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
Amid AI and tech startups, Eastseabrother proved the power of demand and trust.
Updated
January 23, 2026 10:41 AM
Cats having a jolly good time with a can of tuna. PHOTO: UNSPLASH
At a Silicon Valley pitch event crowded with AI, SaaS and deep-tech startups, the company that stood out was not selling software or algorithms. It was selling pet treats.
Eastseabrother, a premium pet food brand from South Korea, ranked first at a Plug and Play–hosted investor pitch competition in Sunnyvale. The product itself is simple: single-ingredient pet treats made from wild-caught seafood sourced from Korea’s East Sea. The company follows a principle it calls “Only What the Sea Allows”, working directly with regional fishermen while avoiding overfishing. With no additives and minimal processing, what sets Eastseabrother apart is not novelty, but control—over sourcing, supply chains and consistency.
That clarity helped the company walk away with both Best Product and Best Potential. “Investors asked detailed questions about repeat purchase rates and customer feedback, not just our technology or supply chain”, said Eunyul Kim, CEO of Eastseabrother. “That told us the market is shifting—real consumer trust now carries as much weight as a compelling tech narrative”.
What truly caught investors’ attention was not an ambitious vision of the future, but concrete evidence of traction today. Eastseabrother has already secured shelf space in specialty pet stores across California, New York and North Carolina, including an exclusive partnership with EarthWise Pet, a national specialty retail chain. At a consumer showcase at San Francisco’s Ferry Building, the brand recorded the highest on-site sales among all participating companies.
At its core, the pitch was built on simplicity: one ingredient, clear sourcing and a defined customer need. In a market saturated with complex products and abstract claims, that focus and transparency stood out.
The judges’ decision also reflects a broader shift in venture capital thinking. Not every successful startup is built on complex software or high-tech innovation. In categories like pet care—where trust, quality and transparency shape buying behavior—execution and credibility can matter more than technical sophistication.
Today, Eastseabrother has extended its reach beyond the U.S., expanding into Singapore and Hong Kong, with additional plans to grow further in North America as demand for premium pet food rises. And the broader takeaway from this pitch is not that consumer brands are overtaking tech startups. It is that investors are increasingly focused on fundamentals: who is buying, why they are returning and whether the business can sustain itself beyond the pitch deck.