Introduction
PromptJang is a trusted message delivery platform. Send events to any endpoint — a server, a service, or an AI agent — and we handle retries, cryptographic signing, and full delivery tracking. Your partners can also send events to you through the same platform.
พร้อมแจ้ง — Ready to Inform.
The Problem
Reliable message delivery is deceptively hard:
- Retries — endpoints go down, networks drop, servers return 500s. Events get lost silently.
- Trust — how does the receiver know the message really came from you? How do you prove delivery?
- Observability — did it arrive? What did the endpoint return? How long did it take?
- Recovery — your endpoint was down for 2 hours. Now what?
- Agents — as AI agents join the ecosystem, they need the same reliable delivery guarantees as human-operated services.
Most teams build a half-baked retry loop and move on. The result: silent failures, angry customers, 3am pages.
The Solution
PromptJang is the trusted middle layer between your service and any target:
Three steps:
- Create an endpoint — tell us where to deliver (your customer's URL)
- Send JSON — one POST request with your API key, no signing required
- Check status — query by event ID or your own correlation ID
Bidirectional by Design
PromptJang works in both directions:
Outbound (you send to others): Create an endpoint pointing to your customer's URL. Send events, we deliver with retries and signing.
Inbound (others send to you): Create an endpoint pointing to your webhook URL. Give your API key to your customer. They send events through PromptJang to you.
Same platform. Same signing. Same retry logic. Same audit trail. Your customer is both sender and receiver depending on context.
Built for Agents
The target endpoint doesn't have to be a server. It can be an AI agent, a notification service, or any system that accepts HTTP requests. PromptJang delivers the same way:
- Signed payloads — the agent can verify the message came from a trusted source
- Idempotency — every event gets a unique ID the agent can use to avoid processing duplicates
- Retry with backoff — if the agent is busy, we retry automatically
- Full audit trail — request and response logged for every delivery attempt
As AI agents join company ecosystems, PromptJang becomes the trusted bridge between them.
What PromptJang Does For You
- Retries with backoff — failed deliveries retry automatically (60s, 120s, 240s, up to 5 attempts)
- Signs your webhooks — every outbound delivery is HMAC-SHA256 signed, so your target can verify authenticity
- Tracks every delivery — status code, latency, and error details for each attempt
- Event replay — re-deliver any past event with one API call
- Idempotency support — every event gets a unique ID your target can use to avoid processing duplicates
- SSRF protection — target URLs validated against private IPs and localhost
What You Don't Have To Build
| Without PromptJang | With PromptJang |
|---|---|
| Retry queue with exponential backoff | One POST request |
| Signature generation and verification | We sign for you |
| Delivery attempt logging | Full audit trail in dashboard |
| Payload storage for replay | Stored automatically |
| Monitoring and alerting | Stats API + dashboard |
| SSRF protection on target URLs | Built-in |