How Extend’s scores are calculated

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

• [probe] https://docs.extend.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.extend.ai/llms.txt # Extend > Extend is a platform for building, iterating on, evaluating, and deploying AI-powered document processing in”
• [claimed-docs] https://docs.extend.ai/agent-quickstart“Agent Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/mcp“Using Extend via MCP | Extend Documentation”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://www.extend.ai“pip install extend-ai”
• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/sdks“SDKs | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/general/async-processing.md#sync-vs-async“Every processing endpoint in Extend (extract, classify, split, parse, and edit) supports both a synchronous and asynchronous mode.”
• [claimed-docs] https://docs.extend.ai/general/test-environment-guide.md“Runs made with a test API key never touch production data and never fire production webhooks”
• [probe] https://docs.extend.ai/cli“official CLI documented at https://docs.extend.ai/cli”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://docs.extend.ai/mcp“Using Extend via MCP | Extend Documentation”
• [probe] https://docs.extend.ai/mcp“official MCP server documented at https://docs.extend.ai/mcp”

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

• [claimed-docs] https://docs.extend.ai/mcp“Using Extend via MCP | Extend Documentation”
• [probe] https://docs.extend.ai/mcp“official MCP server documented at https://docs.extend.ai/mcp”

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”
• [probe] https://docs.extend.ai/cli“official CLI documented at https://docs.extend.ai/cli”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

• [claimed-docs] https://docs.extend.ai/api-reference/authentication“Authenticate a request”
• [claimed-docs] https://docs.extend.ai/sdks“SDKs | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-reference/endpoints/file/upload-file.md“This endpoint accepts file contents and registers them as a File in Extend, which can be used for running workflows, creating evaluation set items, parsing, etc.”
• [claimed-docs] https://docs.extend.ai/general/async-processing.md#sync-vs-async“Every processing endpoint in Extend (extract, classify, split, parse, and edit) supports both a synchronous and asynchronous mode.”
• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”
• [community] https://hn.algolia.com/api/v1/items/45529628“We've been using Extend for over a year and have been super happy with the product and accuracy of the data extraction.”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://www.extend.ai“pip install extend-ai”
• [claimed-docs] https://docs.extend.ai/sdks“SDKs | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-reference/authentication“Authenticate a request”
• [claimed-docs] https://docs.extend.ai/api-reference/endpoints/file/upload-file.md“This endpoint accepts file contents and registers them as a File in Extend, which can be used for running workflows, creating evaluation set items, parsing, etc.”

Subscribe to events via webhooksweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [claimed-docs] https://docs.extend.ai/webhooks/configuration“Webhook Configuration | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/general/test-environment-guide.md“Runs made with a test API key never touch production data and never fire production webhooks”
• [claimed-docs] https://docs.extend.ai/general/async-processing“Async Processing | Extend Documentation”

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://docs.extend.ai/api-reference/authentication“Authenticate a request”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-reference/endpoints/file/upload-file.md“This endpoint accepts file contents and registers them as a File in Extend, which can be used for running workflows, creating evaluation set items, parsing, etc.”
• [claimed-docs] https://docs.extend.ai/sdks“SDKs | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 8 (quality) × 1.0 (full) = 8.0 of 10 max

• [claimed-docs] https://docs.extend.ai/general/test-environment-guide.md“Runs made with a test API key never touch production data and never fire production webhooks”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [claimed-docs] https://docs.extend.ai/evaluation/processors.md#versioning“the thing you version and iterate on in Extend Studio, and the unit you evaluate and optimize”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”
• [claimed-docs] https://docs.extend.ai/model-versioning/overview.md“Base model versions are Extend's underlying model releases, selected with the baseVersion config field.”
• [claimed-docs] https://docs.extend.ai/api-reference/authentication“Authenticate a request”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/mcp“Using Extend via MCP | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/sdks“SDKs | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/api-quickstart“API Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/agent-quickstart“Agent Quickstart | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/evaluation/processors.md“you save that config once as a processor, give it a stable id, and reference it from then on”
• [claimed-docs] https://docs.extend.ai/evaluation/processors.md#versioning“the thing you version and iterate on in Extend Studio, and the unit you evaluate and optimize”
• [claimed-docs] https://docs.extend.ai/evaluation/overview.md“Evaluation sets let you test the accuracy of your document processors reliably and repeatedly.”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”
• [claimed-docs] https://www.extend.ai/pricing“Composer & Review Agent”

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://docs.extend.ai/security/data-handling“Data handling, Zero Data retention: "We maintain automatic data-retention policies that vary in default length by billing tier and can be configured to fit your policy. We also support zero data retention options." — including ZDR with AI subprocessors, configurable at the workspace level.”
• [claimed-docs] https://docs.extend.ai/security/data-handling“Data Handling | Extend Documentation”

Read the product's source under an open licenseweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 3 (quality) × 0.6 (partial) = 5.4 of 30 max

• [claimed-docs] https://www.extend.ai/pricing“BYOC (your VPC) and Hybrid deployments”

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://docs.extend.ai/extraction/confidence-scores.md“Use them to trust high-confidence values automatically and route the rest to human review.”
• [claimed-docs] https://docs.extend.ai/extraction/response-format.md#citations“plus per-field confidence scores and citations that point back to the exact spot on the page”
• [claimed-docs] https://www.extend.ai/pricing“Agentic OCR”
• [claimed-docs] https://www.extend.ai“Parse, extract, and split your hardest documents with unmatched accuracy. Ship reliable document agents in minutes, not months.”
• [claimed-docs] https://docs.extend.ai/extraction/confidence-scores“Confidence Scores | Extend Documentation”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://www.extend.ai/pricing“Workflows”
• [claimed-docs] https://docs.extend.ai/webhooks/configuration“Webhook Configuration | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/general/async-processing“Async Processing | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/general/async-processing.md#sync-vs-async“Every processing endpoint in Extend (extract, classify, split, parse, and edit) supports both a synchronous and asynchronous mode.”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

• [claimed-docs] https://www.extend.ai/pricing“Composer & Review Agent”
• [claimed-docs] https://www.extend.ai/pricing“Agentic OCR”
• [claimed-docs] https://www.extend.ai/pricing“Agent form filling”
• [claimed-docs] https://docs.extend.ai/agent-quickstart“Agent Quickstart | Extend Documentation”
• [claimed-docs] https://www.extend.ai“Ship reliable document agents in minutes, not months.”

Operate the product with natural-language commandsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://docs.extend.ai/mcp“Using Extend via MCP | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/agent-quickstart“Agent Quickstart | Extend Documentation”
• [probe] https://docs.extend.ai/mcp“official MCP server documented at https://docs.extend.ai/mcp”
• [probe] https://docs.extend.ai/cli“official CLI documented at https://docs.extend.ai/cli”
• [claimed-docs] https://docs.extend.ai/cli“CLI | Extend Documentation”

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://docs.extend.ai/extraction/multifile.md#citations-and-file-provenance“Multifile extraction lets you run a single extraction over a collection of files with a shared context.”
• [claimed-docs] https://docs.extend.ai/general/async-processing.md#sync-vs-async“Every processing endpoint in Extend (extract, classify, split, parse, and edit) supports both a synchronous and asynchronous mode.”
• [claimed-docs] https://docs.extend.ai/evaluation/running-evaluation-sets.md#matcher-type-extractors-only“An evaluation set run scores one processor version against every item in an evaluation set and returns aggregate metrics”
• [claimed-docs] https://docs.extend.ai/general/async-processing“Async Processing | Extend Documentation”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

• [claimed-docs] https://docs.extend.ai/webhooks/configuration“Webhook Configuration | Extend Documentation”
• [claimed-docs] https://www.extend.ai/pricing“Workflows”
• [claimed-docs] https://docs.extend.ai/general/async-processing.md#sync-vs-async“Every processing endpoint in Extend (extract, classify, split, parse, and edit) supports both a synchronous and asynchronous mode.”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [claimed-docs] https://www.extend.ai/pricing“Workflows”
• [claimed-docs] https://docs.extend.ai/webhooks/configuration“Webhook Configuration | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/general/async-processing“Async Processing | Extend Documentation”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”

Version, review, and roll back my automationsweight 1

1 (weight) × 6 (quality) × 0.6 (partial) = 3.6 of 10 max

• [claimed-docs] https://docs.extend.ai/evaluation/processors.md#versioning“the thing you version and iterate on in Extend Studio, and the unit you evaluate and optimize”
• [claimed-docs] https://docs.extend.ai/workflows/workflow-versioning.md“A workflow has one editable draft and any number of immutable deployed versions.”
• [claimed-docs] https://docs.extend.ai/evaluation/overview.md“Evaluation sets let you test the accuracy of your document processors reliably and repeatedly.”
• [claimed-docs] https://docs.extend.ai/evaluation/running-evaluation-sets.md#matcher-type-extractors-only“An evaluation set run scores one processor version against every item in an evaluation set and returns aggregate metrics”
• [claimed-docs] https://docs.extend.ai/evaluation/processors.md“you save that config once as a processor, give it a stable id, and reference it from then on”
• [claimed-docs] https://www.extend.ai/pricing“Composer & Review Agent”