Documentation Index
Fetch the complete documentation index at: https://docs.neuraltrust.ai/llms.txt
Use this file to discover all available pages before exploring further.
Content moderation controls what your application is allowed to say and be asked about — financial / legal / medical advice, political or religious content, competitor mentions, internal-policy leakage, and more — on either side of the LLM call.
Moderation is not a separate screen: it’s a detection you pick inside a policy’s When condition, just like Prompt Guard.
Apply to prompts or responses
The same detections run on either direction of the traffic — you control this with the condition’s Field:
| Field | Moderates | Typical use |
|---|
| Input | What the user sends to the model. | Stop off-policy questions before they hit the LLM. |
| Output | What the model generates. | Prevent the LLM from saying something the product, brand, or regulator forbids. |
Topics — the built-in catalog
In Create Policy → When, open the detection picker and pick the Topics category. It ships with the following out-of-the-box topics:
| Topic | Catches |
|---|
| Financial Advice | Recommendations on investments, trades, tax strategy, etc. |
| Legal Advice | Advice on contracts, litigation, legal interpretation. |
| Medical Advice | Diagnoses, treatment suggestions, dosage guidance. |
| Political Content | Political opinions, parties, elections, activism. |
| Religious Content | Religious beliefs, practices, comparative religion discussions. |
| Internal Policies | Leakage of internal guidelines, SOPs, or playbooks. |
| Confidential Projects | Codenames, unannounced initiatives, sensitive programs. |
Financial Advice + Legal Advice; a healthcare assistant might enable Medical Advice; an internal copilot might enable Internal Policies + Confidential Projects.
How a topic condition looks
Once selected, the condition row reads like any other When condition:
Input · triggers · Topics: Financial Advice, Legal Advice
+ Add Condition — per the policy model, rows always combine with AND, so for OR semantics use multiple policies.
Keyword & Regex — deterministic rules
Alongside the classifier-driven Topics catalog, you can attach deterministic lists:
| List | Use for |
|---|
| Blocked Keywords | Exact or substring matches — brand names, competitors, policy vocabulary. |
| Regex Patterns | Structured matches — SKUs, internal IDs, complex compliance patterns. |
Sensitivity
Topic and keyword detections expose a 5-level sensitivity scale:
| Level | Profile | Good for |
|---|
| L1 — Lenient | Minimal filtering, only the most obvious violations. | Internal or already-hardened traffic. |
| L2 — Light | Low sensitivity, catches clear cases. | Low-risk customer apps. |
| L3 — Balanced | Recommended default — clear threats with low false-positives (~85% threshold). | Typical production routes. |
| L4 — Enhanced | Higher sensitivity, flags borderline content. | Regulated or high-risk workloads. |
| L5 — Strict | Maximum protection, strictest filtering. | Kids / health / finance / government. |
Log policy, review the hits on real traffic, then raise the level and/or promote the action to Block once the false-positive rate is acceptable.
Using moderation in a policy
Standard Where / When / Then flow:
- Where — typically the
Gateway surface, optionally filtered by Routes or Applications.
- When —
Input · triggers · Topics: … (for the prompt side), and/orOutput · triggers · Topics: … (for the generation side).
- Then —
Log while tuning, Block once the policy is ready for enforcement.
A single policy can mix Topics with Keyword/Regex rows and other Content Security detections — they all AND together.
Common policies
- Keep a fintech assistant off financial advice —
Output · triggers · Topics: Financial Advice, Legal Advice → Block.
- Block medical advice on a general-purpose chatbot —
Output · triggers · Topics: Medical Advice → Block.
- Protect internal policy leakage on external routes —
Output · triggers · Topics: Internal Policies, Confidential Projects → Block.
- Log political and religious content for review —
Input + Output · triggers · Topics: Political Content, Religious Content → Log.
