AI for Google Slides

Converts natural language prompts into complete Google Slides presentations by routing user input through an LLM (identity unknown) that generates slide content, then applies layout templates from a library of hundreds of pre-designed slide types. The system generates both text content and structural decisions (slide order, content distribution) in a single inference pass, then materializes output directly into Google Slides format via the native add-on API, bypassing manual slide creation entirely.

Accepts uploaded documents (format unknown, likely PDF or DOCX) and extracts key content, structure, and themes via document parsing and LLM summarization, then generates a presentation outline and populates slides with extracted/synthesized content. This differs from prompt-based generation by using document structure (headings, sections, paragraphs) as the source of truth rather than free-form text, enabling more coherent multi-slide narratives. Available only on Pro tier and above, suggesting higher computational cost.

Allows Teams/Premium tier users to define custom brand colors, logos, and typography that are automatically applied to all generated presentations. This requires storing brand configuration (color palettes, logo assets, font choices) in a user/team profile, then injecting these styles into the template rendering pipeline during presentation generation. The system likely maintains a brand registry keyed by user/team ID and applies styles at template instantiation time rather than post-processing generated slides.

Allows users to select existing slides in a Google Slides presentation and apply AI-assisted formatting, text refinement, or styling changes without regenerating the entire deck. This likely works by accepting a slide selection, extracting the current content and layout, sending it to an LLM for refinement (grammar, tone, clarity), and writing the updated content back to Google Slides via the add-on API. Differs from generation by operating on existing content rather than creating new slides.

Implements a three-tier subscription model (Basic, Pro, Teams/Premium) that gates prompt length, document upload capability, and brand customization behind increasing price points. The system likely enforces token-window limits at the API level, rejecting or truncating prompts that exceed tier-specific thresholds. This is a business model enforcement mechanism rather than a technical capability, but it directly impacts user experience and feature availability. Basic tier allows 'standard prompts', Pro/Premium allow 'longer prompts', suggesting token-window constraints are tier-dependent.

Implements AI for Google Slides as a native Google Workspace add-on (not a web app or API wrapper), meaning it runs within the Google Slides UI and integrates with Google's add-on API for reading/writing presentation content. This architecture eliminates context switching — users invoke the add-on from within Google Slides, receive generated content, and edit it in-place without leaving the application. The add-on likely uses Google Slides' Apps Script API or REST API to read current presentation state, send content to an inference backend, and write results back to the presentation.

Maintains a library of hundreds of pre-designed slide templates (exact count unknown) covering common presentation types (title slides, content slides, charts, quotes, etc.) and applies these templates to generated content during presentation creation. The system likely uses a template selection algorithm (rule-based or LLM-guided) that chooses appropriate templates based on slide content type and context, then populates the template with generated text and applies formatting. This reduces the need for generative design and ensures consistent, professional output.

Outputs generated presentations directly to Google Drive as native Google Slides files, enabling immediate sharing, collaboration, and version control through Google's native tools. Generated presentations are stored in the user's Google Drive (location unknown — may be root or a dedicated folder) and can be shared with collaborators using Google's standard sharing controls. This leverages Google Drive's built-in collaboration features (real-time editing, comments, version history) without requiring additional infrastructure.

Generates presentation content using an LLM backend whose identity, version, and capabilities are completely undocumented. The system routes user prompts and documents to an inference service (cloud-based, provider unknown) and returns generated text content for slide creation. Without knowing the underlying model (GPT-4, Claude, proprietary, etc.), it's impossible to predict capabilities, hallucination rates, context window limits, or cost structure. This is a critical architectural gap that affects all downstream capabilities.

Restricts access to document uploads, longer prompts, and custom branding behind three subscription tiers (Basic $10-15/mo, Pro $20-25/mo, Teams/Premium $35-40/mo), enforcing these restrictions at the API level. Users hitting feature limits (e.g., prompt length) must manually upgrade to access higher tiers; there is no graceful degradation, in-app upgrade prompting, or trial period to evaluate tier value. The exact feature boundaries are not documented, making it difficult for users to predict which tier they need.