Cyncly, B2B software · 2023 to 2025
Customers could not find a product they could only picture
Led by Ansuj Joshi as senior AI engineer at Cyncly (formerly 2020 Technologies), Nov 2023 to Jan 2025
Situation
A B2B catalogue where the fastest way to describe what you want is a photo.
What we built
Visual search with deep metric learning, served through REST APIs for reverse image search and recommendations.
What changed
Customer engagement rose 35% and inference latency fell 40%.
The problem
Keyword search fails when the customer has a picture and no vocabulary. The catalogue needed search by image, integrated into existing B2B systems.
What we built
- Deep metric learning models that embed product images into a space where similar items sit together.
- REST serving for reverse image search and recommendations, integrated into the existing platform.
- Model quantisation and caching to make serving cheap and fast.
How it works
- A query image is embedded and its nearest neighbours in the catalogue are returned as results and recommendations.
What changed
35%
higher customer engagement
Source: Ansuj Joshi resume, 2026
40%
lower inference latency via quantisation and caching
Source: Ansuj Joshi resume, 2026
Stack
If this looks like your situation
Tell us where it hurts. We will say whether it is worth automating, and what we would build first.
Related work
Agriva, real estate
2026
Buyers could not search farmland the way they talk about it
Chat is now the primary way buyers search on agriva.ai, and every answer is grounded in listing data rather than guessed.
Built by Vyzma. Led by Ansuj.
Agriva, real estate
2026
Founders wanted answers from the database without waiting for a developer
Admins ask questions in plain English and get a table back, and no write path or personal data is reachable from the model.
Built by Vyzma. Led by Ansuj.
Quantiphi and Google PSO
2018 to 2019
Enterprise vision and ML delivery for Fortune 500 clients, with Google's services team
Deployment time for ML APIs fell by 60%.
60%faster ML API deployment
Led by Ansuj Joshi as machine learning engineer at Quantiphi Analytics, May 2018 to Dec 2019, including work with Google Professional Services as Associate Cloud Engineer