Work the way you think.

Your decision loop, enhanced and preserved. AI for research velocity.

IRIS is the operating system for institutional investment research.

What changed? /
IRIS runtime spreadsheet with Research Shell and model context
Runtime / Spreadsheet IRIS Product Surface

Figure 1 The Research Velocity Flywheel The operating model behind IRIS.

Engineering Diagram IRIS Research System
Context to Orientation to Evidence to Continuity to Better Context flywheel
Context

The repository already knows the model, workbook, evidence, research, and history. You start with context instead of rebuilding it.

Orientation

IRIS gets you moving quickly with concise synthesis, minimal controls, and one next action. Less time navigating. More time thinking.

Evidence

Every answer connects directly to supporting evidence. Research is one click away, not another search.

Continuity

Every governed output strengthens the repository. Today's work becomes tomorrow's context.

A Point of View

Ending investment amnesia.

AI answers questions.

IRIS preserves how your organization thinks.

Research compounds.

Institutional knowledge compounds.

Every decision strengthens the next one.

Memory is the multiplier.

Search

Start with the model.

Search is the front door. Open a company, model, question, or research surface without managing files.

IRIS repository search surface for opening models and research surfaces
Search opens the current model and the research surfaces around it.
Analyze

Work in the model.

Keep the familiar grid and familiar formulas, but attach assumptions, outputs, evidence, formulas, and reasoning to the model itself.

The spreadsheet stays familiar. The context becomes durable.

IRIS model screen with spreadsheet and Research Shell panel
Analyze is where model work, assumptions, outputs, and evidence stay in one surface.
Research Shell

Ask the model.

Research Shell is the analyst interface to the repository.

  • Why?
  • What changed?
  • What stands out?
  • Have we believed this before?
  • Remember this.
  • What if margin were 5%?
  • Write the report.

Ask questions. Run research. Test scenarios. Build memory.

Meeting Mode puts IRIS on your phone. You don't need Excel to understand a model. You need the repository.

IRIS Research Shell model value lookup with governed action evidence
Analyst language covers asking, remembering, comparing, testing, and writing from the model.
Report

Turn work into communication.

Reports are emitted from model work. The explanation stays attached to the assumptions, outputs, evidence, and changes that produced it.

IRIS Report surface inside model context
Report turns the model state into communication without detaching it from its evidence.
Timeline

Preserve what changed.

The timeline keeps institutional memory: what changed, when it changed, and why it mattered. Every decision becomes part of the model's history.

IRIS Timeline surface showing model history
Timeline records versions, reports, and memory as the model evolves.
Why it compounds

Learns the Work.

Most software stores information.

IRIS learns from the durable investment work your organization chooses to create.

  • Not by watching clicks.
  • Not by profiling analysts.
  • By learning from governed outputs.
  • Every model.
  • Every report.
  • Every explanation.
  • Every decision.

Every governed model, report, explanation, and decision strengthens the repository's understanding of your investment process.

That understanding compounds.

Operating loop
  1. Great Workspace
  2. Daily Work
  3. Governed Context
  4. Learns the Work
  5. Remembers
  6. Prepares
  7. Finds Things Worth Your Attention
  8. Better Decisions
  9. More Daily Work

Most software gets better when the vendor ships an update.

IRIS improves the more you use it.

The more governed models, reports, explanations, and decisions your organization creates, the better IRIS understands your investment process, prepares future work, preserves institutional knowledge, and helps analysts focus on what matters.

Serious teams

Serious research teams move faster when the model remembers.

Preserve reasoning. Not files.
Test ideas. Not spreadsheet copies.
Explain changes. Not screenshots.
Build memory. Not archaeology.

One repository.

One timeline.

One Research Shell.

One model.

Everything stays connected.