PII redaction on every message
Emails, phones, SSNs, cards, IPs detected and masked before the prompt leaves your gateway. Customer data never lands unredacted in a provider log. Every redaction recorded.
Use Case · Customer Support
Support bots with guardrails built in.
Support traffic carries real customer data and the occasional hostile prompt. NemoRouter redacts PII and blocks injection on every request, keeps tone consistent with versioned templates, and caps spend with budgets.
support-bot · guardrail trace
Every message, screened first
Injection scanclean
PII detectedemail, phone
PII actionredacted
Prompt templatesupport-v4
Modelgemini-2.5-flash
Budget$18 / $50
PII-safeinjection-blockedbudgeted
- PII categories
- 5
- Injection defense
- Every request
- Prompt tone
- Versioned
- Spend
- Budgeted
Email, phone, SSN, card, IP — redacted
Inbound jailbreak patterns blocked
One template drives the whole fleet
Per-key and per-team cost ceilings
Why Nemo for support
Safety, consistency, and cost — handled
A support bot is the part of your AI stack that talks to real customers. It needs to protect their data, resist abuse, stay on-brand, and not blow the budget.
Prompt-injection defense
A public-facing bot gets hostile inputs. Jailbreak and instruction-override patterns are blocked before the provider call and surfaced in the guardrail log for review.
Versioned prompt templates
Tone, escalation rules, and brand voice live in one central template. Edit it and every bot updates; A/B test two versions, roll back without a redeploy.
Cost control for bursty volume
Per-key and per-team budgets cap spend with a hard 402 ceiling, while caching absorbs the repeated FAQ traffic that drives most support volume.
How it works
A support message, screened end to end
Every inbound message passes the same gates: injection detection, then PII redaction, then the templated prompt. Guardrails run before the model ever sees the text.
Support request flow
Customer message
inbound to your bot
Real names, account details, sometimes a hostile prompt.
Injection check
guardrail · pre-call
Jailbreak / override patterns blocked before the model.
PII redaction
guardrail · pre-call
Email, phone, SSN, card, IP masked from the prompt.
Template + model
prompt template id
Central system prompt; routed to your chosen model.
Reply + logged
guardrail log
Redactions, blocks, cost, and latency all recorded.
Guardrails run inline before the provider call. A blocked or redacted message never reaches the model, and the event is logged so your trust and safety team can review it.
The code
Reference a template, let guardrails run
Your bot calls the standard chat endpoint and points at a prompt template by id. Guardrails apply automatically. You do not wire them per request. These snippets are generated from the SDK examples the playground uses.
Install
pip install openai| 1 | # Cache: enabled (org default). Pass nemo_cache: false to skip. |
| 2 | from openai import OpenAI |
| 3 | import os |
| 4 | |
| 5 | client = OpenAI( |
| 6 | api_key=os.environ["NEMOROUTER_API_KEY"], |
| 7 | base_url="https://api.nemorouter.ai/v1", |
| 8 | ) |
| 9 | |
| 10 | response = client.chat.completions.create( |
| 11 | model="gemini-2.5-flash-lite", |
| 12 | temperature=1, |
| 13 | max_tokens=1024, |
| 14 | messages=[ |
| 15 | {"role": "user", "content": "Hello! What models do you support?"}, |
| 16 | ], |
| 17 | extra_body={ |
| 18 | # "nemo_cache": False, # Uncomment to skip cache |
| 19 | }, |
| 20 | ) |
| 21 | |
| 22 | print(response.choices[0].message.content) |
Pass nemo_prompt_template_id in extra_body to drive tone from a central, versioned template.
FAQ
Common support-bot questions
How does NemoRouter protect customer PII in support conversations?
PII redaction runs as a guardrail on every request. It detects and masks email addresses, phone numbers, SSNs, credit-card numbers, and IP addresses before the prompt reaches the model, so customer data never sits in a third-party provider log unredacted.
Can guardrails block prompt-injection attempts from customers?
Yes. A prompt-injection detection guardrail inspects every inbound message for jailbreak and instruction-override patterns. A flagged request is blocked before it reaches the model, and the event is recorded in the guardrail log.
How do I keep a support bot’s tone consistent across the team?
Versioned prompt templates hold the system prompt centrally. The bot references a template by id and passes variables at call time; editing the template updates every bot at once. A/B test two template versions to measure which resolves tickets better.
Can I limit how much a support bot costs per month?
Yes. Set a per-key or per-team budget on the bot’s virtual key. When the budget is reached the gateway returns a 402 rather than overspending, and caching absorbs the repeated FAQ traffic that drives most support volume.
Safe by default
Ship a support bot your security team signs off on
PII redaction, injection defense, versioned prompts, and budgets — all unlocked on every plan across 240+ models.