LAUNCHMongoDB 8.3 is built for the sub-100ms retrieval & zero downtime AI demands. Read blog >

AI DATAStop fighting your data layer. Get the memory & retrieval agents need to scale. Read blog >

TinyFish

TinyFish Scales AI Agent Platform with MongoDB

Two professionals sitting in an office, looking at a computer screen and discussing work.

The Challenge

TinyFish needed highly accurate embeddings to power thousands of AI agents that automate web research and data extraction for enterprises.

Our Solution

TinyFish adopted Voyage AI for precise product matching and reranking.

Outcome

Enterprises can access fresh, structured web data, eliminating the need for weeks of ETL processing and accelerating decision-making.

Industry

Computer Software and Technology

Product

Voyage AI

MongoDB Atlas

Use Case

Gen AI

TinyFish Cofounder and CEO Sudheesh Nair explains how his company uses Voyage AI’s embedding and reranking models to transform web-based research for enterprise knowledge workers.

THE CHALLENGE

Building an intelligent web engine at enterprise scale

Product managers, marketing analysts, and other enterprise knowledge workers spend hours browsing the internet, conducting research, interacting with websites, and extracting data. TinyFish, which launched with $47 million in funding, set out to change this reality. The company’s platform deploys thousands of specialized AI agents that autonomously perform the web-based research and data extraction tasks that typically consume knowledge workers’ most valuable time. Like schools of fish that swarm together to achieve a goal, these agents collaborate to manage and run critical web-based workflows.

TinyFish focuses on use cases where fresh internet data can create immediate value: product matching for retailers, competitive pricing analysis, and social sentiment tracking. To achieve accurate results at enterprise scale, the company needed fast, precise, and reliable retrieval capabilities. Embedding models and rerankers provided the ideal solution, enabling search and retrieval systems that could accurately understand intent and meaning within unstructured web data.

“We were looking for extremely accurate embedding models, and Voyage AI provided accuracy at scale. The Python APIs that Voyage comes out of the box with are also extremely lightweight and very fast.”

Sudheesh Nair
Cofounder and CEO, TinyFish

OUR SOLUTION

Using Voyage AI and MongoDB to power enterprise web intelligence for TinyFish

TinyFish built its product-matching solution by using the embedding and reranking capabilities of Voyage AI, part of the MongoDB ecosystem. The platform uses the Voyage AI voyage-3.5 embedding model to index competitor catalogs and quickly identify an initial set of similar products to what vendors are selling. The Voyage AI rerank-2.5 reranking model then refines the results to surface the most relevant options.

“We were looking for extremely accurate embedding models, and Voyage AI provided accuracy at scale,” says Sudheesh Nair, Cofounder and CEO of TinyFish. “The Python APIs that Voyage comes out of the box with are also extremely lightweight and very fast.”

“When it comes to document storage, when it comes to unstructured data, MongoDB is the place. It’s the bookend for value creation and value delivery.”

Sudheesh Nair
Cofounder and CEO, TinyFish

OUTCOME

Accelerating decision-making with fresh internet data

By combining the semantic understanding of Voyage AI with the flexible data storage of MongoDB, TinyFish has created a new pathway for internet data to drive business value. The solution takes the signal from internet noise and delivers it as structured intelligence that enterprises can act on immediately. Instead of waiting weeks for data to move through traditional ETL processes and dashboard updates, businesses can make decisions based on fresh, accurate information extracted in real time.

Using this technology, TinyFish can rapidly expand into its use cases in customer acquisition, marketing analytics, and more. As TinyFish continues to scale, the company is exploring MongoDB Atlas to create a unified data infrastructure for the unstructured web data its agents extract. “When it comes to document storage, when it comes to unstructured data, MongoDB is the place,” says Nair. “It’s the bookend for value creation and value delivery.”

The data foundation for your AI strategy

MongoDB’s flexible document model is built for the complex, fast-moving data that modern AI applications require.

Learn More

Explore more success stories

View all stories

LG U+

Read about how LG U+ improves efficiency by 30% with MongoDB-powered AI tool

With Video

DevRev

Learn how IT company DevRev boosted its CRM solution’s performance by 3-4x with MongoDB Atlas.

With Video

Lombard Odier

Learn more about how Lombard Odier modernizes legacy banking technology with gen AI

Take the next step

Get access to all the tools and resources you need to start building something great when you register today.

Get StartedTalk to an expert