Agents

Improve how your team work with individually customised, enterprise-grade AI agents.
Our agents
Our agents are the core of what we do, we build them from the ground up to the specifications required by enterprise.

Fundamental to how we build our agents is our belief in how to best leverage AI - that it is best used to augment how we work (Figure 2), not to do our work for us (Figure 1).

With this in mind, we custom build our agents for individuals and their roles and responsibilities. Our agents are jacks of all trades and masters of one - yours. They help improve the quality of your work and help you do more, faster. But the work remains yours to deliver.
AI Agents help us do better work, in less time, and narrow the performance gap between low and high performers.1
Productivity

+12.2%

Increase in productivity on a selection of tasks
quality

+40%

Increase in quality on a selection of tasks
Speed

+25.1%

Increase in speed on a selection of tasks
1 Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality, Harvard Business School, 2023.
Superficial is the only individually-customised, enterprise-grade AI platform, built on multiple leading models.
We build our agents on a foundation of multiple Large Language Models (LLMs) that are updated regularly and used sequentially to ensure you're getting the most value without being locked into any single vendor.

Sitting atop this is our Security Engine which masks all confidential personal and organisational data to ensure that no private information is shared with underlying LLMs.

From this secure foundation, we construct diverse Agent Operating Systems (Agent OSs) that are trained on the top material from specific functional domains. Users select their specific Agent OS based on their role and responsibilities, and then further train their agents with proprietary organisational and personal data to build agents that are truly theirs.

agent Capabilities

Data Synthesis & Analysis

Agents are equipped to query conversational text and complex documents, helping their users synthesise and analyse vast amounts of data quickly.

Workload Planning

Agents are specifically trained with daily planning and review capabilities, helping their users to manage their workloads and learn how to augment their work with AI.

Review & Improve

Agents are trained on best-in-class, role-specific content, giving users an always-on expert in their domain to help review and improve their work.

Brainstorming & Creativity

Agents are skilled at brainstorming and helping users to think outside the box. Users can take advantage of our Prompt Library to find helpful, creativity-creating prompts.

Internal FAQs

At your discretion, agents are trained on your proprietary data to help users find what they need faster.

Incognito Conversations

Users can select to have incognito conversations with their agents, ensuring conversational data is deleted immediately and not used to further customise their agents.

On The Job Coaching

Agents are trained to leverage their expert material to provide on-the-job professional and personal coaching for their users.

Market Research

Agents have vast knowledge and can assist users in quickly researching and synthesising information.

Assistant

Agents are skilled assistants, offering users a rapid way to complete their administrative work and focus on what matters.

Prompt Library

Every user gets access to our community-driven Prompt Library tailored to their role and responsibilities. Our Prompt Library contains role-specific, best practice prompts to help users get the most out of their agents.
📅 Onboarding #2 begins july 01 2024

Join Our Next Onboarding