Product

Pricing

Use Cases

Build

Pricing

Partnership

Select Language

Start search

Talk to Sales

creator research

Creator discovery that doesn’t trade depth
for scale.

CrowdCore uses coordinated AI agents to search broad creator pools, inspect videos and comments, identify proven content formats, evaluate audience signals, and reuse past campaign learnings before your team starts outreach.

Talk to Sales

Search beyond the obvious

CrowdCore explores public discovery, private pools, competitors, content styles, formats, and saved lists instead of stopping at keyword matches and trending creators.

Vet with content-level evidence

Agents inspect videos, captions, comments, audience reactions, engagement quality, risks, and buyer signals before a creator reaches your shortlist.

Build campaign mixes, not guesses

CrowdCore groups creators by proven format, campaign role, backup coverage, and risk so the channel does not depend on one perfect pick.

Use Cases

Vetting deep enough to replace hours of manual checking.

Content layer

Videos and captions

Hooks and story arcs

Proven formats

Content layer

Videos and captions

Hooks and story arcs

Proven formats

Audience layer

Comment quality

Buyer questions

Trust signals

Engagement quality

Audience layer

Comment quality

Buyer questions

Trust signals

Engagement quality

Campaign layer

Brand risk

Format match

Campaign role

Backup coverage

Campaign layer

Brand risk

Format match

Campaign role

Backup coverage

WHY IT COMPOUNDS

Not one AI assistant. A creator research team that compounds.

Single-agent tools crawl through creators one by one. CrowdCore coordinates specialized agents for discovery, content vetting, comment signals, proven formats, risk, portfolio planning, and memory, so every search can reuse what previous searches already learned.

Parallel search

Cover more creators and signals at once.

Specialized vetting

Separate agents inspect content, comments, risks, formats, and fit.

Shared memory

Rejected, saved, risky, and high-signal creators inform future searches.

Less repeated waste

Your team stops paying the same manual review cost every campaign.

Parallel search

Cover more creators and signals at once.

Specialized vetting

Separate agents inspect content, comments, risks, formats, and fit.

Shared memory

Rejected, saved, risky, and high-signal creators inform future searches.

Less repeated waste

Your team stops paying the same manual review cost every campaign.

Shared memory

Rejected, saved, risky, and high-signal creators inform future searches.

Less repeated waste

Your team stops paying the same manual review cost every campaign.

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)

Your creator search gets smarter every time your team uses it.

CrowdCore agents can reuse past searches, rejected creators, saved lists, notes, risks, and format learnings so future campaigns start with more context.

See how it works

Try creator search.
Pay for deeper vetting and shortlist output.

Choose the mix of public creator discovery, content-grounded vetting, private pool indexing, shortlist reports, seats, and API volume your team needs.