What if your ERP could write its own emails, answer your team's questions, score your leads, transcribe your meetings, and help your developers write code — all without a single third-party tool? That is not a future promise. That is Odoo.sh with Odoo 19, available right now.
Odoo has been quietly building one of the most complete AI layers in the ERP market. With Odoo 19 released in October 2025 and new AI coding capabilities rolling into Odoo.sh in 2026, this is the moment to understand what is actually available — and what it means for your business and your team.
This is not a feature list. It is a practical guide to what AI on Odoo.sh looks like in real use, written for both the developers building on the platform and the business owners running their operations on it.
Odoo.sh is Odoo's official cloud platform — it manages your hosting, staging branches, automated builds, backups, and deployments so you can focus entirely on what matters. Now, it is also the home of Odoo's most ambitious AI release yet.
Why this moment matters
Most ERP vendors are bolting AI on as an expensive add-on or a separate subscription. Odoo took a different route: it built AI directly into the core system and shipped it as part of Odoo 19. No extra licence. No third-party integration to maintain. No steep learning curve on a separate tool.
Odoo's CEO Fabien Pinckaers made a striking point when discussing this direction: 2% of all open-source Python code in the world is Odoo-related. That means AI models like ChatGPT and Gemini are already deeply trained on Odoo's architecture, logic, and patterns. The AI you use inside Odoo actually understands Odoo — it is not guessing.
The result is a system where a sales manager, an accountant, an HR officer, and a developer can all benefit from AI inside the same platform, on the same day, without anyone needing to become an AI expert first.
v19
Odoo version powering it — live on Odoo.sh now
40+
AI-powered features across all modules
₹0
extra add-on cost on Odoo Enterprise
2%
of all Python open-source code is Odoo
For business users: what AI actually does inside your Odoo
Let's be specific. Here is what changed in Odoo 19 for the people running day-to-day operations — and why each one saves real time from the very first week.
Your team gets an assistant that knows your business
Odoo 19 introduces customisable AI agents that live inside your system. You train them on your own documents — product catalogues, HR policies, SOPs, pricing sheets — and they answer questions from your team or your customers in real time.
Unlike a generic chatbot, these agents can also take actions: update a record, generate a report, fill a field, or trigger a workflow — all from a simple chat interface. Connect one to your website Live Chat and it handles support queries around the clock. Connect one internally and your HR team stops answering the same leave-policy question fifty times a week.
Find any record by simply asking for it
How often does someone on your team spend five minutes building filters just to find something they could describe in one sentence? Natural language search ends that. Type "show me all overdue invoices above ₹1 lakh from last month" and Odoo returns the right records instantly — no filters, no domain logic, no waiting for a developer.
Build automations by describing what you want
Odoo's automation engine is powerful — but configuring it has always required some technical know-how. With prompt-based server actions, you simply describe what you want the system to do. "When a sale order is confirmed, send a WhatsApp message to the customer with the order reference." The AI handles the configuration. No developer required, no technical conditions to fiddle with manually.
Never lose what was decided in a meeting
Start a recording from any CRM opportunity, project task, or calendar event. Odoo AI produces a live transcript and a structured summary — key decisions, action items, next steps — and attaches it directly to the relevant record. Your sales team stops spending 20 minutes writing call notes after every customer meeting. Your project manager always knows exactly what was agreed.
Vendor invoices that process themselves
AI-powered OCR reads vendor invoices, receipts, and scanned documents with up to 98% accuracy — and auto-reconciles them against open purchase orders. Your accounts team reviews and approves instead of typing. That is a significant chunk of manual work eliminated from every single working day.
CRM that tells you which leads are worth your time
The CRM module now scores every inbound lead using your own historical conversion data. It flags the ones most likely to close, recommends the next best action — call, email, demo — and can draft the follow-up email for you. Your sales team stops triaging hundreds of leads every Monday morning and starts acting on the right ones immediately.
"AI is not only present across all applications in specific features — it is consolidated into a dedicated app. Odoo users now get AI embedded directly into every standard process across their entire database."
Which AI engine powers it — and can you choose?
Yes. You choose. Odoo 19 supports multiple AI providers and routes API calls at no additional cost on Enterprise. Configure your API key once in Settings and every AI feature across the entire system uses it.
| Provider | Models | Best suited for |
|---|---|---|
| Google Gemini | Gemini 1.5 Pro, Flash | Default option — fast and reliable for everyday tasks |
| OpenAI / ChatGPT | GPT-4o, GPT-4, GPT-3.5 | Complex reasoning, email drafting, agentic workflows |
| Custom / self-hosted LLM | Any model via API | Data-sensitive industries, strict GDPR environments |
Now for the developers. Odoo.sh itself is getting AI built into the development environment — and it changes the way Odoo modules are built from the ground up.
For developers: AI is coming directly into Odoo.sh
In February 2026, Fabien Pinckaers confirmed that Odoo.sh now has vibe coding capabilities — AI coding tools built directly into the platform's development environment, and live today.
If you have used AI for Odoo development before, you know the
frustration. Open Claude or ChatGPT, paste a chunk of Python, spend two
paragraphs explaining your _inherit chain and custom field
names, receive a response that largely ignores that context, copy it
back to your editor, hit an error, and start the loop again. The AI
never actually sees your project — you are the bottleneck, manually
shuttling context between two disconnected worlds.
Odoo.sh with integrated AI closes that gap. Your coding assistant has
access to your module structure, your ORM, your
__manifest__.py, and your running container. Ask it to
review your sale.order extension and suggest test cases —
it reads your actual overrides and responds with specifics, not a
generic template answer.
Works with the tools developers already use
Odoo.sh works alongside Claude Code, Cursor, Gemini Code Assist, and GitHub Copilot. Odoo Experience 2025 in Brussels featured a dedicated session — "Beyond Code Generation: Integrating AI into Odoo's Development Lifecycle" — with honest, field-tested insight into what works, what breaks, and where Odoo-specific challenges like version confusion, ORM nuances, and XML view inheritance trip these tools up. The key takeaway: AI amplifies Odoo expertise. A developer who understands the framework gets dramatically better results than one who does not.
AI fields mean fewer custom compute methods
How often do you write an @api.depends compute method just
to concatenate or summarise field values into a text field? The new
AI field type in Studio handles these cases with a
simple prompt. Define what you want generated, reference the source
fields, done. Faster to build, zero maintenance when field names change,
and your client can actually read and understand the configuration.
Prompt-based server actions reduce client delivery boilerplate
Client customisations repeat the same patterns constantly: on confirmation update this field, when status changes send this notification. With prompt-driven automation, you describe the rule and Odoo builds the server action. Less boilerplate, faster delivery per project, and fewer maintenance issues six months later.
MCP: the pattern worth knowing now
Model Context Protocol (MCP) is becoming the standard bridge between AI agents and Odoo's XML-RPC and JSON-RPC APIs. An MCP server receives a plain-language instruction, translates it into the correct Odoo API call, and returns structured results. It works on both Community and Enterprise. If you are building connectors or integrations — Shopify, carrier APIs, marketplaces — understanding MCP now puts you ahead of the curve.
Same feature — two very different perspectives
Every AI capability in Odoo 19 on Odoo.sh means something different depending on whether you are building it or using it every day:
| Feature | What it means for developers | What it means for business users |
|---|---|---|
| AI Agents | Configure once, train on docs, deploy to Live Chat — no Python needed | Instant answers on products, invoices, HR policy — 24/7, no ticket needed |
| AI Fields in Studio | Replaces @api.depends compute methods for text generation |
Records auto-fill descriptions, summaries, and notes on creation |
| Prompt-based server actions | Fewer bespoke automation scripts to write and maintain per client | Build automations by describing them — no technical setup required |
| Natural language search | Reduces custom domain filters needed in list views | Find any record by asking a plain-English question |
| Vibe coding on Odoo.sh | AI sees your actual addon code — no more context switching | Faster, more accurate customisation delivery from your Odoo partner |
| Meeting transcription | Auto-linked summaries cut post-call admin on project delivery | Decisions and action items captured and attached to CRM or task instantly |
| OCR & invoice processing | No custom field mapping scripts needed for standard document types | Vendor invoices posted and reconciled against POs automatically |
What do you actually need to get started?
Four things — no surprises:
- Odoo Enterprise — the AI app, agents, OCR, lead scoring, and AI fields are all Enterprise-only. Community edition has no built-in AI layer.
- Odoo 19 (minimum 18.3) — the full AI app and agent configuration require Odoo 18.3 or later. Odoo 19 gives you the complete feature set as launched at Odoo Experience 2025.
- An Odoo.sh subscription — managed cloud environment, staging branches, automated builds, and the vibe coding dev tooling rolling out through 2026.
- An AI provider API key — Google Gemini is the default and quickest to configure. OpenAI works too. Set it once in Settings and every AI feature in the system uses it automatically.
5 things to do on your Odoo.sh instance this week
- Install the AI app. Go to Apps in Odoo 19, install the AI module, and configure Gemini or ChatGPT in Settings. Under 10 minutes. Unlocks AI features across every module immediately.
- Set up one AI agent for your biggest support pain point. Train it on your product catalogue, FAQ, or pricing policy. Connect it to Live Chat. Measure how many queries it handles before they reach your team.
- Add an AI field to one high-volume form. Product descriptions and lead summaries are the easiest wins. Define a prompt, reference the relevant fields, and watch records fill themselves on creation.
- Replace one repetitive manual step with a prompt-based automation. Pick the task someone on your team does manually after every sale confirmation or invoice approval. Describe it in plain language in Odoo Automation. Ship it.
- Developers: start using Odoo.sh vibe coding today. Tools like Claude Code and Cursor are now integrated at the environment level — your AI assistant finally sees your actual project. Start using it on your next module and measure the difference in delivery speed.
Frequently asked questions about Odoo AI
Is Odoo AI available on the Community edition?
No. All native AI features — the AI app, agents, OCR, lead scoring, AI fields, and meeting transcription — require Odoo Enterprise. The Community edition has no built-in AI layer. You need the Standard plan or higher.
Do I need to purchase extra AI tokens or credits?
No. Odoo routes API calls to your chosen provider (Gemini or ChatGPT) at no additional cost on Enterprise. You configure your own API key in Settings — there is no Odoo-specific AI subscription or separate token pack to purchase.
What is vibe coding in Odoo.sh?
Vibe coding is AI-assisted development where you describe what you want in plain language and an AI coding agent writes the code. Odoo.sh now has these capabilities live — AI tools work inside your actual project with full context of your module structure and running container, rather than in a disconnected browser tab.
Which Odoo version do I need for the full AI feature set?
Odoo 19 gives you the complete AI feature set as launched at Odoo Experience 2025. Odoo 18.3 supports the AI app and agents with a smaller feature set. Versions 16 and 17 have limited AI — basic OCR and ChatGPT integrations only.
Can I use my own AI model instead of ChatGPT or Gemini?
Yes. Odoo 19 supports custom or self-hosted LLMs via API for teams in data-sensitive industries or those with strict GDPR requirements. You can run a local model and keep all data within your own infrastructure while still using Odoo's full AI feature layer.
Does Odoo AI work on on-premise installs or only on Odoo.sh?
Odoo AI features work on any Odoo 19 Enterprise deployment — on-premise, Odoo.com cloud, or Odoo.sh. However, Odoo.sh is the recommended platform for development teams because of its staging branches, automated builds, and the AI coding tools that are now live on the platform.
The gap between using Odoo and using Odoo intelligently is smaller than it has ever been. The features are already in your instance. The competitive advantage is simply in switching them on.
The bottom line
Odoo 19 on Odoo.sh is the most complete version of Odoo ever shipped. For the first time, AI is not a feature you turn on in one module — it is a layer that runs across your entire business: answering questions, drafting communications, processing documents, scoring opportunities, and helping your developers write better code faster.
Business users get time back from tasks they should never have been doing manually. Developers get an assistant that actually knows the codebase they are working in. Both work inside the same platform, without stitching together separate tools to make it happen.
If you are already on Odoo.sh and Odoo 19 — the question is not whether to use AI. It is which process you are going to transform first.
Note: AI features described in this article require Odoo Enterprise on version 18.3 or later, with the full feature set available on Odoo 19. AI capabilities on Odoo.sh — including vibe coding tools announced by Fabien Pinckaers in February 2026 — are now live. Refer to the official Odoo.sh documentation and release notes for the latest feature details.
What if your ERP could write its own emails, answer your team's questions, score your leads, transcribe your meetings, and help your developers write code — all without a single third-party tool? That is not a future promise. That is Odoo.sh with Odoo 19, available right now.
Odoo has been quietly building one of the most complete AI layers in the ERP market. With Odoo 19 released in October 2025 and new AI coding capabilities rolling into Odoo.sh in 2026, this is the moment to understand what is actually available — and what it means for your business and your team.
This is not a feature list. It is a practical guide to what AI on Odoo.sh looks like in real use, written for both the developers building on the platform and the business owners running their operations on it.
Odoo.sh is Odoo's official cloud platform — it manages your hosting, staging branches, automated builds, backups, and deployments so you can focus entirely on what matters. Now, it is also the home of Odoo's most ambitious AI release yet.
Why this moment matters
Most ERP vendors are bolting AI on as an expensive add-on or a separate subscription. Odoo took a different route: it built AI directly into the core system and shipped it as part of Odoo 19. No extra licence. No third-party integration to maintain. No steep learning curve on a separate tool.
Odoo's CEO Fabien Pinckaers made a striking point when discussing this direction: 2% of all open-source Python code in the world is Odoo-related. That means AI models like ChatGPT and Gemini are already deeply trained on Odoo's architecture, logic, and patterns. The AI you use inside Odoo actually understands Odoo — it is not guessing.
The result is a system where a sales manager, an accountant, an HR officer, and a developer can all benefit from AI inside the same platform, on the same day, without anyone needing to become an AI expert first.
v19
Odoo version powering it — live on Odoo.sh now
40+
AI-powered features across all modules
₹0
extra add-on cost on Odoo Enterprise
2%
of all Python open-source code is Odoo
For business users: what AI actually does inside your Odoo
Let's be specific. Here is what changed in Odoo 19 for the people running day-to-day operations — and why each one saves real time from the very first week.
Your team gets an assistant that knows your business
Odoo 19 introduces customisable AI agents that live inside your system. You train them on your own documents — product catalogues, HR policies, SOPs, pricing sheets — and they answer questions from your team or your customers in real time.
Unlike a generic chatbot, these agents can also take actions: update a record, generate a report, fill a field, or trigger a workflow — all from a simple chat interface. Connect one to your website Live Chat and it handles support queries around the clock. Connect one internally and your HR team stops answering the same leave-policy question fifty times a week.
Find any record by simply asking for it
How often does someone on your team spend five minutes building filters just to find something they could describe in one sentence? Natural language search ends that. Type "show me all overdue invoices above ₹1 lakh from last month" and Odoo returns the right records instantly — no filters, no domain logic, no waiting for a developer.
Build automations by describing what you want
Odoo's automation engine is powerful — but configuring it has always required some technical know-how. With prompt-based server actions, you simply describe what you want the system to do. "When a sale order is confirmed, send a WhatsApp message to the customer with the order reference." The AI handles the configuration. No developer required, no technical conditions to fiddle with manually.
Never lose what was decided in a meeting
Start a recording from any CRM opportunity, project task, or calendar event. Odoo AI produces a live transcript and a structured summary — key decisions, action items, next steps — and attaches it directly to the relevant record. Your sales team stops spending 20 minutes writing call notes after every customer meeting. Your project manager always knows exactly what was agreed.
Vendor invoices that process themselves
AI-powered OCR reads vendor invoices, receipts, and scanned documents with up to 98% accuracy — and auto-reconciles them against open purchase orders. Your accounts team reviews and approves instead of typing. That is a significant chunk of manual work eliminated from every single working day.
CRM that tells you which leads are worth your time
The CRM module now scores every inbound lead using your own historical conversion data. It flags the ones most likely to close, recommends the next best action — call, email, demo — and can draft the follow-up email for you. Your sales team stops triaging hundreds of leads every Monday morning and starts acting on the right ones immediately.
"AI is not only present across all applications in specific features — it is consolidated into a dedicated app. Odoo users now get AI embedded directly into every standard process across their entire database."
Which AI engine powers it — and can you choose?
Yes. You choose. Odoo 19 supports multiple AI providers and routes API calls at no additional cost on Enterprise. Configure your API key once in Settings and every AI feature across the entire system uses it.
| Provider | Models | Best suited for |
|---|---|---|
| Google Gemini | Gemini 1.5 Pro, Flash | Default option — fast and reliable for everyday tasks |
| OpenAI / ChatGPT | GPT-4o, GPT-4, GPT-3.5 | Complex reasoning, email drafting, agentic workflows |
| Custom / self-hosted LLM | Any model via API | Data-sensitive industries, strict GDPR environments |
Now for the developers. Odoo.sh itself is getting AI built into the development environment — and it changes the way Odoo modules are built from the ground up.
For developers: AI is coming directly into Odoo.sh
In February 2026, Fabien Pinckaers confirmed that Odoo.sh now has vibe coding capabilities — AI coding tools built directly into the platform's development environment, and live today.
If you have used AI for Odoo development before, you know the
frustration. Open Claude or ChatGPT, paste a chunk of Python, spend two
paragraphs explaining your _inherit chain and custom field
names, receive a response that largely ignores that context, copy it
back to your editor, hit an error, and start the loop again. The AI
never actually sees your project — you are the bottleneck, manually
shuttling context between two disconnected worlds.
Odoo.sh with integrated AI closes that gap. Your coding assistant has
access to your module structure, your ORM, your
__manifest__.py, and your running container. Ask it to
review your sale.order extension and suggest test cases —
it reads your actual overrides and responds with specifics, not a
generic template answer.
Works with the tools developers already use
Odoo.sh works alongside Claude Code, Cursor, Gemini Code Assist, and GitHub Copilot. Odoo Experience 2025 in Brussels featured a dedicated session — "Beyond Code Generation: Integrating AI into Odoo's Development Lifecycle" — with honest, field-tested insight into what works, what breaks, and where Odoo-specific challenges like version confusion, ORM nuances, and XML view inheritance trip these tools up. The key takeaway: AI amplifies Odoo expertise. A developer who understands the framework gets dramatically better results than one who does not.
AI fields mean fewer custom compute methods
How often do you write an @api.depends compute method just
to concatenate or summarise field values into a text field? The new
AI field type in Studio handles these cases with a
simple prompt. Define what you want generated, reference the source
fields, done. Faster to build, zero maintenance when field names change,
and your client can actually read and understand the configuration.
Prompt-based server actions reduce client delivery boilerplate
Client customisations repeat the same patterns constantly: on confirmation update this field, when status changes send this notification. With prompt-driven automation, you describe the rule and Odoo builds the server action. Less boilerplate, faster delivery per project, and fewer maintenance issues six months later.
MCP: the pattern worth knowing now
Model Context Protocol (MCP) is becoming the standard bridge between AI agents and Odoo's XML-RPC and JSON-RPC APIs. An MCP server receives a plain-language instruction, translates it into the correct Odoo API call, and returns structured results. It works on both Community and Enterprise. If you are building connectors or integrations — Shopify, carrier APIs, marketplaces — understanding MCP now puts you ahead of the curve.
Same feature — two very different perspectives
Every AI capability in Odoo 19 on Odoo.sh means something different depending on whether you are building it or using it every day:
| Feature | What it means for developers | What it means for business users |
|---|---|---|
| AI Agents | Configure once, train on docs, deploy to Live Chat — no Python needed | Instant answers on products, invoices, HR policy — 24/7, no ticket needed |
| AI Fields in Studio | Replaces @api.depends compute methods for text generation |
Records auto-fill descriptions, summaries, and notes on creation |
| Prompt-based server actions | Fewer bespoke automation scripts to write and maintain per client | Build automations by describing them — no technical setup required |
| Natural language search | Reduces custom domain filters needed in list views | Find any record by asking a plain-English question |
| Vibe coding on Odoo.sh | AI sees your actual addon code — no more context switching | Faster, more accurate customisation delivery from your Odoo partner |
| Meeting transcription | Auto-linked summaries cut post-call admin on project delivery | Decisions and action items captured and attached to CRM or task instantly |
| OCR & invoice processing | No custom field mapping scripts needed for standard document types | Vendor invoices posted and reconciled against POs automatically |
What do you actually need to get started?
Four things — no surprises:
- Odoo Enterprise — the AI app, agents, OCR, lead scoring, and AI fields are all Enterprise-only. Community edition has no built-in AI layer.
- Odoo 19 (minimum 18.3) — the full AI app and agent configuration require Odoo 18.3 or later. Odoo 19 gives you the complete feature set as launched at Odoo Experience 2025.
- An Odoo.sh subscription — managed cloud environment, staging branches, automated builds, and the vibe coding dev tooling rolling out through 2026.
- An AI provider API key — Google Gemini is the default and quickest to configure. OpenAI works too. Set it once in Settings and every AI feature in the system uses it automatically.
5 things to do on your Odoo.sh instance this week
- Install the AI app. Go to Apps in Odoo 19, install the AI module, and configure Gemini or ChatGPT in Settings. Under 10 minutes. Unlocks AI features across every module immediately.
- Set up one AI agent for your biggest support pain point. Train it on your product catalogue, FAQ, or pricing policy. Connect it to Live Chat. Measure how many queries it handles before they reach your team.
- Add an AI field to one high-volume form. Product descriptions and lead summaries are the easiest wins. Define a prompt, reference the relevant fields, and watch records fill themselves on creation.
- Replace one repetitive manual step with a prompt-based automation. Pick the task someone on your team does manually after every sale confirmation or invoice approval. Describe it in plain language in Odoo Automation. Ship it.
- Developers: start using Odoo.sh vibe coding today. Tools like Claude Code and Cursor are now integrated at the environment level — your AI assistant finally sees your actual project. Start using it on your next module and measure the difference in delivery speed.
Frequently asked questions about Odoo AI
Is Odoo AI available on the Community edition?
No. All native AI features — the AI app, agents, OCR, lead scoring, AI fields, and meeting transcription — require Odoo Enterprise. The Community edition has no built-in AI layer. You need the Standard plan or higher.
Do I need to purchase extra AI tokens or credits?
No. Odoo routes API calls to your chosen provider (Gemini or ChatGPT) at no additional cost on Enterprise. You configure your own API key in Settings — there is no Odoo-specific AI subscription or separate token pack to purchase.
What is vibe coding in Odoo.sh?
Vibe coding is AI-assisted development where you describe what you want in plain language and an AI coding agent writes the code. Odoo.sh now has these capabilities live — AI tools work inside your actual project with full context of your module structure and running container, rather than in a disconnected browser tab.
Which Odoo version do I need for the full AI feature set?
Odoo 19 gives you the complete AI feature set as launched at Odoo Experience 2025. Odoo 18.3 supports the AI app and agents with a smaller feature set. Versions 16 and 17 have limited AI — basic OCR and ChatGPT integrations only.
Can I use my own AI model instead of ChatGPT or Gemini?
Yes. Odoo 19 supports custom or self-hosted LLMs via API for teams in data-sensitive industries or those with strict GDPR requirements. You can run a local model and keep all data within your own infrastructure while still using Odoo's full AI feature layer.
Does Odoo AI work on on-premise installs or only on Odoo.sh?
Odoo AI features work on any Odoo 19 Enterprise deployment — on-premise, Odoo.com cloud, or Odoo.sh. However, Odoo.sh is the recommended platform for development teams because of its staging branches, automated builds, and the AI coding tools that are now live on the platform.
The gap between using Odoo and using Odoo intelligently is smaller than it has ever been. The features are already in your instance. The competitive advantage is simply in switching them on.
The bottom line
Odoo 19 on Odoo.sh is the most complete version of Odoo ever shipped. For the first time, AI is not a feature you turn on in one module — it is a layer that runs across your entire business: answering questions, drafting communications, processing documents, scoring opportunities, and helping your developers write better code faster.
Business users get time back from tasks they should never have been doing manually. Developers get an assistant that actually knows the codebase they are working in. Both work inside the same platform, without stitching together separate tools to make it happen.
If you are already on Odoo.sh and Odoo 19 — the question is not whether to use AI. It is which process you are going to transform first.
Note: AI features described in this article require Odoo Enterprise on version 18.3 or later, with the full feature set available on Odoo 19. AI capabilities on Odoo.sh — including vibe coding tools announced by Fabien Pinckaers in February 2026 — are now live. Refer to the official Odoo.sh documentation and release notes for the latest feature details.