Trust answer

The ad never writes into the AI answer.

wavebird runs the sponsor path beside your model path. Your model call stays untouched, and the placement renders in a separate slot your app controls.

App request

Your backend asks wavebird for a placement while the model is generating.

CSL firewall

The signal is reduced to policy-safe delivery metadata.

Approved path

Only configured partner paths can be reached.

Proof

Render and beacon events create the audit trail for settlement.

Two paths, one moment.

When your user sends a prompt, two things happen at the same time. The model thinks. An ad is matched. Neither waits for the other.

User sends prompt

Model path

Your API call runs exactly as usual

~800ms+

Ad path

Filtered signal goes to the approved partner path

< 20ms

Response + ad delivered

Filter

Only topic and language leave your system. No prompts. No PII. No history.

Match

Scoped partner request during model inference. No extra user-side roundtrip.

Prove

Every impression gets signed proof. Auditable. Billable. No self-reporting.

What data leaves your system

Your app

"Plan me a weekend trip to Barcelona with museum visits"

Raw prompt blocked

After firewall

topic: travel, lang: en

Filtered signal allowed

Ad market

Receives only abstract category and language. It never sees the original prompt, user data, or conversation history.

You control what leaves. Config is explicit. Missing config means blocked by default.

The timeline

0 ms5 ms15 ms20 ms800 ms+

Ad pathdone ~20 ms

Model path~800 ms+

Firewall 0.22 ms

Partner roundtrip 15.28 ms

Model inference ~800 ms+

The ad is ready before the model finishes. Zero added latency to the user.

Proof chain

1
Slot created
2
Partner fills
3
Beacon sent
4
Proof signed

Every impression is cryptographically linked to a compute unit. Settlement is signed, auditable, and billable. No self-reported counting.

In code

server-api-flow.ts

typescript

API FLOW

const decision = await fetch("https://api.wavebird.ai/v1/placements?wait_ms=1500", {
  method: "POST",
  headers: {
    Authorization: "Bearer sk_test_your_key",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    client_id: "wbproj_your_client_id",
    session_id: "sess_demo_123",
    job_type: "chat",
    slots_requested: 1,
    slot_hint: { position: "below", max_width: 728, max_height: 90 },
    overrides: { allowed_formats: ["banner", "clip"], timing: "during" },
  }),
}).then((response) => response.json());

return Response.json(decision);

Compliance

Built on Compute Sponsoring v1.0

Profile: CS-S (S1/P0)

✓Ads and AI stay architecturally separated

✓Sponsors never receive user-level data

✓Semantic targeting requires explicit consent

Full API documentation Engineering evidence

Why teams do not start with static ads or a custom ad stack.

The real choice is not whether ads exist. It is whether the ad path fits the GenAI compute moment, stays auditable, and can ship without rebuilding market infrastructure.

Classical display

What you get

Static placements outside the compute moment
Mature demand rails for web inventory
No neutral proof layer for GenAI compute

Why wavebird is different

Runs in parallel to inference
Fits Compute Sponsoring rather than generic display
Keeps proof and delivery independently auditable

Direct build

What you get

Maximum product and policy flexibility
Custom market connectivity and billing paths
Full ownership of consent, proof, and ops

Why wavebird sits in the middle

Keeps rollout incremental
Avoids rebuilding proof, billing, and partner ops
Stays compatible with configured partner paths

wavebird

What you get

Parallel to inference with no extra user-side roundtrip
Neutral infrastructure layer instead of in-app ad logic
Controlled data egress and auditable proof

Why teams adopt it

Compute Sponsoring ready
Rollout without a full ad-stack rebuild
Fits product surfaces that need proof and trust controls

Guide: AI monetization How wavebird works

The ad never writes into the AI answer.

App request

CSL firewall

Approved path

Proof

Two paths, one moment.

Why teams do not start with static ads or a custom ad stack.

Classical display

Direct build

wavebird

Start with the SaaS path.