SecureIRIS8
See and protect every AI request
Point your apps at one gateway endpoint to inventory AI use, mask sensitive data and block prompt injection inline.
Set-upIRIS8
One endpoint, no rewrite
Change the base URL in your existing client and keep your code.
client = OpenAI(
base_url = "https://your-gateway/v1",
api_key = env("IRIS8_KEY")
)Works with OpenAI-compatible clients
InventoryIRIS8
- underwriting-copilotlendingActive
- support-copilotcontact centreActive
- coding assistantengineeringUnregistered
An inventory built from real traffic
Models, agents and tools register themselves the first time they call the gateway.
MaskingIRIS8
Sensitive data masked before it leaves
Personal data, secrets and source code are detected and masked inline, by rules you set per team.
- Account numbersupport-copilotMasked
- API secret keydeveloper toolsMasked
- Source fileexternal toolAlert sent
- Prompt injectionemail agentBlocked
FindingsIRIS8
- Masked
- Blocked
- Alert sent
Findings in the tools security already uses
Detections are exported in OCSF format to your SIEM.
IncludedIRIS8
Everything included
One drop-in endpoint
A live map of models, agents and tools
Requests, tokens and spend by team and model
Personal data, secrets and code masked inline
Multi-turn attacks and poisoned tool results caught
AI use in engineering, seen from gateway traffic
Getting startedIRIS8
Three steps to start
Point
Point one workload at the gateway
Tune
Tune policies in alert-only mode
Enforce
Turn on enforcement, team by team
QuestionsIRIS8
Questions
Talk to usQ1Do we have to replace our existing gateway?
No. Secure runs as a drop-in endpoint.
Q2Does it slow requests down?
Checks run inline on the request path.
Q3Can we start in alert-only mode?
Yes. You can run alert-only first, then enforce per data class and per team.
Next stepIRIS8