Artificial Intelligence
Formic AI Introduces Boreal, An Explainable Language Model Built For Verifiable Enterprise Use
Share
Boreal restructures unstructured text into a verifiable knowledge graph, checks answers against source material, and records its reasoning for an auditable trail, pairing precision with an efficiency-minded design.
TORONTO, Jan. 05, 2026 (GLOBE NEWSWIRE) -- Formic AI today announced the launch of Boreal, an explainable language model (XLM) built to deliver answers that organizations can verify to source and audit end-to-end. Boreal turns unstructured text into a knowledge graph, cross-checks each answer against the original materials before display, and logs the reasoning steps so reviewers can trace how a result was produced.
Unlike systems that rely only on probabilistic next-word prediction, Boreal operates on a structured, queryable graph. This approach shifts risk from opaque guesswork to evidence-based interpretation, which is why it is positioned for high-stakes professional work where provenance and accountability are required.
“Trust comes from being able to check the answer and the path that produced it,” said Daniel Escott, Chief Executive Officer at Formic AI. “Boreal gives teams a clear link back to source documents and a simple audit trail, so decisions are grounded in verifiable evidence rather than guesswork.”
“Boreal pairs a neuro-symbolic engine for precise, auditable analysis with a generative fluency engine for drafting and conversational tasks,” said Varun Ranganathan, Chief Technology Officer at Formic AI. “That hybrid design keeps day-to-day work efficient while preserving the ability to show how every result was assembled.”
Boreal’s design emphasizes trust through verification. Deterministic checks block unsupported statements before they reach the user, and the audit trail captures the route taken through the source corpus for quick review. The model is engineered for efficiency using a precomputed graph-traversal approach that reduces the compute required for retrieval and integration, supporting practical deployment choices and aligning with environmentally and fiscally responsible AI use goals.
To meet security and governance needs, Boreal supports on-premises and air-gapped environments. It can also act as a governance layer around existing tools built on language models, adding grounding, preventing hallucinations, and providing auditability without forcing teams to rip apart and replace their workflows.
Academic Partnership and Program Recognition
Formic AI is proud to announce its partnership with York University’s Connected Minds program in support of a research project centred on Boreal. Through the program’s Prototyping Award, Formic AI has received funding as well as non-financial support, including commercialization assistance.
For more information about Formic AI and to request a demonstration, visit www.formic.ai.
About Formic AI
Formic AI is Canada's trusted AI platform, empowering organizations to get authentic, reliably sourced answers from their own knowledge archives. Every response delivered by Formic AI is accompanied by transparent citations, ensuring verifiable, trustworthy outcomes for regulated industries and legal teams. By combining local innovation, explainable outputs and full data control, Formic AI sets the standard for reliable, sustainable and accountable artificial intelligence in Canada. To learn more, visit https://www.formic.ai/
Media Contact:
Ashley McFarlane, Talk Shop Media
ashley@talkshopmedia.com
647-522-0660
Frequently Asked Questions
What is Boreal and what does it do?
Boreal is an explainable language model (XLM) from Formic AI that converts unstructured text into verifiable knowledge graphs, providing auditable and evidence-based answers.
How does Boreal ensure accuracy and trust?
It cross-checks answers against source materials, logs reasoning steps for auditing, and uses deterministic checks to prevent unsupported or hallucinated statements.
Can Boreal integrate with existing AI tools?
Yes, Boreal can act as a governance layer for existing language models, adding grounding, preventing hallucinations, and providing auditability without workflow disruption.
First published on Tue, Jan 6, 2026
Enjoyed what you've read so far? Great news - there's more to explore!
Stay up to date with the latest news, a vast collection of tech articles including introductory guides, product reviews, trends and more, thought-provoking interviews, hottest AI blogs and entertaining tech memes.
Plus, get access to branded insights such as informative white papers, intriguing case studies, in-depth reports, enlightening videos and exciting events and webinars from industry-leading global brands.
Dive into TechDogs' treasure trove today and Know Your World of technology!
Disclaimer - Reference to any specific product, software or entity does not constitute an endorsement or recommendation by TechDogs nor should any data or content published be relied upon. The views expressed by TechDogs' members and guests are their own and their appearance on our site does not imply an endorsement of them or any entity they represent. Views and opinions expressed by TechDogs' Authors are those of the Authors and do not necessarily reflect the view of TechDogs or any of its officials. While we aim to provide valuable and helpful information, some content on TechDogs' site may not have been thoroughly reviewed for every detail or aspect. We encourage users to verify any information independently where necessary.
Trending GlobeNewswire
Loyaltylion Launches AI Campaigns To Help Shopify Brands Drive More Loyalty Revenue
Overworld Unveils Real-Time Diffusion World Model For Playable, AI-Native Worlds
Intuitive.Ai Partners With Matilda Cloud To Accelerate Secure, Compliant AI And Cloud Modernization For Life Sciences
AI-First Hits Amazon Best Sellers List: The Executive Blueprint For Transformation
Activengage To Unveil AI Suite Of Products At NADA Show 2026
Join Our Newsletter
Get weekly news, engaging articles, and career tips-all free!
By subscribing to our newsletter, you're cool with our terms and conditions and agree to our Privacy Policy.
Join The Discussion