Evidence · first-party tested

Retains logo imagery through a structured reference and annotation, but places the visual out of document context instead of inline in the reading flow.

◐ Mixed🧾 artifact-verifiedTested Jun 20, 2026Extend AI →

Output — unretouched

Parsed logo figure metadata.

The observation

Retains logo imagery through a structured reference and annotation, but places the visual out of document context instead of inline in the reading flow.

Criterion: Visual Content Retention · Scenario: Target 2015 Annual Report (group: financial-report)

Query this

get_evidence({
  tool: "extend-ai",
  scenario: "financial-report"
})

MCP · mcp.aidemos.com/api/mcp
Free with attribution.

Same input, other tools

Adobe PDF Extract API ✗ Failed Landing AI ✗ Failed Llamaparse ✗ Failed Mistral AI ✓ Worked Nutrient.io ✗ Failed Tensorlake ✓ Worked Upstage AI ✗ Failed

Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com