CloudGlance - Document Intelligence Platform

I shaped the structural foundation that would drive the entire platform:

• Projects as the core workspace model
• Files with clear global and project-level scopes
• Tasks and Task Runs as repeatable workflows
• Indexing logic that makes the AI’s awareness visible
• AI Assistant with global and project-focused contexts
• Navigation hierarchy that preserves orientation
• Output flows and a split-view system for verification

Many ideas already existed directionally; my role was to clarify them, connect them, and turn them into a cohesive structure that could scale without fragmenting the experience.

While designing early screens, it became clear that CloudGlance needed a cohesive identity, something stable, mature and enterprise-friendly.

This wasn't part of the original brief; I initiated it because the platform needed a visual language that could carry the weight of document-heavy, high-stakes workflows.

Only after presenting the reasoning did the team align on the need for a new identity.

The earlier logo leaned literal and playful, revolving around a bulky "cloud" visual and green palette. It didn't reflect the seriousness of the workflow nor the enterprise clients they were approaching. The green colour palette also overlapped with the existing competitor landscape, making it harder to establish a distinct, enterprise-grade presence

I suggested creating a new identity system that could:

• communicate maturity and trust
• visually hold the weight of enterprise workflows
• feel timeless, not startup-like
• live consistently across platform, website and future materials

The team welcomed the direction.

I designed a compact symbol built from C + G + a focal point - representing "glance", clarity and attention without being literal.

It reads cleanly at small sizes, aligns with enterprise expectations, and supports a more composed visual language.

I replaced the green palette with a composed, trustworthy blue.

Blue carries the exact qualities the platform needed:

• Stability
• Calm
• Reliability
• Professional maturity

Accents are used sparingly to maintain a calm environment for long work sessions.

Neutral, readable sans-serif.

Structured hierarchy.

Comfortable line spacing.

Nothing decorative, entirely built for clarity and long-form reading.

Calm over clever
No flashy AI theatrics. The interface stays quiet, composed, and focused on the work.

Predictable patterns
Core interaction models repeat across the platform - tabs, headers, panels, and workflows behave consistently, helping users build familiarity as they move between features.

Depth only when needed
Users start with a clear overview and move into deeper layers only when they choose to.

Designed for senior users
Clear labels, comfortable spacing, and no hidden interactions.

Transparency over abstraction
Users can always see what the AI referenced, which files were used, and where answers came from.

Intentional empty states
Guiding, informative, and restrained.

UI gets out of the way
Documents and outputs remain the primary focus.

Built for long work sessions
Soft neutrals, stable spacing, and low visual fatigue.

Navigation that always shows where you are

• Sidebar supports both open and collapsed modes
• Logo doubles as a toggle to reduce header clutter
• During output-heavy views, the sidebar collapses to prioritise horizontal space and reappears as an overlay when needed

This approach helps users stay oriented without interrupting their flow, especially during long or complex review sessions.

CloudGlance was designed around a unified way of framing pages and handling actions, so that the experience remains consistent as users move across different workflows. From the beginning, the platform followed a shared structural logic that defines where context lives, where actions appear, and how work is carried out - instead of treating each screen as an isolated layout.

Every page follows the same foundational logic:

• a clear sense of where you are
• a predictable place for actions and filters
• a focused work area
• supporting panels that appear only when needed
• consistent behaviour around navigation, spacing, and content flow

Actions across the platform follow the same structure.
Starting a task, creating or editing a project, searching, or adjusting settings all use a shared interaction model,keeping actions familiar regardless of where they are triggered and ensuring context is never lost.

By designing pages and actions around the same structural thinking, the platform avoids fragmentation as features grow. New workflows can be added without introducing new patterns, allowing the platform to scale while remaining calm, learnable, and dependable.

Designed to give users orientation without demanding attention.

The dashboard acts as a stable entry point into the platform. Users land here, understand what's active, and move into their work without being distracted by unnecessary noise.

From the dashboard, users can directly start an AI-assisted conversation, giving them an immediate way to ask questions or explore information before committing to a specific workflow.

A small set of high-level indicators, recent items, and a complete activity log provide awareness and traceability without overwhelming the interface. The dashboard is not meant for deep decision-making - it exists to orient, ground, and guide users toward their next action.

Where teams organise, manage, and act on work within a consistent structure.

Projects are the core workspace in the platform. They act as stable containers that hold documents, tasks, activity, and outputs, while adapting to the specific purpose of the work.

Although CloudGlance supports different workflows such as tender bidding and tender evaluation, the overall project structure remains the same. What changes are the available automations and actions within a project, not the way the project is navigated or understood.

This allows the platform to support varied client needs:

• some organisations only bid
• some only evaluate
• others do both

all within a familiar, predictable project framework.

By keeping the project structure consistent and allowing capabilities to vary inside, it reduces cognitive load while remaining flexible as the platform evolves.

This approach allows new project types and automations to be introduced over time without breaking the core project experience or requiring users to relearn the platform.

A high-level snapshot that helps users understand the project before taking action.

The Project Overview acts as the entry point into a project. Its role is to establish context quickly and help users orient themselves before moving into detailed work.

This view surfaces essential project information such as core metadata, current status, and recent activity, giving users a clear understanding of what the project represents and where it stands.

Available tasks and automations are visible directly from the overview, allowing users to move into action without navigating through multiple layers. The overview reflects the specific context of the project, surfacing only the information and actions relevant to that workflow.

Rather than acting as a reporting dashboard, the overview is designed to help users settle into the project - providing clarity, direction, and a clear sense of what can be done next.

All documents live within a single system, accessed through different contexts.

The platform uses a unified file system that supports both organisation-wide document management and project-specific work without fragmenting where files live or how they are handled.

Users can access the full file manager directly from the platform to browse, organise, and manage documents across the organisation. Within a project, the same system is presented in a focused way, showing only the files relevant to that project and keeping users anchored to their current context.

The file system is structured around three primary areas:

• Templates, used for standardised files required by specific tasks
• Projects, where each project has its own dedicated folder that acts as the root for all project-specific documents
• Resources, used for shared organisational files

This structure ensures clarity and control. When working inside a project, users remain within that project's scope and cannot accidentally move out of context, reinforcing trust and predictability in document-heavy workflows.

Across both entry points, users can browse folders, upload files, organise content, view documents, and manage file details - all within a consistent experience that supports long review sessions and careful verification.

AI-powered workflows designed for repeatable, document-heavy tasks.

Tasks represent how CloudGlance applies its document intelligence within a project. Rather than exposing AI as an abstract capability, the platform packages intelligence into structured workflows that teams can run with confidence.

Tasks are intentionally project-bound. Only the AI workflows relevant to a project's context are visible, keeping the workspace focused and preventing unnecessary complexity.

Each execution of a task is recorded as a Task Run, preserving a clear history of what was processed, when it was run, and what outputs were generated. This supports verification, auditing, and iteration, especially in workflows where the same task may need to be run multiple times as documents evolve.

By fitting AI tasks into the platform's shared structure, these workflows allows new intelligence capabilities to be introduced without changing how users interact with them. The behaviour remains familiar, even as the underlying AI grows more powerful.

A predictable way to initiate AI-powered work without breaking context.

Starting a task in the platform follows a consistent, modal-based workflow designed to keep users focused on their current context.

Rather than navigating away to separate screens, task initiation happens within a contained flow that guides users through a clear, repeatable sequence - selecting the task type, reviewing inputs, and confirming execution.

The workflow adapts to where the action is initiated:

• when starting from a project, the context is already set
• when starting from higher-level surfaces, the necessary context is requested upfront

This keeps actions fast for frequent users while remaining clear for those performing them less often.

By keeping task initiation consistent across the platform, the structure ensures that starting AI workflows feels familiar regardless of where users begin - reinforcing confidence, reducing friction, and supporting scale as new tasks are introduced.

A structured space designed for understanding, navigation, and verification.

Task outputs are where CloudGlance's intelligence is reviewed and acted upon. This space is designed to help users move confidently from AI-generated results to informed decisions, without losing context or trust.

The output experience is intentionally organised into clear functional areas. Users are first grounded in the context of the task: what was run, when it was executed, which files were involved, and how the output is structured. This helps users orient themselves before engaging with the results.

The primary output occupies the main work area, where extracted information, answers, or comparisons are presented in a readable, focused format. This is where users spend most of their time understanding what the AI has produced.

For verification, users can reference the original source material alongside the output. Relevant documents and highlighted citations allow any result to be traced back to its origin, making it easy to inspect evidence without breaking the flow of review.

By separating context, results, and sources into distinct but connected areas, the platform supports both quick understanding and deeper verification within the same workspace. This structure keeps AI outputs transparent, navigable, and dependable, especially in workflows where accuracy and accountability matter.

A conversational layer that adapts to user intent across the platform.

The AI Assistant in CloudGlance acts as a flexible, conversational layer that users can access from anywhere in the platform. Rather than being tied to a single screen or workflow, it responds based on the context the user provides.

Users can start a conversation directly from the dashboard or create a new chat from the sidebar. While asking questions, they can guide the assistant's focus by:

attaching external files for ad-hoc queries

focusing the conversation on a specific project

enabling web search when broader information is needed

When a project is in focus, the assistant draws from that project's files, task runs, and outputs to provide grounded, relevant answers. Without an explicit focus, it works across the broader platform context to surface helpful information.

This approach allows the assistant to remain lightweight and supportive, useful for exploration, clarification, and quick checks, while more structured or repeatable work continues to live inside tasks.

By keeping the assistant context-aware, the experience ensures that conversational AI feels integrated into the platform, not separate from it.

A transparent record of who did what, and when.

Within each project, People & Activity provides a clear view of participation and change over time. It brings together roles, actions, and system events into a single, readable timeline.

Activity logs capture key moments: task runs, file changes, updates, and interactions, helping teams understand how a project has evolved and making it easier to trace decisions back to their source.

By keeping this information accessible and structured, CloudGlance supports accountability and confidence in collaborative, document-heavy workflows where clarity and traceability are essential.

Simple, trustworthy entry points for a platform handling sensitive data.

Login and signup are designed to feel calm, familiar, and unobtrusive. These screens establish trust from the first interaction by keeping layouts minimal, language clear, and actions straightforward.

Nothing here competes for attention. The focus is simply on getting users into the platform with confidence, reinforcing the same principles of clarity and restraint that guide the core product experience.

To stabilise the platform, I formalised it around a UnifiedLayout - a single, composable page structure that every screen inherits from.

Instead of treating pages as independent layouts, the platform is built from a fixed set of structural regions, each with a strict responsibility. Pages do not decide layout. They declare intent and assemble themselves using predefined parts.

Once UnifiedLayout was enforced in the frontend codebase, page creation shifted from designing layouts to assembling intent.

New screens no longer defined their own structure. Instead, they composed themselves from existing regions: header, action bar, panes, and content, following the same rules every other page used. This removed layout-level decision-making from individual features and made consistency the default.

As a result:

new pages could be introduced without rethinking layout

complex workflows were built by combining existing panes rather than inventing new patterns

layout behaviour could be updated centrally, without touching every screen

The platform stopped behaving like a collection of screens and began operating as a system of composable surfaces.

The same system thinking was applied to actions through a UnifiedModal - a single structural model used for all action-based interactions.

Instead of treating modals as one-off UI flows, every action in the platform is built from the same internal structure. The modal handles layout, behaviour, and state. Individual actions only provide content and intent.

To prevent further drift, I restructured the frontend codebase myself, mirroring the same discipline used in design and removing layout and action logic from individual screens.

Pages declare intent.
Shared systems handle structure and behaviour.

This reduced duplication, simplified maintenance, and ensured that consistency was enforced by the system itself rather than relying on manual oversight.

Mobile support was introduced to ensure that active users were not limited to desktop access and could continue using the same platform on smaller screens when needed.

Rather than designing a separate mobile experience, the existing layout and action systems were adapted to fit reduced screen space while preserving behaviour and intent. Structural regions respond based on context:

• left and right panes transition into contextual sheets that slide in from their respective sides
• action-based modals adapt into swipable bottom sheets
• the header, center pane, and footer remain the primary visible surface, maintaining orientation and continuity

This approach ensured that users encountered the same mental model across devices. Actions behaved the same way, content appeared in familiar places, and workflows remained understandable without relearning the interface.

Mobile access became an extension of the system, not a parallel design, allowing users to stay connected and productive without being confined to their desktops.