Automatic Influencer Research
AI influencer research across Instagram, TikTok, YouTube, LinkedIn, X and the open web. Ranks creators, finds contact routes, exports CSV, JSON and a campaign brief.
Created by Emil Hjorth • Version 103 • 67 steps
What you get
- AI influencer research across Instagram, TikTok, YouTube, LinkedIn, X and the open web. Ranks creators, finds contact routes, exports CSV, JSON and a campaign brief.
Use cases
- SaaS and AI tool teams looking for launch creators and early advocates
- Agencies building influencer, UGC, or creator partnership campaigns for clients
- Ecommerce and DTC brands researching creators for product videos or social campaigns
- Founders who want a repeatable creator discovery process before cold outreach
- Growth teams that need cleaner influencer research data to feed downstream outreach workflows
- B2B marketing teams running thought-leader or executive-influencer campaigns on LinkedIn and X
Integrations
- apify
- openai
- outreach-lead-files
- Find Influencers
How it works
- Import demo video as same-flow publish media
- Coerce string form-inputs to numbers
- Start company-website crawl
- Fetch + persist crawl dataset
- Extract + truncate crawl text
- Build company-brief LLM prompt
- Generate company brief
- Parse + validate brief JSON
- Persist company brief blob
- Detect whether user supplied keywords
- Build keyword-inference LLM prompt
- Auto-infer keywords from campaign goal + company brief
- Parse inferred keywords JSON
- Resolve final keywords (user > inferred)
- Prepare per-platform Apify actor inputs
- Serialize IG actor input to JSON for helper
- Coerce helper output to inline-shape
- Normalize YouTube dataset
- Normalize TikTok dataset
- Normalize LinkedIn dataset
- Normalize X dataset
- Normalize web search dataset
- Coerce filter inputs to numbers
- Gather + tag candidates (filter follower range + engagement, extract emails)
- Split candidates into LLM-safe batches
- Build LLM filter prompt (batch 1)
- Build LLM filter prompt (batch 2)
- Build LLM filter prompt (batch 3)
- Build LLM filter prompt (batch 4)
- Build LLM filter prompt (batch 5)
- Persist LLM batch inputs
- Filter candidates with OpenAI (batch 1)
- Filter candidates with OpenAI (batch 2)
- Filter candidates with OpenAI (batch 3)
- Filter candidates with OpenAI (batch 4)
- Filter candidates with OpenAI (batch 5)
- Merge LLM decisions onto candidates
- Compute final run status
- Prepare candidate rows for table upsert
- Upsert candidates table
- Prepare outreach-ready lead rows
- Upsert outreach-ready leads table
- Prepare human-readable lead review rows
- Persist human-readable lead review table
- Build markdown report
- Persist markdown report blob
- Build JSON and CSV lead exports
- Persist outreach leads JSON export
- Persist outreach leads CSV export
- Prepare run row
- Upsert runs table
Find influencers for any niche, ranked across every platform
Automatic Influencer Research is an AI-powered creator discovery workflow for marketing teams, founders, agencies, and creator partnership teams that need a faster way to find relevant influencers across every major platform.
Start with a company name, campaign goal, optional company URL, keywords, and discovery depth. The flow searches Instagram, YouTube, TikTok, LinkedIn, X, and the open web, then ranks and filters creator candidates into an outreach-ready report you can hand straight to your outbound team or paste into HubSpot, Salesforce, Pipedrive, or any CRM.
How does this AI influencer research workflow work?
You give the flow a brand, a campaign brief, and the social channels you care about. From there it does the heavy lifting:
- Searches Instagram, TikTok, YouTube, LinkedIn, X, and Google for creators that match your campaign
- Optionally crawls your company website to learn the brand voice and category before searching
- Infers search keywords automatically when you write
autoinstead of a manual keyword list - Filters candidates by follower range and recent engagement where platform data is available
- Uses GPT-class AI review to classify each candidate as keep, review, or reject with reasoning
- Produces a ranked creator lead table, contact routes, CSV/JSON exports, and a markdown campaign brief
It runs end-to-end in a single flow. No spreadsheet juggling, no manual social scraping, no separate enrichment passes.
Who is the influencer research workflow for?
- SaaS and AI tool teams looking for launch creators and early advocates
- Agencies building influencer, UGC, or creator partnership campaigns for clients
- Ecommerce and DTC brands researching creators for product videos or social campaigns
- Founders who want a repeatable creator discovery process before cold outreach
- Growth teams that need cleaner influencer research data to feed downstream outreach workflows
- B2B marketing teams running thought-leader or executive-influencer campaigns on LinkedIn and X
What inputs does the flow need?
You only need three required inputs to run a search:
- Company name (the brand running the campaign)
- Campaign goal (what kind of creators are you looking for, and why)
- Discovery depth (Quick, Balanced, or Deep)
Optional inputs that improve results:
- Company URL: when provided, the flow crawls the site and feeds brand context into ranking
- Keywords: write a comma-separated list, or write
autoto let AI infer them from your campaign goal - Follower filters: minimum and maximum follower counts to separate micro from mid-tier creators
- Engagement filter: minimum recent likes for Instagram, TikTok, and YouTube candidates
What do you get back from each run?
Each completed run returns a full outreach-ready bundle:
- Ranked influencer and creator candidates with relevance score and reasoning
- Social profile links and contact channels (email when discoverable, otherwise DM route)
- Route-mix summary so you can see how many leads need email vs DM vs enrichment vs manual review
- CSV and JSON exports designed for HubSpot, Salesforce, Pipedrive, Clay, Instantly, or any CRM and outreach tool
- A markdown research report with candidate notes, next actions, and campaign-fit commentary
The data is structured for the sibling Automatic Influencer Outreach flow if you want to send the first-touch messages directly from Breyta.
How much does the influencer research workflow cost?
One-time payment for a prepaid run pack. No monthly subscription, no per-seat fees, no annual contract. Pick the pack size that matches your campaign volume:
- Free trial – 1 run, no credit card required
- Starter – $19 for 25 runs ($0.76 per run, recommended starting point)
- Growth – $49 for 75 runs ($0.65 per run)
- Agency – $129 for 250 runs ($0.52 per run)
Try the workflow with a free run first. No card, no commitment. Install, run once, get a full creator research report, then pick a pack if you want to run more campaigns.
Packs do not expire. Only successful completed runs consume the allowance. Failed, cancelled, or timed-out runs do not count. Discovery depth (Quick, Balanced, Deep) controls how many candidates a single run targets and does not affect the per-run price.
For context: most influencer research SaaS tools (Modash, HypeAuditor, CreatorIQ, Klear) start at $199–$499 per month and lock features behind annual contracts. Automatic Influencer Research is pay-as-you-go, so a full Growth pack costs less than a single SaaS month and the runs do not expire when the month ends.
Does the app work without giving it my website?
Yes. The Company URL field is optional. If you skip it, the flow ranks creators purely on your campaign goal and keywords. Adding a website usually improves ranking quality because the LLM can match creators to your actual brand voice and category instead of a one-line brief.
Which social platforms does the app search?
Every run searches all of these in parallel:
- Instagram (creator handles, follower counts, engagement, bio contact routes)
- TikTok (handles, follower counts, recent engagement)
- YouTube (channels, subscriber counts, niche fit)
- LinkedIn (B2B creators, thought leaders, executive influencers)
- X / Twitter (creators, public posts, public bio contact info)
- Open web search (newsletters, blogs, podcasts, creator websites not on the big social platforms)
LinkedIn and open-web candidates always pass the follower filter because follower counts on those surfaces are noisy or unavailable.
How does the AI ranking work?
After candidates are pulled from each platform, the flow batches them into LLM-safe groups and asks GPT-class models to classify each candidate as keep, review, or reject with a short reason and a relevance score. The classifier uses your campaign goal, optional website context, and the candidate's bio, post history, and engagement signals. Only keep candidates land in the outreach-ready exports. review candidates are kept in the full report so you can override the AI manually when you want a closer look.
What formats can I export the data in?
Every completed run produces:
- A CSV ready to upload into HubSpot, Salesforce, Pipedrive, Clay, Instantly, Lemlist, Smartlead, or any modern outreach tool
- A JSON file with the full schema, ready for engineering teams to script against
- A markdown research report you can paste into Notion, Linear, ClickUp, or a Google Doc
Files are saved to a private blob storage folder you choose at install time.
Setup and permissions
Apify and OpenAI are provided by the flow author, so you do not need to bring API keys or pay separate vendor invoices. Installers only need to enter the campaign inputs and configure where outreach lead files should be saved.
Limits and failure cases
Influencer discovery depends on what each platform makes publicly available. Some social platforms will rate-limit, hide profile details, or return incomplete contact information depending on the day. Private profiles, blocked pages, and profiles without clear contact routes may require manual review or a separate enrichment workflow.
If a platform returns zero candidates for your keywords on a given run, the flow continues with the remaining platforms instead of failing the whole job.
Sibling flows in the same suite
Automatic Influencer Research is one part of a complete outbound stack:
- Creator Partnership Outreach drafts and sends first-touch messages to the creators this flow finds. Email, LinkedIn, Instagram, all approved by you first.
- Contact Enrichment finds emails and contact routes for any list of people or companies. Use it on the leads from this flow, or on any other prospecting list you already have.
You can install one, two, or all three. Same Breyta workspace, same pay-per-pack model, no monthly subscription.
FAQ
What does the Automatic Influencer Research app do?
This app automates the process of finding and vetting influencers across Instagram, TikTok, YouTube, LinkedIn, X, and the open web. It crawls your website to understand your brand, identifies relevant creators, and filters them based on engagement metrics and campaign fit.
How does the AI rank and filter potential influencers?
The app uses Apify to scrape real-time data from social platforms and OpenAI to analyse creator content. It automatically finds contact details and ranks influencers based on how well they match your specific campaign goals.
What information do I need to provide to start a search?
You only need to provide your company website and your campaign goals. If you have specific keywords in mind, you can enter them, but the AI is capable of inferring the best search terms by scanning your brand's online presence.
Which third-party services does this workflow connect to?
The workflow integrates directly with Apify for social media data extraction and OpenAI for intelligent lead scoring. Once the research is complete, you can export your curated lists as CSV or JSON files for your outreach tools.
Can I customise the search for specific niche markets or creator sizes?
Yes, you can set specific follower ranges and engagement thresholds to ensure the results match your budget and strategy. The app processes these filters before the AI finalises the selection, so you only pay for high-quality leads.