Skip to main content
Preview mode lets you quickly and inexpensively test your Find All queries with a small sample of candidates before committing to a full run. It’s ideal for validating your match conditions and enrichments. When to use preview:
  • Test query structure before running on large datasets
  • Validate match conditions work as expected
  • Iterate quickly on Find All schema and descriptions

​
How Preview Works

Preview mode uses the same API endpoint as regular Find All runs, but with processor: preview. It generates approximately 10 evaluated candidates (both matched and unmatched) to give you a representative sample of results.

​
Preview vs. Full Run

FeaturePreview ModeFull Run
Processorpreviewbase, core, pro
Candidates Generated~10 evaluatedUntil match_limit matches found
Match LimitMax 10Max 1000
SpeedFast (minutes)Slower (varies by processor)
CostFlat, cheapVariable, higher
OutputsFullFull
Enrichments❌ No✅ Yes
Can Extend❌ No✅ Yes
Can Cancel❌ No✅ Yes

​
Key Characteristics

  • Fast & Cost-Effective: Much faster and cheaper than full runs
  • Sample Size: Generates ~10 evaluated candidates with no guarantee of match rate
  • Full Outputs: Candidates include full match outputs, reasoning, and citations (just like regular runs)
  • Capped Limit: match_limit is capped at 10 and interpreted as candidates to evaluate, not matches to find
  • No Modifications: Cannot be extended or cancelled after creation
Preview candidates follow the same structure as full run candidates. See Candidates for details on candidate object structure and fields.

​
Quick Example

curl -X POST "https://api.parallel.ai/v1beta/findall/runs" \
  -H "x-api-key: $PARALLEL_API_KEY" \
  -H "parallel-beta: findall-2025-09-15" \
  -H "Content-Type: application/json" \
  -d '{
    "objective": "Find all portfolio companies of Khosla Ventures founded after 2020",
    "entity_type": "companies",
    "match_conditions": [
      {
        "name": "khosla_ventures_portfolio_check",
        "description": "Company must be a portfolio company of Khosla Ventures."
      },
      {
        "name": "founded_after_2020_check",
        "description": "Company must have been founded after 2020."
      }
    ],
    "processor": "preview",
    "match_limit": 10
  }'

​
Best Practices

  1. Always Preview First: Run preview to validate match conditions before committing to full searches
  2. Review Both Results: Check matched and unmatched candidates to refine your query logic
  3. Test Enrichments Early: Validate enrichment outputs in preview before running at scale
  4. Examine Reasoning: Review the basis field to understand how matches were determined
  5. Iterate Quickly: Use preview’s fast feedback loop to refine queries before full runs