Give the agent the operational context
State the product, program, target creator, platform, region, evidence requirements, and exclusions.
Transparent screening
Score creator fit with reasons your team can inspect.
UGC Agent turns profile evidence into an explainable first-pass score. The score helps prioritize manual review; it does not predict creative performance, campaign results, or whether someone will accept a project.
Explainable scoring reasonsFollower and language guardrailsCampaign-specific relevance
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
What the baseline score measures
The baseline rubric awards signals for UGC language in the username, display name, or bio; public contact information; portfolio language; known portfolio-link hosts; and structured niche descriptions. Each retained lead carries the reasons behind its score.
02
What can exclude a profile
Default micro-UGC sourcing excludes private accounts, profiles outside the configured follower range, strongly non-English bios, missing emails, low scores, and profiles that fail the campaign relevance check. Brand-collaboration mode uses a wider follower band and requires public collaboration evidence.
03
Why scoring is not a verdict
A profile can look qualified and still be wrong for a particular product, rate, timeline, or creative direction. Use the score to reduce the first-pass workload, then review content examples, brand safety, availability, compensation, and rights manually.
04
Adapt the score to the job
Saved agent preferences, one-run overrides, seed-creator analysis, niche requirements, agency-email exclusions, and brand-evidence mode change which profiles survive. The goal is consistent screening around the campaign, not a universal ranking of creators.
05
How relevance changes the baseline score
Baseline UGC signals show whether a public profile presents as a contactable creator, but campaign relevance answers a different question: does this person fit the product, buyer, region, format, and creative context in the current brief? A strong generic profile can still fail a specific relevance gate.
Seed analysis and saved preferences can add context without rewriting the scoring system into a hidden universal ranking. The result should explain which requirements were supported, missing, or contradicted.
06
Use pass, review, and reject states
A score is easiest to operate when it supports three human-readable states. Pass means the public evidence supports the configured first-pass requirements. Review means a material field is ambiguous or missing. Reject means a hard campaign constraint is clearly not met.
Operators should record overrides. If a reviewer retains a low-score profile for a demonstrated skill or rejects a high-score profile for a campaign-specific risk, the note keeps the process explainable without pretending the rubric predicted the final choice.
07
What to verify after scoring
Open recent work, confirm product and customer fit, review brand-safety requirements, and verify that the public contact route is legitimate. Then discuss availability, rates, deliverables, rights, revisions, product access, and disclosure with the creator or representative.
Do not use the score as evidence of audience authenticity, expected response, creative quality, regulatory compliance, or paid-media performance. Those decisions need different evidence and, in some cases, specialist review.
A complete screening record should include the campaign brief, source profile, review date, reasons, exclusions, missing evidence, reviewer, and final status. Keeping those fields together makes the recommendation reproducible and lets the team improve requirements without claiming that one campaign decision applies to every future search.
Review the rubric whenever product behavior, provider fields, or campaign requirements change, and date material methodology updates.
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.