Give the agent the operational context
State the product, program, target creator, platform, region, evidence requirements, and exclusions.
Application operations
Review creator applications without rebuilding the same spreadsheet workflow.
Upload creator application exports or MP4 samples, define the program criteria, and ask UGC Agent to score, rank, flag risks, update statuses, and convert accepted applicants into saved leads.
CSV application importOptional account and video analysisAccept, reject, shortlist, and convert
Workflow
From request to usable output.
Inspect the structured output
Review sources, score reasons, classifications, risk flags, and any missing evidence before acting.
Keep the human decision
Use automation for the first pass while your team controls outreach, approvals, commercial terms, and publishing.
01
Normalize messy application data
The importer recognizes common fields for name, email, Instagram, TikTok, location, niche, followers, rate, availability, portfolio links, and sample videos. Stable application IDs help update repeated imports instead of creating silent duplicates.
02
Score what the applicant actually supplied
The baseline application rubric checks contact details, social profiles, portfolio or video evidence, UGC language, availability, location, follower context, and optional program criteria. Missing evidence becomes a risk flag rather than a fabricated assumption.
03
Add account or sample analysis when useful
Optional public-account analysis reviews recent posts, median and maximum views, likes, engagement, cadence, hooks, and breakout patterns. Uploaded MP4 analysis can assess the opening, pacing, on-screen text, strengths, risks, and suggested edits.
04
Keep a human approval step
Recommendations such as strong accept, shortlist, review, or reject are triage aids. A human should review samples, product fit, compensation, rights, availability, brand safety, and any sensitive category requirements before deciding.
05
Design the application for review
Ask only for fields that change a legitimate campaign decision: contact route, public profiles, location when relevant, niche, availability, rate context, portfolio, product access, and appropriate work samples. Explain how submissions will be reviewed and avoid collecting sensitive information before it is needed.
Use existing portfolio work where possible. If the program requires a custom test, define compensation and permitted use in advance; an unpaid application sample should not become brand content without a separate agreement.
06
Keep recommendations reproducible
Each recommendation should retain the supplied fields, evidence links, scoring reasons, missing information, risk flags, review date, and final status. Strong accept, shortlist, review, and reject are queue states, not predictions of campaign performance.
When a reviewer overrides the recommendation, record the campaign reason. That improves consistency across a large applicant pool without removing judgment from the process.
07
Move accepted applicants into operations
Accepted applicants can become saved leads with their contact and profile context, then move into lists, tags, outreach stages, briefs, and contract workflows. Private application fields should remain separate from the public creator record and be shared only with people who need them.
Before hiring, confirm availability, compensation, deliverables, revisions, product shipping, usage rights, exclusivity, disclosure, approval, and payment. Application scoring does not replace that commercial agreement.
Keep rejection and shortlist communication concise and respectful. Do not expose internal risk flags, other applicants' information, or automated reasoning that a human has not reviewed. When a missing field is the only blocker, ask for clarification instead of presenting uncertainty as a final judgment about the creator.
After the program closes, retain only the application and creator data needed for legitimate operational, contractual, or legal purposes. The eventual privacy notice and program terms should explain retention, access, deletion, and service-provider handling before the workflow is used at scale.
Export only the fields the downstream reviewer needs and restrict access to the active campaign team.
Questions
What teams usually need to know.
Is this feature available in the web app?
Yes. Availability and usage limits depend on the active UGC Agent plan.
Does UGC Agent make the final creator decision?
No. It provides structured evidence and a first-pass recommendation for human review.
Does the feature use private social data?
The sourcing workflow uses public creator profile and content signals supplied by configured data providers.
Can I export the result?
Creator leads and unlocked analysis fields can be exported where the workflow supports CSV export.
Can the same workflow run through MCP?
Premium MCP access exposes the supported server-side tools to compatible LLM clients.
Turn the brief into a creator list.
Try a restricted sourcing run free, then upgrade only when you need more visible or monthly creator leads.