Skip to main content
PromptWall sits between your application and your LLM. It captures every request, surfaces them on a unified Observability dashboard, and (optionally) enforces runtime policies — block, rewrite, or regenerate — when an answer violates your rules. You can integrate in three ways, all of which feed the same dashboard:

Full Control

Recommended. Drop-in OpenAI replacement. Change OPENAI_BASE_URL to PromptWall and you get observability immediately. Runtime control is opt-in.

Verify

Keep calling your LLM directly. POST the prompt + answer to /v1/verify and PromptWall validates it against your policies.

Events

Observability-only ingest. Use when PromptWall did not run the LLM (your own SDK, a vendor like Moveo, or a log archive).

How the modes compare

FeatureProxyVerifyEvents
EndpointPOST /v1/chat/completionsPOST /v1/verifyPOST /v1/events
Required keysOpenAI and PromptWallPromptWall onlyPromptWall only
Control modesobserve / guard / verify / fullblock / rewrite / regeneratenone (read-only)
Code changeTwo env varsTwo SDK linesOne HTTP POST
Observability✓ Always on✓ Always on✓ Always on
You can mix modes. Some apps use Proxy while others use Verify or Events. They all write to the same canonical event log and show up on the same Observability dashboard.

What you get out of the box

  • Org-wide AI activity sliced by use case · team · app · integration
  • Cost & token rollups at 1-minute / 1-hour / 1-day granularity
  • Trace drill-through for every request (prompt → guards → upstream → policy hits)
  • Failure-cluster panel showing the top patterns this week
  • Policy synthesis that watches traces and suggests new guards
  • Usage-based billing primitives (volume only — never per use case)
Next: pick an integration mode →