Data to AI™ / Gemini/Odoo
Give the people who maintain your Odoo reporting a terminal view of the replicated models, so stale extractions, unexpected changes and upgrade side effects show up before anyone reads a wrong number.
Better answers, fewer tokens.
Gemini CLI
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.
For every replicated Odoo entity, return the latest dataddo_extraction_timestamp and tell me which ones are older than 26 hours.
A data engineer runs this in Gemini CLI before publishing a new version of the finance dashboard. If any model is stale, the release waits until the extraction is fixed.
Compare dataddo_hash values between the last two extractions of the invoice model and write the changed records, with Last Updated On, to audit/odoo-changes.csv.
An accounting systems analyst keeps a dated change file in the repo for the auditors, so edits to booked invoices are visible without opening Odoo.
List the columns and field types of each replicated Odoo model and save them to upgrade/columns-before.json, then repeat after the upgrade and show the differences.
The Odoo partner running the version upgrade uses Gemini Code Assist in VS Code to check that monetary and many2one fields the reports rely on still exist afterwards.
Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Knowing the data is current | A dashboard shows last week's numbers after an extraction quietly failed, and no one notices until a manager asks. | Every row carries dataddo_extraction_timestamp, so Gemini checks the age of each model before a release or report. | Stale data caught early |
| Tracking edits to records | Comparing two Odoo exports row by row to find changed invoices takes an afternoon of spreadsheet work. | dataddo_hash identifies each record version, so Gemini lists what changed between runs and writes it to a file. | Changes in minutes |
| Upgrades and custom fields | An Odoo upgrade renames or drops a custom field, and the first sign is a broken report weeks later. | Gemini describes the replicated entities with their field types, so a before and after diff shows changes on upgrade day. | Breaking changes found on day one |
| Approving each lookup | Scripts using an Odoo API key can read any model of the instance and nobody reviews the calls. | Gemini CLI asks you to confirm each Dataddo tool call, and Always allow is your choice per tool. | Every call reviewed |
| Token consumption | Gemini 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. | Fewer 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. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Odoo Table Replication (one model per source) |
|
Which language setting does each replicated model use, and which of its columns are custom fields? |
| Date range fields |
|
Which records have a Last Updated On older than six months, so they no longer change in our sync window? |
| Replicated field types |
|
Which many2one fields in our replicated models point to the same related model, so we can join them in code? |
| Dataddo metadata columns |
|
Which replicated models have a latest dataddo_extraction_timestamp older than one day? |
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 →Replicate the Odoo models you need in Dataddo, one model per source, and attach them to a Google Gemini destination or AI Model. Add Dataddo to ~/.gemini/settings.json under mcpServers with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI, run /mcp auth dataddo and sign in.
The replicated models in flows or Contexts attached to an AI destination or AI Model in your Dataddo account, including ones attached to other AI clients. Gemini never connects to Odoo itself.
By default Dataddo extracts only the selected company's data. Add a custom filter to the source to include more companies, and Gemini can then answer per company or for the group.
Odoo's external API pagination can return duplicates on large models. Set the source's date range field to Last Updated On and use dataddo_hash as a natural key.
Yes. Put the mcpServers entry in .gemini/settings.json inside that project instead of ~/.gemini/settings.json, which applies to every project.
Credentials are kept in ~/.gemini/mcp-oauth-tokens.json and renewed automatically. If a session expires or is revoked, run /mcp auth dataddo and sign in with your Dataddo email and password.
No. Gemini queries replicated data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model and nothing is written back to Odoo.
