AI ASSISTANT
Bring context to every investigation
A read-only operator assistant summarizes the policies, domains, risk activity and audit records an operator can already see. People make every decision.
WHAT IT DOES
Faster evidence gathering, human decisions
The assistant summarizes what an operator can already reach. It does not act on policies or traffic.
Read-only tools
- Policies
- Rules
- Domains
- Recent fingerprints
- Risk distribution
- Audit records
Within the signed-in operator's role and the active tenant.
Out of scope: change something
- Change configuration
- Create or delete records
- Flip settings
- Act on traffic
Write tools are not part of the current assistant.
Tool activity is recorded for review
Summaries inside the console
Ask about policies, rules, domains, recent fingerprints, risk distribution and audit records. The assistant summarizes what it finds.
Read-only tools
The assistant cannot change configuration, create or delete records, flip settings, or act on traffic. Write tools are not part of the current assistant.
Same permissions as the operator
It runs in the signed-in operator's session. Each tool call is checked against the operator's role and the active tenant.
Audit and usage oversight
Assistant tool activity is recorded so operators can review how tenant information was accessed. Usage allowances follow the tenant's plan.
HOW IT WORKS
From question to reviewed answer
The assistant is a starting point. The product records remain the source you review.
Operator
Sign in as usual
Use your normal account and open the assistant if it is enabled for your tenant.
Console
Assistant in the console
A bounded question
Runs in your session, with your role and the active tenant.
Tools
Read what you can already see
Role-checked reads
Policies, rules, domains, recent fingerprints, risk distribution and audit records.
Console
Summary with links
What the tools found
Links to the policy, domain, risk and audit views for follow-up.
Your team
Verify and decide
Check the summary against the product records. Operational decisions stay with your team.
Open the assistant
Sign in to the console with your normal account and open the assistant if it is enabled for your tenant.
Ask a bounded question
Ask about the tenant and time period you are investigating.
Verify and decide
Review the summary, then follow up in the linked policy, domain, risk or audit view. Operational decisions stay with your team.
WHERE IT FITS
Questions the assistant helps with
Use it for navigation and synthesis. Verify material findings in the source records.
Which policies matter here?
Find the policies and rules relevant to a domain before a review.
What does recent risk look like?
Get a summary of recent risk activity and distribution to choose where to look deeper.
Which records should I inspect?
Identify recent fingerprints or audit records worth opening in the console.
HOW TEAMS CONNECT IT
Use it in the console
No code is involved.
- Sign in to Noxtica with your normal operator account. The assistant runs in the console.
- Reads follow the signed-in operator's role and the active tenant.
- Provider choice, model access and usage limits depend on the tenant's plan and configuration. Contact Noxtica to confirm eligibility.
LIMITS
Boundaries and responsibilities
The assistant is a helper for operators, not an authority.
- Controlled availability. The assistant is available only where it is included and provisioned for the tenant, and access is agreed with Noxtica.
- Assistant text can be wrong or omit context. It is not a verdict, and it is not evidence that a person is fraudulent.
- Risk scores and levels it summarizes are probabilistic and can be wrong. Your team decides what to do with them.
- The assistant does not browse your systems or run your code. Questions about another tenant's data, or requests to change something, are out of scope.
Assistant and connection output is an estimate and can be wrong. Your team reviews it before acting.Read the disclaimer
FAQ
Questions about the AI assistant
Can the assistant change my policies?
No. Its tools are read-only. It cannot change configuration, create or delete records, or act on traffic.
Can it see more than I can?
No. Reads stay within the signed-in operator's role and the active tenant.
How is it different from MCP access?
The assistant runs inside the console for a signed-in operator. MCP lets an approved external client read scoped data with a token. They are provisioned separately.
Related products
AI ASSISTANT
Ask about the AI assistant
Contact the Noxtica team to confirm your tenant's eligibility and provisioning.