Platform Workflows And Connectors
Unstructured (API + Platform) · Unstructured
Document ETL for LLMs — Unstructured (API + Platform)
Evaluates Unstructured's Platform Workflows & Connectors across 9 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 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator builds a Platform workflow but wires partition after the embedding transform, so embeddings run on raw bytes instead of chunked elements. | Order the workflow DAG correctly: source connector → partition → chunk → (enrich) → embed → destination connector. Embedding must run on chunked elements, not on raw documents. Validate the node order before scheduling the workflow. | Pass / FailAi Platformhigh |
| 02 | A SharePoint source connector is configured with an over-broad admin credential that can read the entire tenant, not just the target document library. | Scope connector credentials to least privilege — only the specific drive/library/bucket the workflow needs. Store credentials in the Platform's secret store, never inline in the workflow config or logs. Rotate on schedule. | Pass / FailAi Platformcritical |
| 03 | A scheduled workflow re-reads an entire S3 bucket every run instead of only changed/new objects, re-embedding everything and inflating cost. | Use the connector's incremental-ingest capability so only new/changed source objects are re-processed between runs. Verify the change-detection cursor advances and that unchanged documents are skipped; do not full-scan every schedule. | 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
- Platform Workflows And Connectors
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 Platform Workflows And Connectors eval for Unstructured Unstructured (API + Platform) test?+
Evaluates Unstructured's Platform Workflows & Connectors across 9 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 Platform Workflows And Connectors 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 Platform Workflows And Connectors pack for Unstructured Unstructured (API + Platform) 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 Platform Workflows And Connectors 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.