Framer AI AgentsDesign and publish professional sites with AI
Badge gives an AI agent that collects peer reviews to build proof of work. For job seekers - The agent connects to your contacts, requests anonymous reviews from your past colleagues, and builds a verified, portable trust score. score. For hiring managers - Badge gives you a 30 second reference checks on candidates, collecting authentic feedback from their actual coworkers to replace unreliable, AI-generated resumes and LinkedIn Recommendations.
The hard part here is making the proof portable without turning it into another opaque score. Peer context, recency, and the option to inspect what evidence produced the badge would matter a lot for trust, especially as AI makes resumes easier to polish.
Badge
@krekeltronics absolutely, we did consider that. It all boils down to how the trust score is calculated.
Your Trust Score is built from verified peer reviews across key dimensions like: quality of work, reliability, professionalism, communication, and how you handle pressure.
What affects it:
Volume : more reviews = more accurate score
Recency : recent reviews carry more weight
Reviewer credibility : reviewers with stronger Badge history carry more weight
Consistency : patterns across multiple reviews are weighted heavily
Continuous peer review as proof-of-work is a clever inversion of the reference letter. What stops it drifting into LinkedIn-endorsement inflation where everyone five-stars each other? Genuinely curious how the incentive design handles that.
Badge
@chielephant Thats a wonderful point. Incentive design does not handle this but anonymity of reviews handles this. For linkedin and uber reviews. The feedback giver does not want to be in bad relation with the reviewee because it is public. When we make all reviews anonymous then there is no politeness and people can be honest and thats why we feel, it should not drift to 5 star clusters.
Really like this idea. Curious how you're handling cases where peer
reviews conflict with each other, or where someone gives an overly
generous review just to be nice — does the agent weigh reviews
differently based on any signals, or is it more straightforward
aggregation?
Badge
@amjad_shaik Amjad the agent does not weigh reviews, It collects them but we believe that over time some traits about professionals will show up. Like hard work, smartness etc.
@lokesh_motwani1 That makes sense — letting patterns emerge naturally over volume
rather than trying to weight individual reviews. Does the aggregation
window matter much, like does someone need X number of reviews before
those traits become reliable signal, or does it start showing
directionally pretty early?
Badge
@amjad_shaik For now we have not thought about this because its is too early and users do not have a lot of reviews. But some patterns will emerge
@lokesh_motwani1 Makes sense — early days, let the data build up before optimizing for
it. Will be curious to see what patterns actually surface once volume
kicks in. Congrats on the strong launch, saw Badge hit #1!
Badge
@lakshminath_dondeti We are thinking this in the lines of credit score for professionals. Weightage can be calculated based on the network distance, trustcore of reviewer, sentiment quality of review. AI has enabled this use case.
Such a solid concept. Traditional reference checks are so broken, and LinkedIn recommendations are usually just traded favors. Building a verified, portable 'Trust Score' makes total sense, especially when pivoting between massive orgs and indie projects. How do you guys handle the verification for freelancers or agency folks who might not have standard corporate email addresses for their reviewers? Really impressive product, upvoted!
Badge
@zachary_f The reviews can be given using the linkedin profile of the said freelancer by the client. We are planning to partner up with freelancing platform in order to increase the credibility.
How does the agent actually get people to leave reviews if I haven't talked to old coworkers in years?
Badge
@cafertrf7 great question!
Two things make this work.
Firstly , it becomes a two way culture. When you review a colleague, you're also building your own reputation on Badge. The more people participate, the more everyone benefits. Your colleagues who review you today will want reviews from their own network tomorrow. It's a reciprocal ecosystem where giving is just as valuable as receiving.
Secondly, Badge is designed to be low effort. You're not asked to sit down and write a long thoughtful, structured paragraph about someone. Instead you have a simple conversational exchange with Badge's AI agent.
Does that help?
Badge
@cafertrf7 Great question, the agent nudges the user to give reviews and the order in which it decides for whom to ask review for is important. So if the agent is asking your contact to give reviews, first it will ask it to give the review for you.
How does the agent actually get coworkers to respond - do they need to install something too, or is it just an email link?
Badge
@adem1398592 Yes, the agent works through Badge, so you have to be on Badge to give and recieve reviews! Did any of your coworkers review you yet?
Badge
@adem1398592 The agent will go to the coworker and say - Build your trustscore to get the best opportunities. and the only way tto build the trustscore is to get review and give reviews. Then the agent asks the user to give one review so that it can collect reviews from him. We follow give to get reviews.
Badge
@adem1398592 Yes, Now by doing so, their Trust score is also available in an instant, and they can get started building their trust score from that very instant.