> ## Documentation Index > Fetch the complete documentation index at: https://docs.promptshields.com/llms.txt > Use this file to discover all available pages before exploring further. # Policies > The Guideline to Strict lifecycle — observe first, enforce second, with an automatic rollback. Two ideas explain the entire policy system. Internalise these and the rest follows. The product ships expert-authored templates — OWASP LLM Top 10, EU AI Act, GDPR, PCI/HIPAA, Shadow AI, Content Safety. Templates are read-only. Every policy you actually run is a **clone** that you own and tune. Policies start in **Guideline** mode — they observe and log what they *would* have caught, and change nothing. Only once you trust the data do you promote to **Strict**, where the same detectors act in real time. This separation exists to answer the hardest question in policy enforcement — *"is this rule going to break our users?"* — with data, before you flip the switch. ## The lifecycle ``` NEW POLICY │ ▼ ┌─────────────┐ │ GUIDELINE │◄──────────┐ │ log only │ │ └──────┬──────┘ │ │ │ Promote request │ ▼ │ [Pending approvals] │ │ │ All approvers approve │ ▼ │ ┌─────────────┐ │ │ STRICT │ │ │ block/redact│ │ └──────┬──────┘ │ │ │ ┌──────┴──────┐ │ Manual Watchdog │ "Pause" auto-demote │ └──────┬──────┘ │ └──────────────────┘ ``` ## Day 1 — clone a template Then choose **New from template** to reach the template library. Filter by category, or search by OWASP reference (`LLM02`) or regulation (`Art. 9`). Each template card opens to its rationale, an example violation, its detectors, and every tunable parameter with its default and help text. Give it a name that means something in your environment — "PII Output — Customer Service" beats the generic template name. Optionally pre-select which applications it applies to. A new policy is **always created in Guideline mode**, regardless of what the template suggests. There is no way to create a policy that starts enforcing. This is deliberate. ## Days 1 to 14 — tune and observe Four tabs on the policy detail page do the work: | Tab | What it is for | | ------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Detection** | The detectors and their tunable parameters. Each parameter is marked `basic`, `advanced`, or `expert`, so you can choose how deep to go. A locked parameter means the template author marked it unsafe to tune. | | **Scope** | Which applications the policy applies to, plus broader filters — data classification, risk tier, department. | | **Test** | Paste a sample prompt, run it, and see exactly which detectors fire with confidence scores and matched substrings. | | **History** | Every mode change over the policy's life. | The **Test** tab is a pure simulation. No state changes, no violations recorded. Use it as much as you like to dial in parameter values before any real traffic is affected. Meanwhile the policy is observing live traffic in the background and logging every near-miss. After 30 days you have real numbers: total evaluations, would-block count, and false-positive rate. ## Day 14 onward — promote to Strict Promotion is gated on two conditions: 1. At least **14 days** in Guideline mode 2. A false-positive rate below the threshold — **2%** by default Until both are met, the promote button tells you exactly what is missing: *"Need 8 more days in Guideline mode"* or *"FP rate is 3.4% — must be below 2%"*. When it unlocks, a four-step wizard opens: Blast-radius arithmetic from the last 30 days of observation — for example, *"Switching to Strict would have blocked 142 events, 0.31% of traffic, with 3 estimated false positives affecting 47 users."* No surprises. **All** for immediate full coverage, **canary** to start with one application, or **phased** for a gradual percentage ramp. Set the auto-demote threshold — by default, revert if the live false-positive rate exceeds 5%. This is the watchdog, and it is the reason promotion is not a one-way door. See which roles must sign off, then send the request. The policy stays in Guideline until every approval lands. ### Who has to approve Required approvers are determined by the template's category: | Category | Required approvers | | ------------------------------ | ---------------------------------- | | OWASP LLM | Security Lead | | EU AI Act | DPO + Security Lead | | GDPR | DPO | | Industry (PCI / HIPAA / Legal) | Security Lead + Compliance Officer | | Content Safety | Trust & Safety Lead | | Shadow AI | Security Lead | One rejection freezes the request and the policy stays in Guideline; submit a new request when you are ready. When the **last** required approval lands, the policy flips to Strict automatically and begins enforcing. ## Steady state — enforcing A Strict policy shows a live badge and running statistics: blocks over 30 days, false-positive rate, and rollout strategy. The **watchdog** polls every 15 seconds, comparing the live false-positive rate against your auto-demote threshold: | Condition | What you see | | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | Healthy | Nothing. The system stays out of your way. | | Over threshold | A grace-period banner with a live countdown — *"FP rate 5.2% > 5% threshold — auto-demote at T-04:32"* | | Recovered | A brief *"Recovered — back below threshold"*, then it disappears | | Auto-demoted | *"Auto-demoted by watchdog: FP rate sustained above threshold"* — the policy is back in Guideline, with the watchdog recorded as the actor in History | ## The safety valve An admin can demote a Strict policy to Guideline **at any time, with no approvals required**. Increasing safety — less enforcement — never needs a second signature. Only increasing enforcement does. Use **Pause to Guideline** on the mode toggle. You are back in observation mode immediately. ## Simple and Advanced views The Policies page has a **Simple ⇄ Advanced** toggle. Simple presents a compact table and a straightforward creation flow for teams that want a handful of sensible rules. Advanced exposes the full template library, per-parameter tuning, scope filters, and the approval machinery. Both operate on the same underlying policies. The toggle changes what you see, not what runs.