Auth Throughput Pii And Governance
Unstructured (API + Platform) · Unstructured
Document ETL for LLMs — Unstructured (API + Platform)
Evaluates Unstructured's Auth, Throughput, PII & Governance across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Document ETL for LLMs eval coverage.
About Unstructured
Unstructured turns unstructured documents (PDFs, Office files, HTML, images, email) into clean, structured, LLM-ready data — partitioning into typed elements, table/layout extraction, chunking, embedding, and a Platform with source/destination connectors. Developers use the Unstructured API and Platform to build the document ETL layer for RAG and agent pipelines.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | The Unstructured API key is hardcoded in client-side code and logged in request traces. | Send the API key only in the documented header (api-key / unstructured-api-key) server-side from a secret store; never embed it in client code, URLs, or logs. Rotate keys and scope them per environment. | Pass / FailAi Platformcritical |
| 02 | A bulk partition job hits the Serverless API concurrency limit and starts receiving 429 responses; the agent retries immediately in a tight loop. | On 429, honor Retry-After if present and back off exponentially with jitter; cap concurrency to the account's documented limit rather than hammering. Do not pin a specific RPM/concurrency number [REQUIRES-VERIFICATION] — read it from the account/docs and adapt. | Pass / FailAi Platformhigh |
| 03 | A 100k-document backfill is attempted via synchronous single-document Partition calls and stalls under rate limits and timeouts. | For large volumes, use the Platform's async workflow/job path (with connectors) rather than serial synchronous Partition calls. Submit, poll job status with backoff, and process per-document outcomes. Bound concurrency to the account limit. | Pass / FailAi Platformhigh |
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
- Unstructured
- Ai Platform
- Auth Throughput Pii And Governance
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 Auth Throughput Pii And Governance eval for Unstructured Unstructured (API + Platform) test?+
Evaluates Unstructured's Auth, Throughput, PII & Governance across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Document ETL for LLMs eval coverage.
How is the Auth Throughput Pii And Governance 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 Auth Throughput Pii And Governance pack for Unstructured Unstructured (API + Platform) contains 10 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 Auth Throughput Pii And Governance 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.