Skip to content

AI platform for businesses

The AI governance platform for your agents and your teams

With GuardWeaver, your teams get AI agents that answer from your documents and your tools, with sources. You set the rules for using AI, the platform enforces them on every action and keeps the proof.

No credit card

GuardWeaver in action

Silent video. You set the rules, GuardWeaver enforces them: the audit log allows an HR question, blocks an export of the customer file, masks a Social Security number and blocks a contract sent to an unauthorized model; every decision is logged in a sealed ledger (Enterprise plan). An AI agent then answers a coverage question citing its source, and refuses to guess when its documents do not cover the topic. Connect your tools: 100+ integrations, one click away. The agent answers on every channel: your website, Teams, WhatsApp, Messenger and Slack.

Plugged into what you already use

GuardWeaver sits between your teams, your data and your AI models, and applies your rules to every exchange.

What you connect

Your documents

  • SharePoint
  • Drive
  • Confluence

Your business tools

  • CRM
  • ERP
  • Tickets

Your messaging

  • Teams
  • Slack
  • WhatsApp

Your AI models

  • Mistral
  • Claude
  • OVHcloud

GuardWeaver

  • Your AI agents
  • Your usage rules

Applied before every action

What GuardWeaver does for you

Sourced answers

Drawn from your documents

Agents that act

In your tools, under your rules

Shadow AI detected coming soon

AI tools used without approval

Automatic masking

Sensitive data masked before sending

Governance and proof

Everything that goes through GuardWeaver follows your rules and leaves a trace.

  • Rules

    checked before the action

  • External agents

    governed too

  • Audit log

    append-only

  • Your AI keys

    no markup

  • Hosting

    Europe or on-premise

Every decision is traced

The audit log keeps a record of every request and the decision taken. With Enterprise, it is sealed, timestamped by a third party and can be exported for an audit.

Audit log

app.guardweaver.ai

TimeWhoRequestDecision
09:42:18 HR assistant Question about the collective agreement Allowed
09:41:55 External agent Export of the customer file Blocked
09:41:02 Payroll assistant Social security number in a request Masked
09:40:37 Sales agent CRM record update Allowed
09:39:12 Legal assistant Contract sent to an unauthorized model Blocked

Every line is written append-only: it can be neither edited nor deleted.

Customer voices

Trusted by

“A high-performing conversational AI agent, easy to use and perfectly integrated into our digital environment.”
Jonathan Claquin
Jonathan Claquin
Global Communication Director, Visionix

Read the Visionix case study

Start for free

15 days of Premium on us when you sign up, no credit card. Governance is included in every plan.

More than 100 users?

Free

To discover GuardWeaver before opening it to your team.

€0 forever

2 users

Basic governance

AI usage rules What AI is allowed to do: flagged in observation, stopped in blocking.
3 rules in observation
Sensitive data Emails, IBANs, card numbers… masked before they reach the AI.
Not included
Audit log
3 days, lightweight version
AI spending caps You cap spending with your AI provider, per person, agent or model.
Not included
Roles and permissions Owner, administrator or member, per person or per team, with a role per workspace and extra rights.
Included
Shadow AI Detects the AI tools used without your approval. coming soon
Not included

AI agents

On your documents and in your tools, with sources

Agents
1
Agent requests One message sent to an agent, pooled across the whole organization.
50 per month
Indexed pages 1 page = 1 PDF page, 1 slide, 1 spreadsheet tab or 3,000 characters of text.
200 for the organization
Workflow runs Each launch of an automated workflow counts as one run.
1,000 per month
Integrations Tools connected to each agent (Teams, Slack, SharePoint, Google Drive…), not counting the web widget or the API.
1
Agents connected to your tools (MCP) Your agents act in your business tools, not only answer.
Not included
Orchestration between agents (A2A) An agent hands over to a more competent agent, internal or external.
Not included

Deployment

Installation on your servers (on-premise) Including with no internet access, with a local AI model.
Not included

Premium

Launch offer

To equip your teams with AI agents, get alerted to risks and block the most sensitive ones.

€120 excl. tax / month

10 users

€1,440 excl. tax billed annually

Price locked for 1 year for the first 50 customers

Governance: track the risks

AI usage rules What AI is allowed to do: flagged in observation, stopped in blocking.
Unlimited in observation, 5 in blocking
Sensitive data Emails, IBANs, card numbers… masked before they reach the AI.
Automatic masking
Audit log
1 year
AI spending caps You cap spending with your AI provider, per person, agent or model.
Per user, agent and model
Roles and permissions Owner, administrator or member, per person or per team, with a role per workspace and extra rights.
Included
Shadow AI Detects the AI tools used without your approval. coming soon
Included at launch

AI agents

On your documents and in your tools, with sources

Agents
Unlimited
Agent requests One message sent to an agent, pooled across the whole organization.
10,000 per month
Indexed pages 1 page = 1 PDF page, 1 slide, 1 spreadsheet tab or 3,000 characters of text.
5,000 for the organization
Workflow runs Each launch of an automated workflow counts as one run.
10,000 per month
Integrations Tools connected to each agent (Teams, Slack, SharePoint, Google Drive…), not counting the web widget or the API.
4 per agent
Agents connected to your tools (MCP) Your agents act in your business tools, not only answer.
Included
Orchestration between agents (A2A) An agent hands over to a more competent agent, internal or external.
Included

Deployment

Installation on your servers (on-premise) Including with no internet access, with a local AI model.
Not included

Enterprise

Advanced governance included

To block risky uses and document your compliance.

Custom

Based on your organization and your needs

Governance: act and document

AI usage rules What AI is allowed to do: flagged in observation, stopped in blocking.
Unlimited, in observation and blocking
Sensitive data Emails, IBANs, card numbers… masked before they reach the AI.
Automatic masking
Audit log
Contract term, sealed and timestamped export
AI spending caps You cap spending with your AI provider, per person, agent or model.
Per user, agent and model
Roles and permissions Owner, administrator or member, per person or per team, with a role per workspace and extra rights.
Included
Shadow AI Detects the AI tools used without your approval. coming soon
Included at launch

AI agents

On your documents and in your tools, with sources

Agents
Unlimited
Agent requests One message sent to an agent, pooled across the whole organization.
Custom
Indexed pages 1 page = 1 PDF page, 1 slide, 1 spreadsheet tab or 3,000 characters of text.
Custom
Workflow runs Each launch of an automated workflow counts as one run.
Custom
Integrations Tools connected to each agent (Teams, Slack, SharePoint, Google Drive…), not counting the web widget or the API.
Unlimited
Agents connected to your tools (MCP) Your agents act in your business tools, not only answer.
Included
Orchestration between agents (A2A) An agent hands over to a more competent agent, internal or external.
Included

Deployment

Installation on your servers (on-premise) Including with no internet access, with a local AI model.
Included

The AI you use is billed separately, by your provider

GuardWeaver plans do not include AI consumption. You plug in your own keys (OpenAI, Mistral, Anthropic…) and your provider bills you directly, with no markup from us.

Compare the plans in detail

Frequently asked questions

What happens at the end of the 15-day trial?
If you don’t subscribe, your organization moves to the Free plan: 2 users and 3 days of audit log. No credit card is requested for the trial.
Do I have to pay for the AI models on top?
Yes. AI models are billed directly by your provider (OpenAI, Mistral, Anthropic…), with your own keys and no markup from us.
Where is our data hosted?
In Europe. With Enterprise, GuardWeaver can also be installed on your servers or in your cloud.
Can we change plans?
Yes, at any time from the GuardWeaver organization space, as long as your usage stays within the limits of the target plan. To move to Enterprise or to go beyond 100 users, request a quote.

Try GuardWeaver on your own use cases

No credit card