End-to-End Configuration Scenarios

These scenarios are schema-backed examples you can adapt directly into policy-config.yaml.

Replace every your-...-model placeholder with a model ID enabled for that provider account before running a scenario.

Provider fallback in these scenarios

Runnable examples omit an explicit providers.fallback block. The gateway already considers later eligible targets using its default trigger list. Its runtime override key is trigger_on; fallback.enabled and max_fallback_attempts do not currently control dispatch. Use providers.routing.allow_fallbacks: false when a scenario must restrict a request to the first eligible target. See Multi-Provider Fallback.

1. Finance assistant with DLP and compliance disclaimers

pack:
  name: finance-assistant
  version: 1.0.0
  enabled: true

providers:
  targets:
    - id: openai-prod
      provider: openai
      provider_type: openai
      format: openai
      model: your-openai-model
      secret_key_ref:
        env: KEEPTRUSTS_OPENAI_API_KEY
    - id: openai-mini
      provider: openai
      provider_type: openai
      format: openai
      model: your-openai-model
      secret_key_ref:
        env: KEEPTRUSTS_OPENAI_API_KEY
  routing:
    strategy: ordered

global_rate_limit:
  max_requests: 500
  window_seconds: 60

user_rate_limit:
  max_requests: 50
  window_seconds: 60
  header_names:
    - X-User-Id

policies:
  chain:
    - prompt-injection
    - pii-detector
    - dlp-filter
    - financial-compliance
    - audit-logger

policy:
  pii-detector:
    action: redact
    pci_mode: true
  dlp-filter:
    blocked_terms:
      - "wire transfer instructions"
      - "raw customer export"
    action: block
    sensitivity_level: restricted
  financial-compliance:
    blocked_patterns:
      - "guaranteed return"
      - "buy this stock now"
    required_disclaimers:
      - "This content is not financial advice."
  audit-logger: {}

audit-logger marks the policy chain and emits an allow result; configure immutable storage and retention in their owning platform controls.

2. HIPAA-aware healthcare assistant

pack:
  name: healthcare-hipaa
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: azure-health
    provider: azure-openai
    provider_type: azure-openai
    format: openai
    model: your-openai-model
    base_url: https://health-resource.openai.azure.com
    secret_key_ref:
      env: KEEPTRUSTS_AZURE_OPENAI_API_KEY
    azure_deployment: your-azure-deployment
    azure_api_version: your-supported-api-version
policies:
  chain:
  - prompt-injection
  - hipaa-phi-detector
  - pii-detector
  - healthcare-compliance
  - audit-logger
policy:
  hipaa-phi-detector:
    mode: hipaa_18
    action: redact
    safe_harbor_method: true
  pii-detector:
    action: redact
    healthcare_mode: true
  healthcare-compliance:
    blocked_patterns:
    - diagnose this patient
    - prescribe a dosage
    required_disclaimers:
    - This content is not medical advice.
    fda_class: II
  audit-logger: {}

3. Defense and export-control gateway

pack:
  name: defense-controls
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: openai-gov
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
ip_allowlist:
  cidrs:
  - 10.100.0.0/16
  - 10.101.0.0/16
policies:
  chain:
  - prompt-injection
  - itar-ear-filter
  - entity-list-filter
  - dual-use-filter
  - audit-logger
policy:
  itar-ear-filter:
    blocked_terms:
    - ITAR
    - EAR99
    - controlled technical data
    action: block
  entity-list-filter:
    blocked_entities:
    - Restricted Aerospace GmbH
    - Acme Ballistics
    action: block
  dual-use-filter:
    blocked_terms:
    - missile guidance
    - centrifuge design
    action: block
  audit-logger: {}

4. EU AI Act recruitment workflow

pack:
  name: eu-ai-act-recruitment
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: openai-eu
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
policies:
  chain:
  - prompt-injection
  - pii-detector
  - bias-monitor
  - eu-ai-act
  - audit-logger
policy:
  pii-detector:
    action: redact
  bias-monitor:
    threshold: 0.85
  eu-ai-act:
    risk_class: high
    articles:
    - 9
    - 10
    - 13
    - 14
    - 15
    action: warn
  audit-logger: {}

The current bias monitor uses a narrow HR-context heuristic and escalates matching outputs; its accepted action and protected_characteristics fields do not change that heuristic. eu-ai-act contributes compliance-report metadata but its action field does not gate inline traffic. Add human-oversight only when every response reaching that chain entry should be escalated.

5. Zero-data-retention routing

pack:
  name: zero-retention-routing
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: openai-zdr
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
    data_policy:
      zero_data_retention: true
      training_opt_out: true
      retention_days: 0
  - id: azure-zdr
    provider: azure
    provider_type: azure-openai
    format: openai
    model: your-azure-openai-model
    base_url: https://replace-with-resource-name.openai.azure.com
    secret_key_ref:
      env: KEEPTRUSTS_AZURE_OPENAI_API_KEY
    azure_api_version: your-supported-api-version
    azure_deployment: your-azure-deployment
    data_policy:
      zero_data_retention: true
      training_opt_out: true
      retention_days: 0
  - id: openai-standard
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
    data_policy:
      zero_data_retention: false
      training_opt_out: true
      retention_days: 30
  routing:
    strategy: ordered
  logging:
    redact_message_bodies: true
policies:
  chain:
  - data-routing-policy
  - audit-logger
policy:
  data-routing-policy:
    require_zero_data_retention: true
    require_no_training: true
    on_no_compliant_provider: block
    log_provider_selection: true
  audit-logger: {}

6. Route-specific policy chains and consumer request budgets

pack:
  name: multi-tenant-gateway
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: primary
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
routes:
- name: chat-route
  path: /v1/chat/completions
  chain:
  - prompt-injection
  - pii-detector
  - audit-logger
- name: responses-route
  path: /v1/responses
  chain:
  - prompt-injection
  - audit-logger
consumer_groups:
  key_header: Authorization
  groups:
  - name: enterprise
    api_keys:
    - 2cc1df694fd36b77cce455e8444733925101d967911cc58e52a426bc7a2ba7df
    rate_limit:
      max_requests: 1000
      window_seconds: 3600
  - name: starter
    api_keys:
    - 99413e437250b08389a70ed27ea55032a0355c75a0cc9c55641736cf68f32615
    rate_limit:
      max_requests: 50
      window_seconds: 3600
global_rate_limit:
  max_requests: 2000
  window_seconds: 60
policies:
  chain:
  - prompt-injection
  - pii-detector
  - audit-logger
policy:
  prompt-injection: {}
  pii-detector:
    action: redact
  audit-logger: {}

Current runtime boundary: route and consumer-group resolution applies to Chat Completions and Responses requests. A matched route selects its chain; parsed route fields such as upstream and strip_path do not change dispatch. A matched consumer group enforces rate_limit.max_requests and window_seconds; its parsed upstream and rate_limit.max_tokens fields are not enforced. Provider selection continues through providers.routing.

7. Execution-target agent workflow

This scenario is for a standalone or local gateway. Connected gateways mark execution targets inactive and do not launch the runner.

pack:
  name: claude-agent-gateway
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: claude-agent
    provider: claude-agent-sdk
    model: your-anthropic-model
    secret_key_ref:
      env: KEEPTRUSTS_ANTHROPIC_API_KEY
policies:
  chain:
  - agent-firewall
  - prompt-injection
  - tool-validation
  - tool-budget
  - audit-logger
policy:
  agent-firewall:
    allowed_tools:
    - Read
    - Write
    blocked_tools:
    - WebFetch
    max_actions_per_session: 100
  tool-validation:
    declared_tools:
    - Read
    - Write
    allow_undeclared: false
  tool-budget:
    budgets:
      Read:
        max_tokens: 5000
        max_cost_usd: 0.5
      Write:
        max_tokens: 10000
        max_cost_usd: 1.0

8. Quality benchmarking with always-on post-quality review

pack:
  name: quality-benchmarking
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: openai-prod
    provider: openai
    provider_type: openai
    format: openai
    model: your-openai-model
    secret_key_ref:
      env: KEEPTRUSTS_OPENAI_API_KEY
policies:
  chain:
  - citation-verifier
  - quality-scorer
  - flagged-review
  - audit-logger
policy:
  citation-verifier:
    require_sources: true
    min_confidence: 0.8
  quality-scorer:
    benchmarks:
      ragas_faithfulness: true
      ragas_relevancy: true
      bleu_score: true
    assertions:
    - type: contains
      config:
        value: source
    - type: llm-rubric
      config:
        rubric: The answer should be grounded and easy to verify.
      threshold: 0.8
    thresholds:
      min_aggregate: 0.8
      min_faithfulness: 0.8
    failure_action:
      action: block
  flagged-review:
    mode: review_and_return
    provider:
      name: review-llm
      endpoint: https://api.openai.com/v1/chat/completions
      model: your-openai-model
      secret_key_ref:
        env: KEEPTRUSTS_OPENAI_API_KEY
      timeout_ms: 5000

This chain does not use flagged-review as a quality-failure fallback. A quality failure with action: block returns immediately, before the later policy runs. A response that passes quality-scorer proceeds to flagged-review, so the review provider runs on every response that reaches that point in the chain.

Next steps

Declarative Config Reference — Schema details for each section
Policy Controls Catalog — All available policies
Config Testing — Add test suites to validate scenarios
Providers Configuration — Provider target setup

1. Finance assistant with DLP and compliance disclaimers​

2. HIPAA-aware healthcare assistant​

3. Defense and export-control gateway​

4. EU AI Act recruitment workflow​

5. Zero-data-retention routing​

6. Route-specific policy chains and consumer request budgets​

7. Execution-target agent workflow​

8. Quality benchmarking with always-on post-quality review​

Next steps​