Data to AI™ / ChatGPT/Odoo
Accountants and RevOps analysts query replicated Odoo records in ChatGPT, see how fresh each answer is and approve every lookup before it touches the data.
Less tokens, better answers.
ChatGPT
On which day last week did our invoice records change the most?
Monday 21 Sep was the busiest day, with 64 invoice records Created On and 118 Last Updated On. Updates outnumbered new records on each day shown.
| Day | Records by Created On | Records by Last Updated On |
|---|---|---|
| Mon 21 Sep Odoo Table Replication | 64 | 118 |
| Tue 22 Sep Odoo Table Replication | 41 | 87 |
| Wed 23 Sep Odoo Table Replication | 38 | 72 |
Counted on one replicated model filtered by Last Updated On, the date range field the docs recommend against Odoo pagination duplicates.
Odoo is an open-source ERP with modules for accounting, inventory, sales, CRM and HR. Dataddo replicates whole Odoo models: you pick a model from your instance and its columns, including custom fields, so the fields match your setup.
Run data_status and known_gaps on my Odoo flows first. If they are current, total the monetary amounts in the invoice flow for September.
The accountant wants to know the data is fresh before quoting a month-end figure, and approves each tool call, so nothing runs that the accountant did not see.
Describe the Odoo invoice entity, find its due date and payment status fields, then total past-due monetary amounts per customer.
A credit clerk lets ChatGPT locate the fields this instance uses for due dates and payment state, then builds the weekly reminder list from the totals.
Count sales order records Created On per week in September and set them against invoice records Created On in the same weeks.
RevOps compares new orders with invoices raised in the same weeks, to see how quickly orders in Odoo turn into billed revenue.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Bringing Odoo records to ChatGPT | An analyst exports invoices and sales orders from Odoo list views and uploads both files before every analysis. | A developer-mode app reads the replicated invoice and sales order models from Dataddo when ChatGPT needs them. | No exports per question |
| Approving each request | Uploaded Odoo files hand the model every row and column at once, whether the question needs them or not. | ChatGPT asks you to confirm each tool call, and the app settings let you turn individual tools off. | Every lookup approved |
| How fresh the records are | An uploaded export carries no date, so changes made in Odoo since then are silently missing from the answer. | Each run re-reads its window on Created On or Last Updated On, and data_status shows when that last happened. | Dated, current answers |
| Finding the right field | ChatGPT guesses which column in an export holds the due date or payment state of your customised invoices. | describe_entity and search return the fields of the model you replicate, with their types, before ChatGPT queries. | Your fields, not guesses |
| Token consumption | ChatGPT spends tokens exploring raw Odoo columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Less tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The Odoo datasets finance and RevOps teams use most, with their real field names. ChatGPT queries them by name through the Dataddo semantic layer.
Runs on your schedule. Each run reads a relative window on the date field you choose, such as Last Updated On, and a full data re-sync loads older records.
Odoo connector →We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Connect Odoo to Dataddo with your host, database and login, create an Odoo Table Replication source for each model, such as invoices or sales orders, and attach the flows to a ChatGPT destination or AI Model. In ChatGPT web, turn on developer mode and add an OAuth app for https://headless.dataddo.com/mcp-data.
Yes, if you tick them when creating the source. Odoo may expose custom fields from your account, and once extracted ChatGPT queries them by name like any other field in the model.
Developer mode is required: Pro, Plus, Business, Enterprise or Education, on the web only. On Business and Enterprise a workspace admin may need to allow it first.
Data appears only after the flow has run once. Check that the source finished its first extraction and the flow is attached to an AI destination or AI Model, then ask ChatGPT to call list_flows again.
Only if the source extracts them. By default the selected company is extracted. Add a custom filter on the Models and columns step to include other companies, then ask ChatGPT per company.
Each run reads the relative window you set on the date range field. A new source starts from that window, so load older records once with a full data re-sync over a wider range.
No. ChatGPT reads extracted Odoo data through the Dataddo semantic layer and never connects to Odoo. You also confirm each tool call and can switch individual tools off.