LandingAI Expands Agentic Document Intelligence with A Document Pre-trained Transformer

Billions of images and documents to be agentically understood, improving and speeding results

PALO ALTO, Calif., Sept. 30, 2025 /PRNewswire/ -- LandingAI, a pioneer in agentic vision AI technologies, today announced its significant upgraded version of Agentic Document Extraction (ADE) which will use a new model, Document Pre-trained transformer-2, to accurately extract information even from complex documents, to better inform organizational decision making.

Document Pre-trained transformer (DPT-2) builds on the strength of ADE's initial launch six months ago, which enabled developers, startups, and Fortune 500 companies to process billions of pages through ADE, with many reporting up to a 90% reduction in time spent searching for information.

ADE DPT-2 represents an even more refined foundation for document intelligence. While generic LLMs often struggle to accurately, fully and consistently extract all visual information from documents, DPT-2 combines structured deep learning models with agentic workflows to deliver higher accuracy and trusted outputs from documents filled not only with text, but also data in the form of tables without gridlines, invoices scanned at odd angles, signatures embedded inside forms, checkboxes, and so on.

"Documents contain the information that organizations need to make not only accurate but the best decisions possible. Key nuances can be lost if the visual representations are not adequately captured," said Dan Maloney, CEO of LandingAI. "ADE addresses this gap and our enhanced release pushes capabilities even further."

LandingAI looks for rapid uptake in industries such as finance, healthcare, insurance, or compliance where accuracy is not optional and workflows are primed for greater agentic efficiencies.

"We're past the era of one-size-fits-all models. Just as we use different processors today for different workloads (your smartwatch has a less powerful processor than your laptop than the datacenter), for AI workloads too, we need different types and amounts of intelligence to do different things." Andrew Ng, founder of LandingAI. "ADE DPT-2, specialized in processing documents, works uniquely well in the space of document extraction."

ADE DPT-2 breaks complex parsing tasks into smaller, reliable steps. New features in the release include:

• Agentic Table Captioning. DPT-2 can parse large, complex, no-gridline, and merged-cell tables with unprecedented fidelity. Every cell is preserved, aligned, and made accessible, enabling cell-level grounding so users know exactly where values came from.
• Figure Captioning, Refined. Logos, seals, and small figures are identified precisely and concisely, eliminating the noise of verbose descriptions.
• Smarter Layout Detection. Fewer chunks are missed, even in messy scans. DPT-2 can even detect stamps inside tables and process them separately—critical for compliance workflows.
• Expanded Chunk Ontology. Beyond text, tables, and figures, DPT-2 recognizes signatures, checkboxes, ID cards, barcodes, and QR codes—ensuring all document elements are classified consistently.

DPT-2, now available in preview, is available in the playground and via API. And the Parse and Extract APIs are all Generally Available and ready for production use for use cases such as:

• Parse converts documents into structured markdown and semantic chunks.
• Extract delivers schema-driven extraction of fields, powered by LLM reasoning, with grounding back to the original document.

Tools for Builders

LandingAI also recently launched its Builder Program to help developers and organizations build document-processing solutions with ADE APIs. The program offers priority support, early feature access, higher rate limits, and go-to-market support to help organizations confidently develop and scale enterprise applications powered by ADE. With SDKs, cookbooks, and direct access to LandingAI experts, Builders can bring production-ready solutions to market faster. Learn more at landing.ai/partners

LandingAI™ delivers cutting-edge agentic vision AI technologies that empower customers to unlock the value of visual data. With LandingAI's solutions, companies realize the value of AI and move AI projects from proof-of-concept to production. LandingAI's flagship product, LandingLens™, enables users to build, iterate, and deploy Visual AI solutions quickly and easily. LandingAI is a pioneer in agentic vision technologies, including Agentic Document Extraction, which empowers the world's leading companies to transform unstructured visual data–from documents, images–into actionable intelligence. Our agentic AI platform makes it possible to build and deploy powerful vision applications that drive efficiency and innovation at scale. Founded by Andrew Ng, co-founder of Coursera, founding lead of Google Brain, and former chief scientist at Baidu, LandingAI is uniquely positioned to lead the development of Visual AI that benefits all. For more information, visit Landing.ai.

CONTACT: press@landing .ai 

SOURCE LandingAI