Building AI With MongoDB: Boosting Productivity and Efficiency with Assistants and Agents

Among generative AI’s (genAI) many predicted benefits, its potential in unlocking new levels of employee productivity and operational efficiency are frequently cited.

Over the course of our “Building AI with MongoDB” blog post series, we’ve featured multiple examples of genAI being used to automate repetitive tasks with virtual assistants and intelligent agents. From conversational AI with natural language processing (NLP) to research and analysis, examples from previous posts include:

• Ada: automating customer service for the likes of Meta, Shopify, and Verizon

• Eni: supporting its geologists’ research on the company’s path to net zero

• ExTrac: sifting through online chatter to track emerging threats to public safety

• Inovaare: transforming complex healthcare compliance processes

• Zelta: analyzing real-time customer feedback to prioritize product development

In today’s roundup of AI builders, I’ll cover three more organizations that are applying genAI-powered assistants and agents. You’ll see how they are freeing staff to focus on more strategic and productive tasks while simplifying previously complex and expensive business processes.

WINN.AI: The virtual assistant tackling sales admin overhead

Salespeople typically spend over 25% of their time on administrative busywork — costing organizations time, money, and opportunity. WINN.AI is working to change that so that sales teams can better invest their working hours in serving customers.

At the heart of WINN.AI is an AI-powered real-time sales assistant that joins virtual meetings to detect, interpret, and respond to customer questions. By comprehending the context of a conversation, it can immediately surface relevant information to the salesperson, for example retrieving appropriate customer references or competitive information. It can provide prompts from a sales playbook, and also make sure meetings stay on track and on time. At the end of the meeting, WINN.AI extracts and summarizes relevant information from the conversation and updates the CRM system with follow-on actions.

Discussing its AI technology stack, Orr Mendelson, Ph.D., the head of R&D at WINN.AI says:

“We started out building and training our own custom NLP algorithms and later switched to GPT 3.5 and 4 for entity extraction and summarization. We orchestrate all of the models with massive automation, reporting, and monitoring mechanisms. This is developed by our engineering teams and assures high-quality AI products across our services and users. We have a dedicated team of AI engineers and prompt engineers that develop and monitor each prompt and response so we are continuously tuning and optimizing app capabilities.”

Describing its use of MongoDB Atlas, Mendelson says:

“MongoDB stores everything in the WINN.AI platform. The primary driver for selecting MongoDB was its flexibility in being able to store, index, and query data of any shape or structure. The database fluidly adapts to our application’s data objects, which gives us a more agile approach than traditional relational databases.”

Mendelson adds, “MongoDB is familiar to our developers so we don’t need any DBA or external experts to maintain and run it safely. We can invest those savings back into building great AI-powered products. MongoDB Atlas provides the managed services we need to run, scale, secure, and back up our data."

WINN.AI is part of the MongoDB AI Innovators program, benefiting from access to free Atlas credits and technical expertise. Take a look at the full interview with Mendleson to learn more about WINN.AI and its AI developments.

One AI: Providing AI-as-a-Service to deliver solutions in days rather than months

The mission at One AI is to bring AI to everyday life by converting natural language into structured, actionable data. It provides seamless integration into products and services, and uses generative AI to redefine human-machine interactions.

One AI curates and hones leading AI capabilities from across the ecosystem, and packages them as easy-to-use APIs. It’s a simple but highly effective concept that empowers businesses to deploy tailored AI solutions in days rather than weeks or months.

“One AI was founded with the goal of democratizing and delivering AI as a service for companies,” explains Amit Ben, CEO and founder at One AI. “Our customers are product and services companies that plug One AI into the heart and core value of their products,” says Ben. “They are spread across use cases in multiple domains, from analyzing financial documents to AI-automated video editing.”

One AI works with over 20 different AI/ML models. Having a flexible data infrastructure was key to helping harness the latest innovations in data science, as Ben explains:

“The MongoDB document model really allows us to spread our wings and freely explore new capabilities for the AI, such as new predictions, new insights, and new output data points.” Ben adds, “With any other platform, we would have to constantly go back to the underlying infrastructure and maintain it. Now, we can add, expand, and explore new capabilities on a continuous basis.”

The company also benefits from the regular new releases from MongoDB, such as Atlas Vector Search, which Ben sees as a highly valuable addition to the platform’s toolkit. Ben explains: “The ability to have that vectorized language representation in the same database as other representations, which you can then access via a single query interface, solves a core problem for us as an API company."

To learn more, watch the interview with Amit Ben.

4149.AI: Maximizing team productivity with a hypertasking AI-powered teammate

4149.AI helps teams get more work done by providing them with their very own AI-powered teammate. During the company’s private beta program, the autonomous AI agent has been used by close to 1,000 teams to help them track goals and priorities. It does this by building an understanding of team dynamics and unblocking key tasks. It participates in Slack threads, joins meetings, transcribes calls, generates summaries from reports and whitepapers, responds to emails, updates issue trackers, and more.

4149.AI uses a custom-built AI-agent framework leveraging a combination of embedding models and LLMs from OpenAI and AI21 Labs, with text generation and entity extraction managed by Langchain. The models process project documentation and team interactions, persisting summaries, and associated vector embeddings into Atlas Vector Search. There is even a no-code way for people to customize and expand the functionality of their AI teammate. Over time, the accumulated context generated for each team means more and more tasks can be offloaded to their AI-powered co-worker.

The engineers at 4149.AI evaluated multiple vector stores before deciding on Atlas Vector Search. The ability to store summaries and chat history alongside vector embeddings in the same database accelerates developer velocity and the release of new features. It also simplifies the technology stack by eliminating unnecessary data movement.

Hybrid search is another major benefit provided by the Atlas platform. The ability to pre-filter data with keyword-based Atlas Search before semantically searching vectors helps retrieve relevant information to users faster.

Looking forward, 4149.AI has an aggressive roadmap for its products as it starts to more fully exploit the chain-of-thought and multimodal capabilities provided by the most advanced language models. This will enable the AI co-worker to handle more creative tasks requiring deep reasoning, such as conducting market research, monitoring the competitive landscape, and helping identify new candidates for job vacancies. The goal for these AI teammates is for them to eventually be able to take the initiative in what to do next rather than rely on someone to manually assign them a task.

Being part of MongoDB’s AI Innovators program puts 4149.AI on a path to success with access to technical support and free Atlas credits, helping them quickly experiment using the native AI capabilities available in the MongoDB developer data platform.

Getting started

These are just a few examples of the capabilities of genAI-powered assistants and agents. Check out our library of AI case studies to see the range of applications developers are building with MongoDB.

Our 10-minute learning byte is a great way to learn what you can do with Atlas Vector Search, how it’s different from other forms of search, and what you’ll need to get started using it.