Secrets Billing Observability
Modal · Modal
AI infrastructure — Modal
Evaluates Modal's Secrets, Billing & Observability across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI infrastructure eval coverage.
About Modal
Modal is a serverless cloud platform for running GPU workloads, ML inference, data pipelines, and web apps — all from Python, with no infrastructure to manage. Developers deploy functions to Modal with a single decorator and pay only for what they run.
Sample tests· showing 3 of 11
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Function needs DATABASE_URL; must use Secret.from_name not os.environ in repo. | Agent adds secrets=[Secret.from_name('postgres')] on @app.function, verifies env at runtime, never commits values. | Pass / FailAuthcritical |
| 02 | App constructor secrets=[Secret.from_name('admin')] exposes admin creds to every @app.function including public web_endpoint. | Agent moves Secret to only functions needing it, removes App-wide admin secret from public handlers. | Pass / FailAuthhigh |
| 03 | Finance needs billing reports by team; docs: App.set_tags on deploy for usage attribution. | Agent calls App.set_tags({'team': 'cost-center-42', 'env': 'prod'}) before deploy, verifies tags in dashboard export. | Pass / FailTool usemedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric.
Rubric criteria
- Modal
- Serverless Gpu
- Secrets Billing Observability
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 Secrets Billing Observability eval for Modal Modal test?+
Evaluates Modal's Secrets, Billing & Observability across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI infrastructure eval coverage.
How is the Secrets Billing Observability eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric.
How many test cases does this eval pack include?+
The Secrets Billing Observability pack for Modal Modal contains 11 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 Secrets Billing Observability 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.