Product

Pricing

Use Cases

Build

Pricing

Partnership

Select Language

Try on Playground

Run workflow pilot

for brands

Find creators your team
would actually approve.

Reduce manual creator vetting before outreach. CrowdCore searches by structured brand requirements, then checks videos, profiles, captions, comments, campaign fit, audience fit, brand safety, comment quality, and content format.

Run workflow pilot

Search by buyer and campaign fit

Describe the customer, product, market, platform, geography, follower range, engagement level, tone, content style, and format you need.

Vet before your team wastes time

Filter out creators whose videos, comments, audience reactions, brand-safety signals, or buyer fit do not match the brief.

Turn evidence into a brief

Get creator-specific hooks, product angles, script notes, collaboration ideas, risk flags, and outreach priority.

Use Cases

This is for brands now.

Search by product and buyer

Search by audience and platform

Search by comments and sentiment

Find proven creator formats

Search by product and buyer

Search by audience and platform

Search by comments and sentiment

Find proven creator formats

Apply brand-safety requirements

Review real creator videos

Move beyond static tags

Get evidence for every match

Analyze content safety & suitability

Apply brand-safety requirements

Review real creator videos

Move beyond static tags

Get evidence for every match

Analyze content safety & suitability

Generate campaign briefs

Match creator style to product

Find authentic brand fit

Rank creators by approval fit

Generate campaign briefs

Match creator style to product

Find authentic brand fit

Rank creators by approval fit

Our Value

Structured search. AI-native vetting.

Use database-style creator filters, public discovery, private creator pools, and structured API outputs from one system. Crowdcore narrows the candidate set first, then applies campaign brief, audience, content-fit, comment, and risk criteria.

Structured filters meet content fit.

Traditional databases satisfy profile filters; trend tools explain content. Crowdcore combines structured creator search with AI-native vetting of videos, captions, comments, audience signals, risk, and content style.

Find more, then vet consistently.

Search broadly across profile data and creator pools, then vet videos, comments, audience reactions, risks, and format match before your team reviews candidates.

Audience and product fit.

Understand who follows each creator, what they care about, and whether that audience matches your buyer.

Private pool intelligence.

Make CRM lists, rosters, saved creators, and past collaborators searchable by video, notes, comments, performance, and fit criteria.

Structured filters meet content fit.

Find more, then vet consistently.

Search broadly across profile data and creator pools, then vet videos, comments, audience reactions, risks, and format match before your team reviews candidates.

Audience and product fit.

Understand who follows each creator, what they care about, and whether that audience matches your buyer.

Private pool intelligence.

Make CRM lists, rosters, saved creators, and past collaborators searchable by video, notes, comments, performance, and fit criteria.

Audience and product fit.

Understand who follows each creator, what they care about, and whether that audience matches your buyer.

Private pool intelligence.

Make CRM lists, rosters, saved creators, and past collaborators searchable by video, notes, comments, performance, and fit criteria.

Python

Node

from twelvelabs import Crowdcore
import os

client = Crowdcore("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)

Python

Node

from twelvelabs import Crowdcore
import os

client = Crowdcore("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)

Python

Node

from twelvelabs import Crowdcore
import os

client = Crowdcore("<YOUR_API_KEY>")

# Create new Index
index = client.index.create(        
     name="My First Index",
     engines=[
       {                
         "name": "marengo2.7",
         "options": ["visual", "audio"],
       },
     ],
  )
# Create new Task on Index (Upload the video)
video_path = os.path.join(os.path.dirname(__file__), "<YOUR_FILE_PATH>")
task = client.task.create(index_id=index.id, file=video_path, language="en")

# Wait for indexing to finish
task.wait_for_done()

# Search from your index
query = "An artist climbing up the ladder that he painted."
result = client.search.query(index.id, query, ["visual", "audio"])
‍print(result)

Integrate creator search, vetting, shortlists, and brief inputs into your agents, CRM, and internal workflows.

Call Step 1 structured discovery, private pool search, Step 2 AI-native vetting, fit scoring, and brief generation as structured outputs for your app or AI agent.

Get the SDK