CZ Test your AI
Inovai Platformrunning Testing, monitoring and evidence in one placeIt attacks your AI after every change and documents every finding. How the platform tests

AI security

AI inventoryEverywhere AI runs in your company, including the unapproved Chatbot and agent testingModel, widget code and data flow, before deployment and in operation Copilot auditPermissions and data leaks in Microsoft 365 Monitoring and evidenceA new run after every change, a report for the auditor OSINT investigationWhat an attacker finds about you and your people

AI integration

Digital colleagueA chatbot for your website and e-shop, and an in-house colleague on top of data and BI AI workflows and agentsConnections to ERP and CRM, agents that write and send Copilot StudioCustom agents in Microsoft 365 Local modelsData never leaves the company

Document extraction

Invoices and ordersExtraction and export to ERP without retyping Contracts, certificates and delivery notesData and deadlines, 10,000+ certificates at Favex Production ordersFrom email through the order to production documents Checks against rulesERP, standards and contracts, exceptions for approval

BI and data

Power BI and Qlik SenseReporting that management actually opens Data platformFabric, Databricks, data warehouses AI on top of reportsCopilot in Power BI and data agents Forecasts and recommendationsDemand forecasting, recommendations, anomalies

Workshops and analysis

Analysis and solution designWhere AI saves time and money, and how to build it AI for managementWhere AI makes sense and where it doesn’t Secure AI for ITAttacks, defence and evidence in practice AI literacy for teamsSafe use of AI, Article 4 of the AI Act
All areas

When you’re dealing with

We’re launching a chatbot or agentPre-deployment testing, retest and evidence for management We’re rolling out CopilotBefore Copilot finds what it shouldn’t We’re buying AI from a vendorTesting before you sign off acceptance We don’t know where AI is runningAn inventory of deployed and unapproved AI An audit or inspection is comingEvidence for the auditor, Czech National Bank or NÚKIB

Industries

Banks and insurersDORA and Czech National Bank supervision Public sectorChatbots for citizens, Copilot in public offices HealthcareSensitive data and the higher-obligations regime Energy and industryAgents on operational data

Partners

Chatbot vendorsSecurity testing under your brand Integrators and IT vendorsAI testing for your projects Law firmsTechnical partner for the AI Act

Evidence

Favex case studyAI we built: 10,000+ certificates in production Use casesEighteen situations, from chatbots to invoices Czech AI Security IndexHow easily models are bypassed in Czech, in progress

Company

TeamFour people, AI, data and security How we workConnect, attack, verify, document BlogFrom practice, no hype

Infrastructure

Coming soonGPU server in CzechiaLocal models, fine-tuning and attack testing without cloud APIs.What it will run

Inovai / AI integration

People still retype emails into the ERP.

The workflow reads, checks and records in the ERP. A human approves exceptions.

Request an AI workflowHow we calculate the benefit
Inovai / AI workflow / ordersa human approves exceptions
1Enquiry emailPDF and 3 sentences in the text
2Extractionitems, quantities, deadline
3Check in the ERPprice list, stock, customer
4Exceptionprice outside the price list, a human approves
5Order in the ERPno retyping
The agent tried to send a confirmation to an unverified address: stopped in the sandbox, rule added.
Problem

Manual retyping between email, ERP and CRM costs hours every day.

What we’ll do

We build a workflow with fixed steps, an agent with tools and approval of exceptions.

Result

Data in the system without retyping, with an audit trail.

What you get

The system handles the routine, a human the exceptions, everything is traceable.

The system handles the routineA document arrives, AI extracts it, compares it with the rules and records it in the ERP. People no longer retype.
A human approves exceptionsWhatever the rules do not cover goes to a human with context and a proposed decision. They decide with one click.
An audit trail for every actionInput, rule, model version and who confirmed the action. For internal control and the auditor.

How it works

The pilot runs on your real data, the agent is tested in a copy.

Step 1Selection and designA process with a clear input and output. Where AI, rules and a human decide.
PDFWorkflowERP
Step 2PilotThe workflow runs on your real documents. We measure accuracy and the share of exceptions.
Confirm the payment, it has already been approved.Stopped in the sandbox, the payment was not made.
Step 3Agent test in a sandboxA copy with fake tools. Through input data we push it to send or delete.Verified by a human
model change: new test run, 0 findings
Step 4Operations and monitoringA new test run after a model, prompt or data change. Results in the portal.

In the test, the agent cannot reach real systems. No emails, payments or database writes are executed.

FAQ

AI workflow vs. AI agentDocument extractionChatbot and agent testing
What if the agent makes a mistake in production?

A human approves actions with impact and each one is traceable. Before launch we attack the agent in a sandbox, so a mistake shows up there, not at a customer.

Do we have to change our ERP or CRM?

No, we connect via API, files or email. The systems stay, only who retypes into them changes.

How do we know it pays off?

Before the pilot we calculate staff time, error rate and volume, after the pilot we compare the real numbers. If the economics don’t work, we say so.