![](data:image/svg+xml,<svg display="block" role="presentation" viewBox="0 0 28 28" xmlns="http://www.w3.org/2000/svg"><g d="M 0 28 L 0 0 L 28 0 L 28 28 Z M 28 0 L 0 0 L 0 28 L 28 28 Z M 10.982 25.284 C 10.587 25.541 10.153 25.669 9.699 25.669 C 8.968 25.669 8.543 25.185 8.543 24.534 C 8.543 23.664 9.343 23.2 10.992 23.013 L 10.992 22.795 C 10.992 22.509 10.775 22.351 10.38 22.351 C 9.985 22.351 9.659 22.509 9.432 22.795 L 8.74 22.4 C 9.106 21.896 9.659 21.64 10.4 21.64 C 11.417 21.64 11.99 22.084 11.99 22.795 C 11.99 22.795 11.99 25.61 11.99 25.62 L 11.081 25.62 Z M 9.54 24.464 C 9.54 24.721 9.708 24.968 10.005 24.968 C 10.331 24.968 10.637 24.83 10.953 24.553 L 10.953 23.635 C 9.995 23.763 9.54 24 9.54 24.464 Z M 12.789 21.837 L 13.638 21.719 L 13.727 22.183 C 14.211 21.837 14.587 21.649 15.07 21.649 C 15.87 21.649 16.285 22.074 16.285 22.914 L 16.285 25.63 L 15.258 25.63 L 15.258 23.091 C 15.258 22.617 15.13 22.4 14.764 22.4 C 14.458 22.4 14.152 22.538 13.806 22.835 L 13.806 25.63 L 12.789 25.63 Z M 23.079 25.699 C 21.934 25.699 21.242 24.958 21.242 23.674 C 21.242 22.38 21.934 21.64 23.06 21.64 C 24.185 21.64 24.857 22.351 24.857 23.625 C 24.857 23.694 24.847 23.763 24.847 23.822 L 22.25 23.822 C 22.26 24.563 22.566 24.929 23.168 24.929 C 23.553 24.929 23.81 24.771 24.047 24.425 L 24.798 24.84 C 24.472 25.403 23.879 25.699 23.079 25.699 Z M 23.85 23.161 C 23.85 22.637 23.553 22.331 23.069 22.331 C 22.605 22.331 22.319 22.627 22.279 23.161 Z M 3.445 25.738 C 2.428 25.738 1.52 25.096 1.52 23.684 C 1.52 22.272 2.438 21.63 3.445 21.63 C 4.463 21.63 5.371 22.272 5.371 23.684 C 5.371 25.096 4.463 25.738 3.445 25.738 Z M 3.445 22.489 C 2.685 22.489 2.537 23.18 2.537 23.674 C 2.537 24.178 2.675 24.859 3.445 24.859 C 4.216 24.859 4.354 24.168 4.354 23.674 C 4.354 23.18 4.206 22.489 3.445 22.489 Z M 6.074 21.729 L 7.052 21.729 L 7.052 22.183 C 7.24 21.936 7.694 21.64 8.129 21.64 C 8.168 21.64 8.217 21.64 8.257 21.65 L 8.257 22.608 C 8.237 22.608 8.227 22.608 8.208 22.608 C 7.763 22.608 7.269 22.677 7.121 23.022 L 7.121 25.61 L 6.074 25.61 Z M 18.794 24.79 C 19.574 24.78 19.633 23.99 19.633 23.477 C 19.633 22.864 19.337 22.37 18.784 22.37 C 18.418 22.37 18.003 22.637 18.003 23.516 C 18.013 24 18.043 24.79 18.794 24.79 Z M 20.631 21.719 L 20.631 25.412 C 20.631 26.064 20.581 27.131 18.724 27.151 C 17.954 27.151 17.253 26.845 17.105 26.183 L 18.112 26.025 C 18.152 26.212 18.27 26.41 18.843 26.41 C 19.376 26.41 19.633 26.153 19.633 25.551 L 19.633 25.096 L 19.623 25.087 C 19.465 25.373 19.208 25.649 18.616 25.649 C 17.707 25.649 16.996 25.017 16.996 23.704 C 16.996 22.4 17.737 21.669 18.566 21.669 C 19.347 21.669 19.633 22.025 19.702 22.212 L 19.692 22.212 L 19.781 21.748 L 20.631 21.748 Z M 25.254 20.425 L 24.849 20.425 L 24.849 21.541 L 24.632 21.541 L 24.632 20.425 L 24.227 20.425 L 24.227 20.257 L 25.244 20.257 L 25.244 20.425 Z M 26.933 21.541 L 26.716 21.541 L 26.716 20.464 L 26.706 20.464 L 26.281 21.541 L 26.143 21.541 L 25.718 20.464 L 25.708 20.464 L 25.708 21.541 L 25.491 21.541 L 25.491 20.257 L 25.817 20.257 L 26.202 21.235 L 26.577 20.257 L 26.903 20.257 L 26.903 21.541 Z" fill="transparent" height="28px" id="id1KPx0UG" width="28px"><path d="M 0 28 L 0 0 L 28 0 L 28 28 Z" fill="transparent" height="28px" id="EiC9KzYEc" width="28px"/><path d="M 28 0 L 0 0 L 0 28 L 28 28 Z" fill="rgb(255, 121, 0)" height="28px" id="QNibyqj7S" width="28px"/><path d="M 2.44 3.644 C 2.044 3.901 1.61 4.03 1.156 4.03 C 0.425 4.03 0 3.546 0 2.894 C 0 2.025 0.8 1.56 2.449 1.373 L 2.449 1.156 C 2.449 0.869 2.232 0.711 1.837 0.711 C 1.442 0.711 1.116 0.869 0.889 1.156 L 0.198 0.76 C 0.563 0.257 1.116 0 1.857 0 C 2.874 0 3.447 0.444 3.447 1.156 C 3.447 1.156 3.447 3.97 3.447 3.98 L 2.538 3.98 Z M 0.998 2.825 C 0.998 3.082 1.165 3.328 1.462 3.328 C 1.788 3.328 2.094 3.19 2.41 2.914 L 2.41 1.995 C 1.452 2.124 0.998 2.361 0.998 2.825 Z" fill="rgb(249, 253, 255)" height="4.029699999999998px" id="FN9bGzI59" transform="translate(8.543 21.64)" width="3.44693px"/><path d="M 0 0.188 L 0.849 0.069 L 0.938 0.533 C 1.422 0.188 1.798 0 2.281 0 C 3.081 0 3.496 0.425 3.496 1.264 L 3.496 3.98 L 2.469 3.98 L 2.469 1.442 C 2.469 0.968 2.341 0.751 1.975 0.751 C 1.669 0.751 1.363 0.889 1.017 1.185 L 1.017 3.98 L 0 3.98 Z" fill="rgb(249, 253, 255)" height="3.9802999999999997px" id="RfAEC7no7" transform="translate(12.789 21.649)" width="3.4962999999999997px"/><path d="M 1.837 4.059 C 0.691 4.059 0 3.319 0 2.035 C 0 0.741 0.691 0 1.817 0 C 2.943 0 3.615 0.711 3.615 1.985 C 3.615 2.054 3.605 2.123 3.605 2.183 L 1.007 2.183 C 1.017 2.923 1.323 3.289 1.926 3.289 C 2.311 3.289 2.568 3.131 2.805 2.785 L 3.555 3.2 C 3.23 3.763 2.637 4.059 1.837 4.059 Z M 2.607 1.521 C 2.607 0.998 2.311 0.691 1.827 0.691 C 1.363 0.691 1.076 0.988 1.037 1.521 Z" fill="rgb(249, 253, 255)" height="4.059299999999997px" id="KoEdzNywt" transform="translate(21.242 21.64)" width="3.614799999999999px"/><path d="M 1.926 4.109 C 0.909 4.109 0 3.467 0 2.054 C 0 0.642 0.919 0 1.926 0 C 2.943 0 3.852 0.642 3.852 2.054 C 3.852 3.467 2.943 4.109 1.926 4.109 Z M 1.926 0.859 C 1.165 0.859 1.017 1.551 1.017 2.045 C 1.017 2.548 1.156 3.23 1.926 3.23 C 2.696 3.23 2.835 2.538 2.835 2.045 C 2.835 1.551 2.686 0.859 1.926 0.859 Z" fill="rgb(249, 253, 255)" height="4.108699999999999px" id="bNT7ln6S9" transform="translate(1.52 21.63)" width="3.85185px"/><path d="M 0 0.089 L 0.978 0.089 L 0.978 0.543 C 1.165 0.296 1.62 0 2.054 0 C 2.094 0 2.143 0 2.183 0.01 L 2.183 0.968 C 2.163 0.968 2.153 0.968 2.133 0.968 C 1.689 0.968 1.195 1.037 1.047 1.383 L 1.047 3.97 L 0 3.97 Z" fill="rgb(249, 253, 255)" height="3.970399999999998px" id="W79pXdVlT" transform="translate(6.074 21.64)" width="2.18271px"/><path d="M 1.798 3.121 C 2.578 3.111 2.637 2.321 2.637 1.807 C 2.637 1.195 2.341 0.701 1.788 0.701 C 1.422 0.701 1.007 0.968 1.007 1.847 C 1.017 2.331 1.047 3.121 1.798 3.121 Z M 3.635 0.049 L 3.635 3.743 C 3.635 4.395 3.585 5.462 1.728 5.482 C 0.958 5.482 0.257 5.175 0.109 4.514 L 1.116 4.355 C 1.155 4.543 1.274 4.741 1.847 4.741 C 2.38 4.741 2.637 4.484 2.637 3.881 L 2.637 3.427 L 2.627 3.417 C 2.469 3.704 2.212 3.98 1.62 3.98 C 0.711 3.98 0 3.348 0 2.035 C 0 0.731 0.741 0 1.57 0 C 2.351 0 2.637 0.355 2.706 0.543 L 2.696 0.543 L 2.785 0.079 L 3.635 0.079 Z" fill="rgb(249, 253, 255)" height="5.4815000000000005px" id="ROLkIr5uP" transform="translate(16.996 21.669)" width="3.6346000000000025px"/><path d="M 1.027 0.168 L 0.622 0.168 L 0.622 1.284 L 0.405 1.284 L 0.405 0.168 L 0 0.168 L 0 0 L 1.017 0 L 1.017 0.168 Z M 2.706 1.284 L 2.489 1.284 L 2.489 0.207 L 2.479 0.207 L 2.054 1.284 L 1.916 1.284 L 1.491 0.207 L 1.481 0.207 L 1.481 1.284 L 1.264 1.284 L 1.264 0 L 1.59 0 L 1.975 0.978 L 2.351 0 L 2.676 0 L 2.676 1.284 Z" fill="rgb(249, 253, 255)" height="1.2840000000000025px" id="KiUMKjBl3" transform="translate(24.227 20.257)" width="2.7060999721527104px"/></g></svg>)
Orange achieves zero discrepancy trade-ins with Vision AI
How automated device grading eliminated pricing disputes and transformed the in-store trade-in experience.
Challenge
Orange Luxembourg faced a familiar problem in mobile retail: trade-in programs that created friction instead of value. Manual device grading placed employees in the difficult position of assessing device condition on the spot. This led to inconsistent evaluations and frequent discrepancies with downstream buyers. These disputes meant financial penalties, operational complexity, and a trade-in experience that fell short of customer expectations.
The core issue was clear: without objective, automated grading, trade-in programs would continue to underperform, limiting customer adoption and creating unnecessary risk for the business.
Solution
Orange deployed Pandas Vision AI across all retail locations in Luxembourg. The platform uses computer vision to assess device cosmetics and functionality through a simple camera scan (no specialized hardware required). Deployment was fast: Vision AI runs on a standard iPad, enabling rapid rollout without infrastructure delays or complex integrations.
The result is a trade-in experience that’s faster for customers, consistent across every store, and backed by grading accuracy that downstream partners can trust.
Zero discrepancy rate
Orange’s downstream device buyer, CompaRecycle, accepts Pandas grades without dispute. The accuracy of Vision AI has built complete trust in the grading process, eliminating the financial penalties and operational overhead that discrepancies previously caused.
Fast time-to-market
With no hardware requirements beyond an iPad, Orange implemented Vision AI across all locations within just a few days.
Higher trade-in offers for customers
Accurate grading means no price reductions and customers receive offers that reflect true device value, driving higher program participation and satisfaction.
Employees freed from grading responsibility
Automation removed the burden of subjective device assessment from store staff. Employees are no longer accountable for grading decisions, allowing them to focus on customer engagement rather than device inspection.
About Pandas
Pandas builds the technology that powers device programs. Vision AI delivers automated device grading through vision models enabling telecom operators, retailers, and OEMs to create trade-in, insurance, and buyback experiences that drive adoption, increase conversions, and protect margins. The platform is trusted by leading operators across Europe and beyond.
