How Iris Works

Understanding the intelligence behind your AI agent

The Agent Loop

At the heart of Iris is an autonomous agent loop that transforms your natural language requests into concrete actions and results. Every interaction follows a structured cycle:

This loop can repeat multiple times within a single request. If the initial results need refinement, or if additional steps are required, Iris will continue iterating until the task is genuinely complete. This is what makes it truly autonomous -- it does not stop at the first answer.

Multi-Model Intelligence

Iris does not rely on a single AI model. Instead, it uses a multi-model intelligence system that routes each task to the most capable model available:

• Deep Reasoning Models -- For complex analysis, detailed research synthesis, and tasks that require careful, nuanced thinking.
• Creative Generation Models -- For writing compelling content, brainstorming ideas, and producing engaging copy.
• Vision Models -- For analyzing images, understanding charts and diagrams, and processing visual information.
• Image Generation Models -- For creating custom visuals, graphics, and design assets on demand.

This flexibility means you always get the best possible output for each part of your workflow. The model selection happens transparently -- you simply describe your task and Iris handles the orchestration.

What Iris Can Do

Iris comes with 20+ integrated tools that give it the ability to produce real-world deliverables, not just text responses:

Information Gathering

• Web Search -- Query search engines and retrieve up-to-date information from across the internet with source citations.
• Browser Automation -- Navigate web pages, read content, and extract data from specific URLs.
• People Search -- Find professional profiles, company details, and background information.

Content Creation

• Document Generation -- Create formatted PDF and DOCX files with professional layouts and rich formatting.
• Presentation Builder -- Generate cinematic slide decks in Iris's proprietary 3DPX format with animations, 3D effects, and dynamic visuals.
• Website Builder -- Create fully responsive web pages from natural language descriptions with live preview.
• Image Generation -- Produce custom images, graphics, and design assets using AI models.

Data & Analysis

• Spreadsheet Analysis -- Process CSV and Excel files, generate charts, and surface insights from your data.
• Vision Analysis -- Analyze images, screenshots, charts, and diagrams to extract information.
• File Processing -- Read and transform PDF, DOCX, and other document formats.

Context & Memory

Iris maintains full conversation context across every message, so you can build on previous interactions without repeating yourself:

• Multi-Turn Conversations -- Reference earlier messages, refine outputs, and chain together complex workflows naturally.
• Output Retention -- Results from previous steps are preserved, so Iris can reference research findings when creating a follow-up document or presentation.
• Conversation History -- Your past conversations are stored and accessible, allowing you to pick up where you left off anytime.

Background Processing

Some tasks -- like intense research across dozens of sources or generating a full presentation deck -- take longer than a quick response. For these, Iris works in the background so you can keep doing other things:

• Asynchronous Execution -- Complex workflows run behind the scenes so the interface stays responsive.
• Real-Time Updates -- As background tasks progress, Iris streams status updates so you can track progress live.
• Reliable Delivery -- Background tasks are processed reliably, ensuring your results are delivered even for the most complex requests.