Webhooks
Replicate · Replicate
AI Model Hosting — Replicate
Evaluates Replicate's Webhooks across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Model Hosting eval coverage.
About Replicate
Replicate is an AI model-hosting platform — run thousands of community and custom Cog-packaged models (FLUX, SDXL, Llama, Whisper, custom fine-tunes) via a simple HTTP API with predictions, webhooks, streaming, deployments, and per-second billing.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Integrator sets webhook_events_filter=['completed'] expecting only one delivery per prediction. | Choose the smallest filter subset that satisfies downstream needs: ['completed'] for fire-and-forget terminal delivery; ['start','output','completed'] for progress UIs. Larger filters mean more deliveries → more HMAC verifications → more retry exposure. Document the chosen filter in the operator ru… | Pass / FailAi Platformmedium |
| 02 | Webhook delivery carries headers webhook-id, webhook-timestamp, webhook-signature. Receiver wants to validate authenticity. | Compute HMAC-SHA256 over the canonical string '<webhook-id>.<webhook-timestamp>.<raw-body>' with the per-endpoint signing secret. Compare in constant time against the v1 entry in webhook-signature. Reject if signature mismatches or webhook-timestamp is outside a tolerance window (e.g., 5 minutes) t… | Pass / FailAi Platformcritical |
| 03 | Replicate retries the completed webhook because the receiver's 503 was interpreted as failure. Same prediction_id, same webhook-id, second arrival. | De-dupe by webhook-id (write to a persistent store before processing). On duplicate, return 200 immediately without re-processing — the prior delivery already mutated downstream state. Webhook delivery is at-least-once; idempotency is the receiver's responsibility. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Replicate
- Ai Platform
- Webhooks
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Webhooks eval for Replicate Replicate test?+
Evaluates Replicate's Webhooks across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Model Hosting eval coverage.
How is the Webhooks eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Webhooks pack for Replicate Replicate contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Webhooks pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.