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
Sensing technology is facilitating the transition of drone delivery services from trial phases to regular daily operations.
Updated
January 23, 2026 10:41 AM
A quadcopter drone with package attached. PHOTO: FREEPIK
A new partnership between Hesai Technology, a LiDAR solutions company and Keeta Drone, an urban delivery platform under Meituan, offers a glimpse into how drone delivery is moving from experimentation to real-world scale.
Under the collaboration, Hesai will supply solid-state LiDAR sensors for Keeta’s next-generation delivery drones. The goal is to make everyday drone deliveries more reliable as they move from trials to routine operations. Keeta Drone operates in a challenging space—low-altitude urban airspace. Its drones deliver food, medicine and emergency supplies across cities such as Beijing, Shanghai, Hong Kong and Dubai. With more than 740,000 deliveries completed across 65 routes, the company has discontinued testing the concept. It is scaling it. For that scale to work, drones must be able to navigate crowded environments filled with buildings, trees, power lines and unpredictable conditions. This is where Hesai’s technology comes in.
Hesai’s solid-state LiDAR is integrated into Keeta's latest long-range delivery drones. LiDAR stands for Light Detection and Ranging. In simple terms, it is a sensing technology that helps machines understand their surroundings by sending out laser pulses and measuring how they bounce back. Unlike GPS, LiDAR does not rely solely on satellites to determine position. Instead, it gives drones a direct sense of their surroundings, helping them spot small but critical obstacles like wires or tree branches.
In a recent demonstration, Keeta Drone completed a nighttime flight using LiDAR-based navigation alone without relying on cameras or satellite positioning. This shows how the technology can support stable operations even when visibility is poor or GPS signals are limited.
The LiDAR system used in these drones is Hesai’s second-generation solid-state model known as FTX. Compared with earlier versions, the sensor offers higher resolution while being smaller and lighter—important considerations for airborne systems where weight and space are limited. The updated design also reduces integration complexity, making it easier to incorporate into commercial drone platforms. Large-scale production of the sensor is expected to begin in 2026.
From Hesai’s perspective, delivery drones are one of several forms robots are expected to take in the coming decades. Industry forecasts suggest robots will increasingly appear in many roles from industrial systems to service applications, with drones becoming a familiar part of urban infrastructure rather than a novelty.
For Keeta Drone, this improves safety and reliability. And for the broader industry, it signals that drone logistics is entering a more mature phase—one defined less by experimentation and more by dependable execution. Taken together, the partnership highlights a practical evolution in drone delivery.
As cities grow more complex, the question is no longer whether drones can fly but whether they can do so reliably, safely and at scale. At its core, this partnership is not about drones or sensors as products. It is about what it takes to make a complex system work quietly in real cities. As drone delivery moves out of pilot zones and into everyday use, reliability matters more than novelty.