock and accounting, where AI turns chat and voice into records, without asking everyone to learn a new system first.

We didn’t reinvent the accounting and stock logic. We studied how Odoo, an open-source ERP, handles double-entry accounting and inventory valuation, then rebuilt it our own way with AI part of the system from day one. And we designed it around how an SME team actually works: a chat in LINE, a voice note after a customer call, a manager with a question about the numbers.

1. 1. LINE chats: reports without changing how the team talks

   A LINE group connects with an activation code and waits for an admin to approve it in the web app before any messages are kept and summarised into reports, in Thai by default, and each organisation can give the AI its own context or instructions.

2. 2. Voice notes: into the customer record

   Voice notes are stored in the organisation’s own Google Drive, and AI transcribes and summarises them in brief, in-depth and conversation views. Each one can be linked to a customer or project at any time, shared through a link with an optional password and exported to PDF.

3. 3. The whole business on one record: switch on only what you use

   Customers, sales, purchasing, inventory, accounting, projects and data analysis are modules each organisation can switch on or off. They all share the organisation’s one set of records, and each is separate enough to add or remove without breaking another, so managers stop stitching reports together from separate tools.

4. 4. The AI assistant: answers at once, asks before acting

   Each request goes to one of seven specialist AI helpers: customers, projects, sales, purchasing, inventory, accounting and data analysis. The AI works within one page, one module or the whole business, fixed from a conversation’s first message. Everything it wants to do is weighed on the risk of the change, the user’s role and the organisation’s credits, which decides whether it runs straight away or waits for a person to approve.

5. 5. Safe and simple: built for non-technical teams

   Each organisation’s data is kept apart right where it is stored, permissions spell out who can do what in each module, and every create, update and delete is recorded automatically. The interface runs in Thai and English, a Lite mode hides advanced menus, and the data-analysis module takes Excel and other data files for the AI to summarise and chart.

Agentic ERP is live, with every organisation’s data kept separate, and the AI runs as its own service alongside the web app.

• The whole business on one record

  Customers, projects, sales, purchasing, stock and accounting sit on one organisation’s data, so managers stop stitching reports together from separate tools.

• LINE chats become reports

  Approved LINE groups are summarised into reports, in Thai by default, and each organisation can add its own context or instructions for the AI.

• Calls become customer notes

  Voice notes come back transcribed, with brief, in-depth and conversation views, and can be linked to a customer or project at any time.

• AI asks before it acts

  The assistant answers from the data straight away; risky changes wait for a person’s approval.