The first AI that manages your infra
Iris doesn't just answer questions — it works your dashboard for you: diagnose an outage, lock down an open endpoint, tune a rule, compile a report. Before any change it previews the real blast radius against your live traffic; after a change it measures the effect and rolls back automatically if it hurts. Acts only within your permissions, and logs everything.
- Confirms every change
- Acts under your role
- Fully audited
The same trustworthy loop, every time
By default Iris changes nothing without your approval. Every action follows the same closed loop.
Ask
Describe what you want in plain language — “secure my open endpoints”, “why is api-prod down?”
Preview the blast radius
Before it writes a rule, Iris replays your recent real traffic through the proposed change and shows exactly what it would affect — how many requests newly blocked, how many were succeeding — with a safe / risky verdict.
Apply, verify, roll back
You approve; it applies within your permissions and logs it. Then it watches the real effect for a few minutes and reverts the change automatically if traffic regresses.
Just ask
Real requests, turned into real work on your account.
“Why is api-prod down?”
Splits platform vs. your origin, checks the agent and last error, and points to the fix.
“Secure all my open endpoints”
Finds every endpoint with no authentication and locks them down in one approved step.
“Who can reach this endpoint?”
A plain-language exposure report across auth, firewall, and IP rules.
“Generate an account report”
A multi-section summary you can download as HTML or PDF, tables as CSV.
Opt in to hands-off, one class at a time
Once you trust the loop, let Iris handle the safe, reversible work on its own — turned on per action type, never all-or-nothing.
Per-class control
For each action type — block a confirmed attacker, relax a proven false positive, tune a rate limit — choose ask first, canary, or automatic. Everything else keeps asking.
Only when it's safe
An automatic change happens only if the traffic dry-run says it's safe. Anything risky, or anything Iris can't fully simulate, still comes to you.
Self-correcting
Every automatic change is verified against real traffic and reverted on regression. Too many reverts in an hour and that action type switches itself back to ask-first.
Declare a goal — Iris keeps it true
Set an objective and it's continuously reconciled. Miss it, and Iris tells you why and how to fix it — or, where it's safe, fixes it for you.
“Keep p95 latency under 300 ms”
Watches the endpoint; on a breach it diagnoses origin-vs-edge and walks you through the fix.
“Keep my error rate under 1%”
Flags the moment it slips and names the endpoints driving it.
“Certificates never within 7 days of expiry”
Renewals stay ahead of expiry before anything breaks.
“Stay under 80% of my data cap”
Warns early with room to act, not after you're throttled.
Two ways to use AI
A one-shot generator for drafting rules, and Iris — the chat agent — for everything else.
AI Generate
- Firewall policies — even fuzzy intents like “block scanners”
- Traffic-policy rules — rate limit, redirect, custom response, headers, JWT
- Routing rules — picks the right agent from your connected fleet
- Rate-limit rules — conditions, scope, window, action
- Error-page templates — full HTML/CSS with error tokens
Iris
- Edit, disable, delete & reorder rules — “disable the jwt-verify rule”
- Diagnose & fix — “why is my endpoint down?”
- Secure — “who can reach this?”, “secure all my open endpoints”
- Reports — compile one, download as HTML/PDF or CSV
- Multi-step flows, navigation, docs lookups, ticket creation
When to use which
| If you want to… | Use |
|---|---|
| Add a new rule from a description | AI Generate button on the tab |
| Toggle / disable / delete / rename a rule | Iris chat |
| Change the order of rules | Iris chat or drag the card on the Routing Rules tab |
| “Show me all my rules that …” | Iris chat |
| Hand-edit many rules at once | YAML mode (Routing Rules / Traffic Policy tab) |
| “How do I configure X?” | Iris chat (it searches the docs + KB) |
If you type an edit intent (“disable…”, “delete…”) into AI Generate, it'll hand off to chat with your message pre-filled — one Enter away.
YAML mode
Routing Rules and Traffic Policy each have a Visual ↔ YAML toggle. Hand-edit, paste, or diff in version control; Apply replaces every rule under the policy atomically.
rules: - name: "API to api-backend" priority: 100 target_agent_id: "api-backend" enabled: true conditions: - match: path pattern: "/api/*"
rules: - phase: on_http_request rule_type: rate-limit name: "Login rate limit" priority: 50 enabled: true config: limit: 5 window: 60 scope: ip
The AI Generate button drops rules straight into the YAML editor when YAML mode is active — review and Apply, no modal needed.
Programmatic access
Every generator is also an HTTP endpoint — for scripted onboarding, infra-as-code seed scripts, or CI that drafts starting-point rules.
Built to be trusted
Iris acts on real infrastructure — so it asks before it changes anything, can only do what you could by hand, and records every action.
Confirm before every change
No write happens silently. Iris shows a confirmation card with a plain-language title and a field-by-field preview — create, update, or delete — and waits for your Approve.
Acts as you, never above you
Iris runs under your own session and role — it can only do what your permissions and plan allow. Out-of-scope and irreversible account actions are blocked on the server.
Every action is logged
Each change is recorded in an audit log on your account — what was done, when, and the outcome — so there's always a record you can review.
Proactive, not just reactive
Iris watches your account and flags issues before you ask — a cert about to expire, usage nearing a limit, an endpoint that just went down — with a one-click path to resolve each.
Cost & limits
Usage and write authority are both bounded per plan — so AI spend stays predictable and the assistant can't run away.
Token & rate budget
Every generate call and chat message counts against your plan's monthly token budget and per-hour message limit.
Per-plan action cap
The number of changes Iris can make per hour is capped per plan, so an unexpected loop can never run away.
Confirmed & logged
Nothing changes without your Approve, and every action is written to your account's AI activity log.
Let AI run your edge.
Start free and let Iris draft, tune, and audit your gateway — every change previewed and logged.