AI agents that work through your MCP servers, under your own rules.
Connect your MCP servers and your own code once, then choose which agents use them. Web research and code execution come built in. Each Task returns one result your team can use.Equip each agent for its work
Your agents read and update your systems, research the web and run calculations.Your MCP servers
Connect the servers your teams and vendors already run, then give their Tools to the agents that need them.
Your own code
Turn the Python functions in your application into Tools. Every change they make follows your business rules.
Built-in Web research
Every Task can search the public web, read the pages it needs and cite them in its result.
Built-in code execution
Every Task can run Python or JavaScript to calculate, compare and transform data. Each run is isolated from your systems.
Connect once, reuse everywhere
Every new use case starts with its Tools in place, because your platform team connects each system for the whole company.One MCP Connection per system
Connect each MCP server once, with its own credentials. Every agent you assign uses that connection, so no application team rebuilds the integration.
You choose the agents
Give each agent only the systems its work needs. Your support agent reaches the service desk, and your finance agent reaches the ERP.
Access changes without a release
In the Dashboard, allow or block an MCP Connection’s calls, or remove an agent from it. Every Task picks up the change at its next step.
Each agent uses its Tools under its own identity. Usage analytics shows the success rate of each MCP Connection. For your company documents, agents use Libraries.
Reach systems that only your network can see
Your own code runs next to your private systems and decides each change before it happens.Your ERP, databases and internal tools stay private. Your Python functions run in your own application, inside your network, and your application opens the connection to Duale AI. The functions read and update those systems with your own permissions. When a change needs a person’s decision, your function can record it as a proposal for that person to approve.
See every source at work in one Task
Illustrative example. A sales team delegates the quarterly review of a key account before its renewal.In one Task, the agent reads the open tickets in your service desk through its MCP server. Your own function returns the usage and invoices from your ERP. Web research finds the customer’s latest public news, and code execution calculates the quarter’s trends. The account manager receives one review:
- Usage: up 14% on the previous quarter.
- Support: three open tickets, all about delivery times; the oldest is 12 days old.
- News: the customer announced a new distribution site on 2 October, with a link to its press release.
- Next step: a volume tier at renewal, recorded by your function as a proposal for the account manager to approve.
Start with work that spans your systems
Your systems, Web research and code execution, combined in the work your teams hand over.Sales
Get a sourced brief on each account before the meeting, with the new facts recorded in your CRM. Your own code makes every write to your records.
Due diligence
Get one due diligence memo with every finding sourced. Web research covers the press, and the figures are calculated from the accounts.
Before you open your systems to your agents
One fixed price per Task
A standard Task costs €0.10 and a fast Task €0.20, excluding VAT. See pricing
Your choice of hosting
Use the managed service, hosted in the European Union, or run the Platform in your own infrastructure.
Unlimited agents
Add agents as your teams and use cases grow.
Questions about Tools
Yes. The agent can work on a test copy, such as your CRM sandbox, before you grant it the live system. See which systems your agents can count on in Usage analytics, then see when to create separate connections.
Yes. The permissions you set in your own system keep applying, whichever agent calls your MCP server. See how Identity and access limits each agent, then see which account reaches each server.
Yes. In the Dashboard, each Task shows every call it made to your Tools and how each one ended. See how Usage analytics follows each Task, then read what each outcome means.
No. A Task keeps its fixed price, standard or fast, Web research and code execution included. See the price per Task, then see the Tools built into every Task.