As workplace knowledge spreads across chats, AI firms are building systems that can structure, retrieve and preserve it over time.
Updated
May 11, 2026 5:24 PM
A messaging app on a phone. PHOTO: ADOBE STOCK
Votee AI, an enterprise AI company headquartered in Hong Kong, has partnered with its Toronto-based research lab Beever AI to launch Beever Atlas. The new platform is designed to turn workplace chats into searchable knowledge that AI systems can retrieve and understand.
The release focuses on a growing issue inside organisations. Much of today’s workplace knowledge now exists inside chat platforms such as Slack, Microsoft Teams, Discord and Telegram. Important discussions, project decisions and technical information often disappear into long message histories that are difficult to search later.
Beever AI developed the platform to organise those conversations into a structured system for AI assistants. The software connects with Telegram, Discord, Mattermost, Microsoft Teams and Slack, then converts conversations into linked records of people, projects, files and decisions.
The collaboration combines Votee AI’s enterprise infrastructure work with Beever AI’s research around AI memory systems. The companies are releasing two versions of the product. The open-source edition is aimed at individual developers, researchers and creators. The enterprise edition is designed for banks, government agencies and larger organisations with stricter security requirements.
The release also reflects a broader shift happening across the AI industry. Companies are increasingly looking at how AI systems store and retrieve long-term knowledge, rather than relying solely on large context windows or search-based retrieval.
Earlier this year, OpenAI founding member and former director of AI at Tesla Andrej Karpathy discussed the growing need for what he described as “LLM Knowledge Bases.” He argued that AI systems need structured and evolving memory rather than depending only on context windows and vector search.
Beever Atlas approaches that problem through workplace communication. Instead of focusing mainly on uploaded files, the system is designed around conversations that happen daily across team chat platforms. It can also process images, PDFs, voice notes and video files within the same searchable system.
The companies say the software is designed to work directly with AI assistants and coding tools such as Cursor, AWS Kiro and Qwen Code. Integrations for OpenClaw and Hermes Agent are expected later in 2026.
Pak-Sun Ting, Co-Founder and CEO of Votee AI said: "Hong Kong has always been known for property and finance. Beever Atlas is proof that world-class AI infrastructure can emerge from an HK-headquartered company and be shared openly with the world. Every growing organization faces the same silent liability: conversational knowledge loss. Beever Atlas turns this perishable resource into a compounding organizational asset."
A large part of the enterprise version focuses on privacy and access control. The system mirrors permissions from Slack and Microsoft Teams so users can only retrieve information they are already authorised to access. Permission updates are reflected automatically when access changes inside company systems.
The enterprise edition also includes audit logs, encryption controls and data retention settings for organisations handling sensitive internal data. Companies can run the software entirely inside their own infrastructure using Docker and connect it to their preferred AI models through LiteLLM.
The companies argue that organising information is more useful than simply storing chat archives. Jacky Chan Co-Founder and CTO of Votee AI said: "The key technical decision was to treat agent memory as a knowledge engineering problem, not a retrieval problem. Structure beats similarity — a typed graph of who works on what is more useful to an AI than vector search over a Slack archive."
The software also includes protections against prompt injection attacks and systems designed to reduce hallucinated responses. According to the companies, the AI is designed to return “I don't know” with citations when confidence is low instead of generating unsupported answers.
As workplace communication becomes increasingly fragmented across chat platforms, companies are beginning to treat internal conversations as information that AI systems can organise, retrieve and build on. Beever Atlas reflects a broader push to turn everyday workplace communication into long-term organisational memory.
Keep Reading
Turning computing heat into a practical heating solution for greenhouses.
Updated
January 23, 2026 10:41 AM
Inside of a workstation computer with red lighting. PHOTO: UNSPLASH
Most computing systems have one unavoidable side effect: they get hot. That heat is usually treated as a problem and pushed away using cooling systems. Canaan Inc., a technology company that builds high-performance computing machines, is now showing how that same heat can be reused instead of wasted.
In a pilot project in Manitoba, Canada, Canaan is working with greenhouse operator Bitforest Investment to recover heat generated by its computing systems. Rather than focusing only on computing output, the project looks at a more basic question—what happens to all the heat these machines produce and can it serve a practical purpose?
The idea is simple. Canaan’s computers run continuously and naturally generate heat. Instead of releasing that heat into the environment, the system captures it and uses it to warm water. That warm water is then fed into the greenhouse’s existing heating system. As a result, the greenhouse needs less additional energy to maintain the temperatures required for plant growth.
This is enabled through liquid cooling. Instead of using air to cool the machines, a liquid circulates through the system and absorbs heat more efficiently. Because liquid retains heat better than air, the recovered water reaches temperatures that are suitable for industrial use. In effect, the computing system supports greenhouse heating while continuing to perform its primary computing function.
What makes this approach workable is that it integrates with existing infrastructure. The recovered heat does not replace the greenhouse’s boilers but supplements them. By preheating the water that enters the boiler system, the overall energy demand is reduced. Based on current assumptions, Canaan estimates that a significant portion of the electricity used by the servers can be recovered as usable heat, though actual results will be confirmed once the system is fully operational.
This matters because heating is one of the largest energy expenses for commercial greenhouses, particularly in colder regions like Canada. Many facilities still rely heavily on fossil-fuel-based heating and policies such as carbon pricing are encouraging lower-emission alternatives. Reusing computing heat offers a way to improve efficiency without requiring a complete overhaul of existing systems.
The project is planned to run for an initial two-year period, allowing Canaan to evaluate real-world performance factors such as reliability, system stability and maintenance needs. These findings will help determine whether the model can be replicated in other agricultural or industrial settings.
More broadly, the initiative reflects a shift in how computing infrastructure can be designed. Instead of operating as energy-intensive systems isolated from everyday use, computing equipment can contribute to real-world applications. Canaan’s greenhouse pilot highlights how excess heat—often seen as a by-product—can become part of a more efficient and thoughtful energy loop.
In doing so, the project suggests that improving sustainability in technology is not only about reducing energy consumption, but also about finding smarter ways to reuse the energy already being generated.