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
A closer look at PMMI’s FastTrack initiative and why it matters for growing manufacturing firms
Updated
February 13, 2026 10:44 AM
Cardboard boxes in a warehouse. PHOTO: UNSPLASH
Large trade shows are built for scale. But for small and medium-sized manufacturers, that scale often creates distance between what’s on display and what they can actually use. Too many options, too little time, and very few tools designed for companies that are still growing. That mismatch is what PMMI is trying to correct with its new SMB FastTrack Program at PACK EXPO East 2026.
That is the problem PMMI is trying to address with its new SMB FastTrack Program, launching at PACK EXPO East 2026 in Philadelphia.
PMMI — the Association for Packaging and Processing Technologies — is the industry body behind the PACK EXPO trade shows and a central organization in the global packaging and processing sector. Through FastTrack, it has created a program (not an app or a product) designed to help small and mid-sized companies navigate the show more efficiently and connect with solutions that fit their scale.
The idea behind SMB FastTrack is simple: reduce friction. Instead of asking smaller firms to sort through hundreds of exhibitors and sessions on their own, the program curates what is most relevant to them. Exhibitors that offer flexible pricing, right-sized machinery, or SMB-focused services are clearly identified with visual icons in both the online directory and on the show floor. That way, a small manufacturer can quickly distinguish between enterprise-only vendors and partners that are realistically accessible.
The same logic carries into education. Rather than treating all attendees the same, PACK EXPO East 2026 will include a learning track specifically built around SMB realities. These sessions focus on issues that smaller teams actually face—how to hire and train workers, use AI without over-investing, improve food safety, cut operating costs, and adopt technology in stages. The goal is not inspiration, but applicability: content that reflects real constraints, not ideal scenarios.
Planning, too, is built into the structure of the program. Through a dedicated FastTrack landing page, participants can access curated supplier lists, recommended sessions, and planning tools that help organize their time before they ever step onto the show floor. Tools like category search and sustainability finders are meant to narrow choices quickly, turning a massive event into something manageable.
Seen together, these elements point to a broader intention. PMMI is not simply adding features—it is reshaping how smaller manufacturers experience a major industry event. Instead of competing for attention in a space built for scale, SMBs are given clearer paths to the people, tools, and knowledge that match where they actually are in their growth cycle.
What makes SMB FastTrack notable is not the technology behind it, but the intention behind it. PMMI is recognizing that progress for small and mid-sized manufacturers depends less on spectacle and more on fit—solutions that are accessible, affordable, and adaptable. The program is designed to help companies move with purpose, not pressure.
In an industry where visibility often follows size, SMB FastTrack represents a structural shift. It treats small and medium-sized manufacturers not as a subset of the audience, but as a distinct group with distinct needs. By doing so, PMMI is quietly redefining what a trade show can be: not just a marketplace of innovation, but a usable platform for companies still building their next stage of growth.