SeekUp.ai

Context

An AI agent pipeline for influencer discovery. You give it a reference TikTok profile that already performs for your brand; four chained agents then analyse that creator's videos, comments and tone of voice, search for lookalikes, score every candidate on four axes, and return an exportable outreach report. Currently in public beta.

The product

What it sells

Lookalike influencer discovery: campaign-ready creator shortlists with a match score and a written explanation for each candidate.

Who buys it

Brands and marketing teams running TikTok creator campaigns who need to scale beyond the handful of influencers they already know.

Pricing

Beta access at €49.99/month instead of €99.99 — a 50% launch discount, cancellable at any time.

The wedge

Competitors match on follower count, language and broad topic. SeekUp matches on communication style, audience type and comment sentiment — who they are versus how they actually communicate.

The problem

Finding creators who genuinely fit a brand is a manual research job: watching hundreds of videos, reading thousands of comments, judging tone. It takes days per campaign, so teams default to the few influencers they already know, and the ones they do find are picked on follower counts — a metric that says nothing about whether the audience will respond to that brand.

Architecture

Technical specification

Agent pipeline

Four stages — profile analysis → discovery → matching → report — each independently observable and retryable.

Matching signals

Topic relevance, comment analysis, content style and performance metrics, combined into a single match rate shown per candidate.

Analysis depth

Video content, tone of voice and comment sentiment, not follower counts alone — a qualitative match rather than a numerical one.

Throughput

Hundreds of profile analyses per second across the discovery stage; a search that would take a human days completes in minutes.

Cost control

Cheap filters run first and expensive multimodal analysis last, keeping per-search inference cost bounded under a flat subscription.

Output

Exportable creator shortlist with per-candidate match score and written justification, ready for direct outreach.

Coverage

TikTok at launch, with Instagram and YouTube agents in development.

Status

Public beta — fully functional, shipping frequent interface updates.

How I built it

1. 1

   Modelled the product as four chained agents — deep profile analysis, smart discovery, intelligent matching, report generation — because each stage has a different cost profile and a different failure mode.

2. 2

   Made the first agent analyse the reference creator properly: not just statistics, but video content, interactions and comment threads, so the downstream search knows what it is actually looking for.

3. 3

   Used the reference profile as the query for discovery, surfacing both large and small creators rather than only the ones already ranked highly by follower count.

4. 4

   Scored every candidate on four explicit axes — topic relevance, comment analysis, content style and performance metrics — so the match is inspectable rather than a single opaque number.

5. 5

   Put a filtering pass before the expensive comparison stage, so deep analysis only runs on candidates that already cleared the cheap checks.

6. 6

   Made the output a downloadable report with a written rationale per creator, because a marketing team has to justify the spend to someone else.

Outcome

• Turned a multi-day manual research task into a search that returns a scored shortlist in minutes.
• Made the match explainable: every candidate carries four sub-scores and a written rationale, which is what lets a marketing team act on it.
• The staged-funnel design keeps inference cost per search predictable, which is what makes a flat €49.99/month price viable.
• Launched into public beta with a paid tier from day one, rather than a free pilot with no pricing signal.