Learn

How the Meta Ads Algorithm Works (and What to Do About It)

The three steps Meta runs on every ad, in plain language: how GEM and Andromeda read, shortlist, and rank your creative, and the moves that help you win.

KO

Kole Ogundipe

·

The video above walks through the whole system in nine minutes. This page is the study-guide version: the three steps Meta runs on every ad, what each step reads, and the practical move that follows from each one.

How does the Meta ads algorithm work? Meta's ad system runs three steps. A foundation model called GEM reads and summarises every ad, the Andromeda retrieval engine narrows tens of millions of candidates to a few thousand for each person, then GEM ranks that shortlist in detail before the auction picks the final winner.

Step 1: GEM reads everything you upload

Before your ad is shown to anyone, Meta's generative ads model (GEM) reads it in full: the copy, the visuals, the audio, the video. It works out what the ad is and who it suits, then stores a summary. There is no targeting form for this part. The creative itself is the input.

The practical consequence: everything in the ad is a signal you are sending, whether you meant to send it or not. A cluttered visual, a generic hook, or a mismatched voiceover all shape who the system thinks the ad is for.

Step 2: Andromeda makes the first cut

Meta's Andromeda retrieval engine scans those summaries every time someone opens the app and cuts tens of millions of ads down to a few thousand candidates for that person.

Here is the part most accounts miss: Andromeda groups ads it reads as functionally the same, so twenty near-identical variations compete as one. We cover the mechanics in Meta's hidden Entity ID problem. If your ads are all variations of one idea, you enter this stage with one ticket, not twenty.

Step 3: the detailed ranking, then the auction

GEM reads the shortlist closely and ranks each candidate on six dimensions, a framework known as POSTER:

  • Persona: who the ad is for.
  • Offer: what moves that person to act.
  • Surface: the format and placement it suits.
  • Type: product shot, testimonial, demo, founder story, UGC.
  • Emotion: the feeling it reaches for, from more than 150 themes Meta tracks.
  • Readiness: how aware the viewer already is of your brand and category.

The survivors go to Meta's ad auction, where the winner is the combination of your bid, how likely the person is to act, and how likely they are to genuinely enjoy the ad. A strong creative match regularly beats a higher bid.

What the system rewards: range, not volume

Each step favours accounts whose ads are genuinely different from each other. Different personas, different emotions, and different formats give Andromeda more distinct candidates to retrieve and GEM more profiles to match. Small tweaks to one concept do not create that range. This is why creative diversity is the working lever, and we keep a full guide on how to measure and improve creative diversity.

See what Meta reads in your ads

Meta never shows you this scorecard. Ads Manager will not tell you that one ad was read as humour for busy parents and another as nostalgia for athletes. Wilow rebuilds the picture from the outside: AI Creative Tagging labels every ad in your account the way the system reads it, and the Creative Leaderboard ranks what is actually winning. Start free, no credit card required, and see the profile the algorithm has built for your account.

Want the full theory? Read the complete deep-dive on The Keyword: how the Meta algorithm decides which ads you see.

KO

Kole Ogundipe

Founder, Wilow

Kole builds Wilow, creative analytics for Meta advertisers. He writes about creative diversity, the Andromeda era, and getting more from every pound of ad spend.