Product

Pricing

Use Cases

Build

Pricing

Partnership

Select Language

Start search

Get API access

agents / api

Creator search and vetting
your agents can call.

CrowdCore gives AI agents a structured way to search creators, inspect content and comments, match proven formats, check risks, use private pools, and return shortlist-ready JSON instead of raw web results.

Get API access

Installable Skill

Give agents a ready-made creator search and vetting skill with structured inputs, evidence fields, and shortlist outputs.

Callable API

Call creator discovery, private pool search, content vetting, comment analysis, format matching, risk checks, and shortlist generation.

Workflow integration

Connect CrowdCore to CRMs, saved lists, campaign briefs, approval workflows, internal dashboards, and reporting tools.

Use Cases

This is agents / api now.

Search capabilities

Public creator discovery

Private pool search

CRM/list import

Search capabilities

Public creator discovery

Private pool search

CRM/list import

Vetting capabilities

Video and caption review

Comment signal analysis

Proven format match

Creator vetting content safety & suitability

Vetting capabilities

Video and caption review

Comment signal analysis

Proven format match

Creator vetting content safety & suitability

Structured outputs

Fit reasons

Evidence fields

Backup candidates

Structured outputs

Fit reasons

Evidence fields

Backup candidates

WHY AGENTS NEED IT

Raw search results are not enough for creator workflows.

Agents need structured creator intelligence: who fits, why they fit, what evidence supports the match, what risks to review, and which backups to use.

Search layer

Find creators across public discovery, private pools, saved lists, and workflow context.

Vetting layer

Inspect videos, captions, comments, audience signals, formats, and risks before output.

Memory layer

Use previous searches, saved creators, rejected candidates, notes, and campaign context.

Output layer

Return stable fields for agents, CRMs, dashboards, and internal tools.

Search layer

Find creators across public discovery, private pools, saved lists, and workflow context.

Vetting layer

Inspect videos, captions, comments, audience signals, formats, and risks before output.

Memory layer

Use previous searches, saved creators, rejected candidates, notes, and campaign context.

Output layer

Return stable fields for agents, CRMs, dashboards, and internal tools.

Memory layer

Use previous searches, saved creators, rejected candidates, notes, and campaign context.

Output layer

Return stable fields for agents, CRMs, dashboards, and internal tools.

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, and shortlist output into your agent workflow.

Call CrowdCore with a campaign brief and constraints, then return creators with fit reasons, content evidence, audience signals, format match, risks, campaign role, and backup candidates.

Get the SDK