Machine-learning infrastructure for discovery

Shaped’s APIs rank which content is most relevant for your users

from shaped import *
setup(
name="video_recommendation",
context=User,
ranking=Video,
label=Watched,
data=Snowflake,
)
results = rank(
name="video_recommendation",
context_id="Keanu",
) # Ranks videos Keanu is most likely to watch
from shaped import *
setup(
name="product_recommendation",
context=User,
ranking=Product,
label=Purchased,
data=Snowflake,
)
results = rank(
name="product_recommendation",
context_id="Jaime",
) # Ranks items Jaime is most likely to purchase
from shaped import *
setup(
name="music_recommendation",
context=User,
ranking=Audio,
label=Listened,
data=Postgres,
)
results = rank(
name="music_recommendation",
context_id="Beyonce",
) # Ranks music Beyonce might want to listen to
Video recommendation
Product recommendation
Song recommendation
Backed by
Y Combinator

In the news

No items found.

Surface relevant content like big tech

The last decade has seen a shift from search to discovery led products.
It has become an expectation that products learn and adapt to user behavior.

Ranking is the technology that has driven this shift. It’s played a pivotal role in the
growth of successful companies like TikTok, Amazon and Netflix.

That’s why we created Shaped — to help all developers use ranking like big tech.

How Shaped works

1

Use our API to connect your data stack

2

Shaped trains and deploys your custom
ranking model

3

Retrieve the content that's most relevant to your users in real-time

Rank results
4

Increase your business metrics

Increase business metrics

Leverage Shaped for multiple use-cases

Whether you’re a marketplace, media platform, e-commerce or SaaS business, Shaped lets you deploy ranking models for your discovery pages, feeds, recommendations, internal tools, or even customer communication.

Content use cases

Content

Watch videos use case
Videos
to watch
Add products use case
Products
to buy
Like images use case
Images
to click
Social use cases

Social

Add user use case
Users
to follow
Join groups use case
Groups
to join
Thumbs up use case
Posts
to like
Communication use cases

Communication

Notifications use case
Notifications
to push
Rank emails use case
Emails
to send
SMS use case
SMS
to send

Designed for developers

We wrapped all the ranking infrastructure you need into an elegant, easy-to-use API.

That means you don’t need to spend months handling the data engineering, model training, and deployment difficulties inherent to ranking.

less data required

Less data required

Shaped pre-trains models so you don’t need much data to get started. This is what allows you to get great results from day 1.

less data required

Use all data types

Shaped drives growth with user interaction data and unstructured data types like images, videos, text or social graphs.

less data required

Deploy in hours

Shaped is built directly on top of your data stack meaning we can train and deploy predictive ranking models in hours.

Ready to get started?

Contact us

We’ll be in touch within 24 hours 🙌
We’ll be in touch within 24 hours 🙌
Oops! Something went wrong while submitting the form.

Built by scientists, engineers, designers, and product from