Second Eyes helps you sort photos, understand the shortlist, and make the final call. For business briefs or personal needs, see why each photo was shortlisted and what still needs checking. You decide what to publish. Explore a real media editorial project involving 404 source files, then try six public sample photos to see how your requirements reshape the shortlist. This demo uses a recorded review. No uploads yet. Would you use this with your own photos? Share your workflow in the comments.
Hi Product Hunt — I built Second Eyes because the hard part of a large photo archive is rarely storage. It’s deciding which few images are worth a human’s final attention.
For this run, we gave GPT-6 Astra a publishing brief and a 404-file source corpus. Astra reviewed the assets it could access, reported 3 HEIC files it could not decode, selected 12 editorial references for IG and Reels, documented its reasons, and turned the result into two human-ready review workrooms.
What interested me most was that the output wasn’t just a list of filenames. Astra completed the whole workflow: inspect, narrow, explain, report failures, and hand the work back to a human.
Second Eyes is deliberately built around one principle: the model can make judgments, but it should never have to pretend it saw something it didn’t.
I’d love to hear how others would use this: creative archives, publishing, photography, brand teams, or something completely different.
Really interesting approach! Love how it combines AI automation with human judgment.
Being part of the Second Eyes team, I found the sample really interesting. What stood out to me is that changing the brief actually changes what deserves attention, while the interface makes the reasoning and gaps visible.
It feels less like “AI chooses for you” and more like “AI helps you get the evidence into shape so you can make the call.”
This looks really interesting, The idea of using AI to help shortlist photos while explaining why each one was selected could save a lot of time. Excited to see how Second Eyes works in real-world workflows.
Question for the room: what would you point Second Eyes at first — wedding archives, product shots, or social content? We started with a 400-photo IG/Reels edit, curious where else this breaks or shines.
About Second Eyes on Product Hunt
“Automatically shortlist photos for faster publishing”
Second Eyes launched on Product Hunt on September 18th, 2026 and earned 65 upvotes and 11 comments, placing #36 on the daily leaderboard. Second Eyes helps you sort photos, understand the shortlist, and make the final call. For business briefs or personal needs, see why each photo was shortlisted and what still needs checking. You decide what to publish. Explore a real media editorial project involving 404 source files, then try six public sample photos to see how your requirements reshape the shortlist. This demo uses a recorded review. No uploads yet. Would you use this with your own photos? Share your workflow in the comments.
Second Eyes was featured in Productivity (661.2k followers), Photography (143.4k followers), GitHub (41.4k followers), Data & Analytics (5.9k followers) and OpenAI Day (39 followers) on Product Hunt. Together, these topics include over 209.8k products, making this a competitive space to launch in.
Who hunted Second Eyes ?
Second Eyes was hunted by Crystal Chang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Second Eyes stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Crystal Chang