Writer

Writer is the full-stack generative AI platform for enterprises. We empower your entire organization — support, operations, sales, HR, marketing, and more — to accelerate growth, increase productivity, and ensure compliance. 

Writer transforms work by delivering high-quality outputs that are accurate, compliant, and on-brand. Palmyra, our family of transparent and auditable LLMs, is top-scoring on benchmarks like Stanford HELM and PubMedQA, faster and more cost-effective than larger models, and fine-tuned for specific industries. Our platform consists of our Writer-built LLMs, a Knowledge Graph that connects our models to your internal data sources, AI guardrails to enforce your rules, and a flexible application layer of chat interfaces, custom apps, and composable UI options that serves a wide range of use cases. Our robust APIs and integrations put generative AI in all the places your people work. 

Our enterprise-grade platform doesn’t use your data in model training and complies with SOC 2 Type II, HIPAA, PCI, GDPR, and Privacy Shield. We offer flexible deployment options, including Writer-managed and customer-managed. Leading enterprises choose Writer, including Vanguard, Intuit, L'Oreal, Accenture, Dropbox, and Salesforce. Visit us at writer.com.

Co-founder and CEO

Qordoba

At Qordoba, we love words! That’s why we build software that helps companies localize content that’s clear, consistent, and on-brand.

More specifically, Qordoba’s AI-powered platform help organizations like Marriott and Braintree localize and align all types of content — from communications to marketing to product to HR. 

Feel free to DM me if you’d like to learn more!

Co-founder

World Economic Forum

Global Shaper

Mubadala Development Company

Vice President

Lehman Brothers

Analyst

May Habib is CEO and co-founder of Writer, a generative AI platform for the enterprise. 

May has worked in NLP and ML for 10 years, and before Writer she founded and built Qordoba, a machine translation and localization software company. She is an expert in AI-driven language generation, AI-related organizational change, and the evolving ways we use language online.

May graduated with high honors in Economics from Harvard University, is a member of the World Economic Forum, and is a Fellow of the Aspen Global Leadership Network.

If powerful LLMs were all that was needed to get to great enterprise generative AI programs, then hundreds of thousands of open-source and closed-source LLMs would mean we'd all have the AI programs of our dreams.

But most enterprise use cases require retrieval-augmented generation (RAG), which basically is a way to give an LLM-based AI app a lot more supporting information about a question being asked / workflow being run.

Despite a lot of time and money invested, many RAG-based apps are still failing at being intelligent, and at Writer, we've found graph-based RAG to very often fix an implementation.

Visualizations are helpful to explain WHY you can get better, deeper, more accurate answers when you integrate knowledge graphs into RAG.

Column 1 is vector-based RAG. Here's what happens:

1️⃣ Data processing: Text data is split into smaller chunks, converted into numbers (vector embeddings), and stored in a vector database. Numerical distance between embeddings is how we know how things are related.

2️⃣ Query and retrieval: In vector-based retrieval, the user's question is converted to an embedding too, and we use those query data points to retrieve the closest other data points to the query, using "nearest  neighbour" type of algos — it’s a similarity search.

3️⃣ Answer generation: The retrieved vector embeddings (the neighbours!) are remapped to the original text data and sent to the LLM for answer generation.

Column 2 is Writer's graph-based RAG. And here's what happens there:

1️⃣ Data processing: Writer's uses a built-for-purpose LLM to *first* split the data you want for RAG into nodes and builds relationships as edges, and stores the node/edge data in a graph structure. The edges are SEMANTIC relationships that would otherwise be lost if you turned text into numbers/vectors.

2️⃣ Query and retrieval: Graph-based retrieval breaks down the query into entities and semantic relationships, and then uses NLP algorithms, heuristic algorithms, and machine learning techniques to map those relationships to semantic connections in the graph of your data, and retrieves both relevant nodes/entities and relationships as potentially relevant. Much more similar to how a human thinks. We think in relationships, not text similarity. 

3️⃣ Answer generation: The retrieved entities and relationships are extracted from the graph and sent to the LLM for answer generation.

So which is better? It depends on the use case. 

🔸 Vector-based RAG can be used for simpler tasks where contextual understanding is not as important — use cases with vast amounts of data but straightforward relationships.

🔸 Graph-based RAG is better for more complex tasks where deeper contextual understanding is critical, aspects of the answer will sit across multiple sets of data/docs, and more "reasoning" is required. Use cases with important relationships—medical diagnosis, legal research, etc.

Taplio

May Habib's Linkedin Analytics

May Habib

What is May talking about?

May Habib's Best Posts (last 30 days)

Want to drive more opportunities from LinkedIn?