Skip to Content
Odoo Menu
  • Sign in
  • Try it free
  • Apps
    Finance
    • Accounting
    • Invoicing
    • Expenses
    • Spreadsheet (BI)
    • Documents
    • Sign
    Sales
    • CRM
    • Sales
    • POS Shop
    • POS Restaurant
    • Subscriptions
    • Rental
    Websites
    • Website Builder
    • eCommerce
    • Blog
    • Forum
    • Live Chat
    • eLearning
    Supply Chain
    • Inventory
    • Manufacturing
    • PLM
    • Purchase
    • Maintenance
    • Quality
    Human Resources
    • Employees
    • Recruitment
    • Time Off
    • Appraisals
    • Referrals
    • Fleet
    Marketing
    • Social Marketing
    • Email Marketing
    • SMS Marketing
    • Events
    • Marketing Automation
    • Surveys
    Services
    • Project
    • Timesheets
    • Field Service
    • Helpdesk
    • Planning
    • Appointments
    Productivity
    • Discuss
    • Approvals
    • IoT
    • VoIP
    • Knowledge
    • WhatsApp
    Third party apps Odoo Studio Odoo Cloud Platform
  • Industries
    Retail
    • Book Store
    • Clothing Store
    • Furniture Store
    • Grocery Store
    • Hardware Store
    • Toy Store
    Food & Hospitality
    • Bar and Pub
    • Restaurant
    • Fast Food
    • Guest House
    • Beverage Distributor
    • Hotel
    Real Estate
    • Real Estate Agency
    • Architecture Firm
    • Construction
    • Property Management
    • Gardening
    • Property Owner Association
    Consulting
    • Accounting Firm
    • Odoo Partner
    • Marketing Agency
    • Law firm
    • Talent Acquisition
    • Audit & Certification
    Manufacturing
    • Textile
    • Metal
    • Furnitures
    • Food
    • Brewery
    • Corporate Gifts
    Health & Fitness
    • Sports Club
    • Eyewear Store
    • Fitness Center
    • Wellness Practitioners
    • Pharmacy
    • Hair Salon
    Trades
    • Handyman
    • IT Hardware & Support
    • Solar Energy Systems
    • Shoe Maker
    • Cleaning Services
    • HVAC Services
    Others
    • Nonprofit Organization
    • Environmental Agency
    • Billboard Rental
    • Photography
    • Bike Leasing
    • Software Reseller
    Browse all Industries
  • Community
    Learn
    • Tutorials
    • Documentation
    • Certifications
    • Training
    • Blog
    • Podcast
    Empower Education
    • Education Program
    • Scale Up! Business Game
    • Visit Odoo
    Get the Software
    • Download
    • Compare Editions
    • Releases
    Collaborate
    • Github
    • Forum
    • Events
    • Translations
    • Become a Partner
    • Services for Partners
    • Register your Accounting Firm
    Get Services
    • Find a Partner
    • Find an Accountant
      • Get a Tailored Demo
    • Implementation Services
    • Customer References
    • Support
    • Upgrades
    Github Youtube Twitter Linkedin Instagram Facebook Spotify
    +32 2 290 34 90
    • Get a Tailored Demo
  • Pricing
  • Help
  1. APPS
  2. Technical
  3. AI Agent (BytesRaw) v 19.0
  4. Sales Conditions FAQ

AI Agent (BytesRaw)

by Fasil https://www.bytesraw.com , Bytesraw https://www.bytesraw.com
Odoo

$ 68.99

v 19.0 Third Party
Apps purchases are linked to your Odoo account, please sign in or sign up first.
You bought this module and need support? Click here!
  • Description
  • Manifest
  • License
●  Available for Odoo 19.0

AI Agent (BytesRaw)

AI skills, retrieval-augmented generation and agents on top of ai_base_bytesraw

⭐ 19.0.1.11.0 📜 OPL-1 💰 89 USD 🏷️ Technical
Explore Features → Contact Support
OVERVIEW

Agents that know your data
and act on your records.

AI Agent turns the raw provider connections of AI Base into something an Odoo business actually uses: agents that know your data, follow your instructions, and act on your records.

An agent is a persona (system prompt, tone, output format) plus three things you configure: skills — instruction packs and indexed documents the agent can search; tools — server actions it may call to read, create, update or navigate your Odoo data; and connections — an ordered failover chain of AI providers. Every tool call runs with the requesting user’s own access rights and is written to an audit log.

📚

Knowledge That Stays Current

Upload Markdown, text, PDF or CSV documents to a skill and they are chunked, embedded and indexed in the background. At question time the agent retrieves only the passages that matter, so answers are grounded in your documents rather than in the model’s training data.

🛠️

Tools Without Writing Code

Any Odoo server action can be exposed to AI with a checkbox. Update a record, create one, post a message, fire a webhook, open a view — pick the fields the AI may fill and the parameter schema builds itself. Destructive tools ask the user to confirm before anything happens.

🔒

The User’s Rights, Always

Tools execute as the human who asked, not as a superuser. Record rules, model access rights and field-level groups all apply unchanged, every call lands in the tool log, and knowledge passages are fenced as untrusted content so a poisoned document cannot issue instructions to the model.

FEATURES

Eleven capabilities.
One governance model.

Whatever a tool is underneath — a server action, a Python callable, a model method or a remote MCP tool — it is validated, user-bound, confirmation-gated and audited the same way.

🤖

Configurable Agents

Give an agent a name, avatar, system prompt, response style (Analytical, Balanced, Creative or a custom temperature), output format (Markdown, plain text, HTML or WhatsApp) and a token ceiling. Restrict it to user groups, hide it from surfaces where it makes no sense, and set a chat expiry so stale conversations are never silently reused.

🔗

Provider Failover with a Circuit Breaker

An agent points at an ordered list of connections, each with its own model. When a provider times out or fails, the agent moves down the list; a line that keeps failing is put on cooldown, and the last error shows right on the connection line. Dropped streams are retried on the same line before failing over.

🧠

Skills with Retrieval-Augmented Generation

A skill bundles instructions injected into the system prompt with a document library. Chunk size, overlap, top-K and a similarity threshold are tunable per skill, and Reindex Documents rebuilds the index on demand. Identical content is embedded only once, even when shared across skills.

⚡

Portable Vector Storage

Embeddings are stored in a JSON column so the module runs on any PostgreSQL, and additionally in a native vector column when the pgvector extension is installed, for fast cosine search. Without pgvector, retrieval falls back to a pure-Python scan — nothing to install, nothing to break.

⏱️

Background Indexing

A scheduled job embeds pending chunks in batches, commits progress as it goes and re-arms itself while work remains, so indexing a large document library never blocks a user or times out a request. Per-chunk status and the exact error are visible on the skill.

🧰

A Library of Ready-Made Tools

More than twenty working tools out of the box: search records, get a record, read groups and aggregates, list model fields, create, update, duplicate and archive records, search the knowledge base, list and read attachments, export to CSV, calculate, convert currency, compute report measures, plus navigation tools that open a form, list, kanban, pivot or graph view on the user’s screen.

🔒

Confirmation Gates for Destructive Actions

Server actions that change data or reach the outside world are confirmation-gated by default. Instead of executing, the agent returns a proposal describing exactly what it intends to do; only after the user says yes does the tool run. A model can escalate a policy, never remove one.

🧪

Test Tool Before Trusting It

The Test Tool button runs a tool for real against a chosen record inside a savepoint that is always rolled back, then shows the exact string the model would have received. Author a tool, see what it returns, adjust the description — without touching production data.

📋

Full Tool Audit Log

Every call is recorded: tool name, agent, user, target record, arguments sent, output returned and a status of Success, Invalid Arguments, Confirmation Required, Error or Access Denied. List, graph and pivot views group by tool, user, agent, status or day.

🧩

An Extensible Tool Registry

Beyond server actions, the registry holds Python callables and model-declared methods as first-class tools — and remote MCP tools once ai_mcp_bytesraw is installed. Whatever the kind, every tool goes through the same validation, user binding, confirmation gate and audit row.

🛡️

Loop and Budget Guards

Each turn is bounded by an iteration cap and a wall-clock budget. A model that re-sends an identical tool call is warned, then stopped, so a confused agent cannot burn a user’s token budget repeating itself.

CONFIGURATION

Configured by managers.
Used by everyone.

Skills, tools and agents are manager-side configuration; everyone else simply uses the agents they are allowed to see.

1

Set up a provider first

This module needs at least one tested connection from AI → Configuration → AI Providers.

2

Create a skill

At AI → Skills, add instructions and — for document retrieval — turn on Use RAG, pick an embedding connection and upload documents.

3

Expose your tools

Open AI → Tools, or any server action, tick Available to AI, write a precise description and choose the LLM-settable fields.

4

Create the agent

At AI → Agents → New, write the system prompt, then attach connection lines in failover order, skills and tools.

5

Restrict access

Use Restricted To to limit an agent to specific user groups, or leave it empty to offer it to everyone with AI access.

6

Watch what it does

AI → Configuration → Tool Logs shows every call the agents have made, with arguments and results.

SCREENSHOTS

See it in action

Following the configuration path: providers, then skills, then tools, then the audit trail.

1
Agents Each card shows the connections, skills and tools the agent is wired to.
AI Agents kanban view with connection, skill and tool tags on each card.
2
A tested provider connection The model that answered is recorded on the Status tab.
AI Provider form with a successful connection test on the Status tab.
3
Pricing and daily budget The ceiling every agent turn is checked against.
Provider Pricing and Budget tab with per-million-token prices and a daily token budget.
4
Skill instructions Injected into the system prompt of every agent that uses the skill.
AI Skill form showing the Instructions tab.
5
Skill documents Markdown, plain text, PDF and CSV files to index.
AI Skill form showing the uploaded document library.
6
RAG settings Chunk size, overlap, top-K and the similarity threshold.
AI Skill RAG settings with chunk size, overlap, top K and similarity threshold.
7
Indexed chunks Per-chunk embedding model and status.
AI Skill chunks list with embedding model and per-chunk status badges.
8
The AI Tools list Every server action currently exposed to agents.
AI Tools list view showing tool names, actions and confirmation flags.
9
Authoring a tool Tool name, description, parameters schema and the Test Tool button.
Server action form with the AI Tool section and Test Tool button.
10
A code tool Validated arguments in, a plain string back to the model.
Server action code tab for an AI tool.
11
Tool Logs Every call with its user, target record and status.
AI Tool Logs list view with tool name, user, record and status columns.
USAGE

Four workflows, end to end

Build an agent, teach it your documents, give it a tool, then audit what it does.

WORKFLOW · 01

Build Your First Agent

Assemble a working agent from a prompt, a provider and a handful of tools.

✓
Go to AI → Agents and click New. Name it for its job, for example Sales Assistant.
✓
Write the System Prompt on its tab — who the agent is, what it should and should not do.
✓
Choose a Response Style (Analytical for factual work, Creative for drafting) and a Format Style.
✓
On Connections (failover order), add your primary provider first, then any backups, dragging them into order.
✓
On Tools, start with read-only tools such as search_records, get_record and read_group.
✓
Save, then talk to the agent from whichever surface you have installed — Discuss, the AI Workspace, live chat or a chatter action.
WORKFLOW · 02

Teach the Agent Your Documents

Ground the agent’s answers in your own policies, catalogues or manuals instead of the model’s general knowledge.

✓
Go to AI → Skills → New and name the skill after the domain it covers.
✓
Fill Instructions with the rules that always apply — tone, terminology, escalation policy.
✓
Leave Use RAG on, pick the Embedding Connection, and confirm the embedding model that fills in.
✓
Upload your documents on the Documents tab, then click Reindex Documents.
✓
Watch the badge move from Pending to Indexed; the Chunks tab shows any file that failed and why.
✓
Attach the skill to an agent, and switch on Restrict to Knowledge if it should refuse to answer beyond the indexed material.
WORKFLOW · 03

Turn an Action Into a Tool

Let the agent do something in Odoo, safely, without writing a line of Python.

✓
Open Settings → Technical → Server Actions (or AI → Tools → New) and build the action as you normally would.
✓
Tick Available to AI. A tool name is derived automatically and mutating actions get Require Confirmation switched on for you.
✓
Write the AI Tool Description carefully: this is the text the model reads to decide when to call your tool.
✓
Pick the LLM-Settable Fields the AI may fill — leave the list empty for a tool where the AI only decides whether to run it.
✓
Click Test Tool, give it a record id and some JSON arguments, and run it — everything is rolled back and you see exactly what the model would receive.
✓
Add the tool to an agent’s Tools tab.
WORKFLOW · 04

Audit and Tune

Find out what your agents are really doing and where they go wrong.

✓
Open AI → Configuration → Tool Logs and filter to Failed to see rejected or errored calls.
✓
Group by Tool to find which tool the model reaches for most, and by Status to spot descriptions that need sharpening.
✓
Switch to the graph or pivot view for call volume per tool over time.
✓
Cross-check token spend under AI → Configuration → Usage Logs, grouped by agent.
KNOWN ISSUES

Full transparency

The current limitations, stated plainly.

🧠

Changing an embedding model requires reindexing

Retrieval quality depends on the embedding model you configure, and the stored vectors are tied to it. Existing chunks embedded under the old model are not comparable with new queries, so reindex the skill after switching.

⚡

pgvector is optional but recommended at scale

Install the PostgreSQL pgvector extension for fast native cosine search on large document sets. Without it everything still works — retrieval falls back to a pure-Python scan, which is fine for modest corpora but slows down as the index grows.

📄

Scanned PDFs yield no text

PDF extraction goes through Odoo’s built-in attachment indexing. A scanned PDF without an embedded text layer produces nothing, and there is no OCR step — convert such files before indexing them.

🧪

Two tool types differ in the dry run

In Test Tool, a webhook’s POST is registered after commit and is therefore cancelled by the rollback, and a mail-posting tool’s message is created and then rolled back. In both cases the wizard shows you what would have been sent.

FAQ

Questions, answered

Quick answers to the questions buyers ask most.

Q

Can the agent see data the user is not allowed to see?

No. Every tool executes with the requesting user’s own environment, so model access rights, record rules and field-level groups apply exactly as they do in the UI. A field the user cannot read is omitted from what reaches the model.

Q

What stops the agent from deleting or changing things by accident?

Server actions that write data or call out to the internet are confirmation-gated by default: the agent returns a proposal and waits for explicit approval before executing. Read-only tools are never gated.

Q

Can a malicious document tell the agent what to do?

Retrieved knowledge passages and tool results are wrapped in explicit untrusted-content markers before they enter the prompt, and content that tries to forge those markers is stripped. This makes an injection attempt visible to the model rather than indistinguishable from your own instructions.

Q

Do I need to know Python to create tools?

No. Every server action type except Execute Code generates its parameter schema from the fields you tick, so a working tool is a form to fill in. Execute Code remains available when you need it.

Q

Which document formats can a skill index?

Markdown, plain text, CSV and PDF (via Odoo’s attachment indexing).

Q

Does one agent have to use one provider?

No. An agent holds an ordered list of connections and moves down it on failure, so you can put a premium model first and a cheaper or local one behind it as a safety net.

Q

How long are tool logs kept?

90 days by default, then removed by Odoo’s autovacuum. Adjust with the ai_agent_bytesraw.tool_log_retention_days system parameter.

CHANGELOG

Release history

A clean record of every release.

2026-07-23 · Latest release
v19.0.1.11.0
▸ Anti-loop guard: identical repeated tool calls are warned about, then aborted, instead of burning the whole turn
▸ Prompt-injection defence: knowledge passages and tool results fenced as untrusted content, with marker forgery stripped
▸ Tool library expanded with knowledge search, attachment reading, CSV export, calculation, currency conversion and report measures
▸ Navigation tools that open a form, list, kanban, pivot or graph view on the user’s screen
▸ Layer 2 tool registry: Python callables and model-declared methods alongside server-action tools, all sharing the same governance
▸ Multimodal attachments on a user turn, per-agent chat expiry and manual agent sequencing
▸ Circuit breaker and stream retry / replay on the connection failover chain
▸ Declarative no-code tool authoring with generated parameter schemas and the Test Tool dry-run wizard
▸ Initial release: agents, skills, RAG indexing with portable and pgvector storage, background embedding cron and the tool audit log
Bytesraw logo

Bytesraw

Automate your success
🌐 www.bytesraw.com

🛠️ Need help?

Got a question, found a bug, or need a custom enhancement? Our support team responds within 24 hours on business days.

help@bytesraw.com →

💼 Custom development

Need this module tailored to your workflow, or a brand-new Odoo solution? Let’s talk about your project.

info@bytesraw.com →
OUR EXPERTISE
✓
Odoo Development
✓
Functional Training
✓
Community Upgradations
✓
Python & PostgreSQL
✓
Hosting Solutions
✓
Automation
✓
Security
✓
API & 3rd-Party Integrations
✓
E-commerce & POS Solutions
© 2026 Bytesraw · All rights reserved · Licensed under OPL-1
Availability
Odoo Online
Odoo.sh
On Premise
Community Apps Dependencies Show
AI Base (BytesRaw)
Lines of code 5902
Technical Name ai_agent_bytesraw
LicenseOPL-1
Websitehttps://www.bytesraw.com
Odoo Proprietary License v1.0

This software and associated files (the "Software") may only be used (executed,
modified, executed after modifications) if you have purchased a valid license
from the authors, typically via Odoo Apps, or if you have received a written
agreement from the authors of the Software (see the COPYRIGHT file).

You may develop Odoo modules that use the Software as a library (typically
by depending on it, importing it and using its resources), but without copying
any source code or material from the Software. You may distribute those
modules under the license of your choice, provided that this license is
compatible with the terms of the Odoo Proprietary License (For example:
LGPL, MIT, or proprietary licenses similar to this one).

It is forbidden to publish, distribute, sublicense, or sell copies of the Software
or modified copies of the Software.

The above copyright notice and this permission notice must be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.

Please log in to comment on this module

  • The author can leave a single reply to each comment.
  • This section is meant to ask simple questions or leave a rating. Every report of a problem experienced while using the module should be addressed to the author directly (refer to the following point).
  • If you want to start a discussion with the author or have a question related to your purchase, please use the support page.
Community
  • Tutorials
  • Documentation
  • Forum
Open Source
  • Download
  • Github
  • Runbot
  • Translations
Services
  • Odoo.sh Hosting
  • Support
  • Upgrade
  • Custom Developments
  • Education
  • Find an Accountant
  • Find a Partner
  • Become a Partner
About us
  • Our company
  • Brand Assets
  • Contact us
  • Jobs
  • Events
  • Podcast
  • Blog
  • Customers
  • Legal • Privacy
  • Security

Odoo is a suite of open source business apps that cover all your company needs: CRM, eCommerce, accounting, inventory, point of sale, project management, etc.

Odoo's unique value proposition is to be at the same time very easy to use and fully integrated.

Website made with