Skip to main contentSkip to footer
Tabbi.
HomeServicesMethodologyCase StudiesKnowledgeAbout
Get in Touch
Tabbi.

Precision qualitative analytics powered by rigorous AI methodologies. Enterprise-grade insights for research leaders.

Navigation

  • Home
  • Services
  • Case Studies
  • About

Capabilities

  • Thematic Analysis
  • Decision Network Mapping
  • Causal Inference
  • Generative Reporting

Contact

  • [email protected]
  • LinkedIn

© 2026 Tabbi Research. All rights reserved.

PrivacyTerms

Our Methodology

The GATOS Workflow

Generative AI-enabled Theme Organization and Structuring—a peer-reviewed methodology for AI-assisted thematic analysis with full traceability.

Every insight traces back to source data. No hallucination. No black boxes.

Read the PaperSee It In Action

The Problem

Why Most AI Analysis Tools Can't Be Trusted

Black Box Analysis

Most AI tools generate "insights" without showing how they reached them. You can't verify whether conclusions are grounded in your data or invented by the model.

AI Hallucination

Large language models can confidently generate plausible-sounding insights that aren't actually in your data. Without traceability, you can't tell the difference.

Unverifiable Claims

When an AI tool tells you "67% of customers mentioned X," can you verify that number? Can you see the actual customer statements that contributed to it?

Lost Context

Summarization-based approaches lose the nuance of individual voices. Themes become abstractions disconnected from the people who expressed them.

The Solution

Extract-Based Traceability

GATOS maintains a chain of custody from source data to final themes. Every insight can be traced back to specific participant utterances.

Raw Utterances

Original participant feedback

Extracts

Discrete summary points

Clusters

Semantic groupings

Codebook

Grounded codes

Themes

Traceable insights

The Key Innovation

Every theme can be traced back through codes → clusters → extracts → original utterances. You can verify exactly which participant voices contributed to each insight.

Interactive Traceability Chain

Explore how insights connect back to source data

Click any step to trace insights back to source data

Theme
Workflow Friction Drives Frustration
High-level pattern identified across multiple codes

Key: Every theme traces back through codes, clusters, and extracts to specific participant utterances—no hallucination possible.

Deep Dive

How Each Step Works

1

Extract Creation

Raw participant utterances are distilled into discrete summary points—each capturing a single idea in the participant's own framing.

// Raw utterance:

"I waited forever in the ER and nobody told me what was happening. The nurse was nice though."

// Extracts:

→ "Long wait time in emergency department"

→ "Lack of communication during wait"

→ "Positive interaction with nursing staff"

2

Semantic Clustering

Extracts are embedded into vector space and clustered using PCA, UMAP, and agglomerative clustering. Similar ideas from different participants converge naturally.

This step reveals natural groupings in the data without imposing predefined categories. Patterns emerge from the participants' own language.

3

Constrained Codebook Development

Codes are generated through nearest-neighbor retrieval, ensuring new codes are grounded in existing patterns. The model cannot invent categories not supported by the data.

Safeguards:

  • • Temperature = 0 for determinism
  • • Must read nearest neighbors first
  • • Explicit anti-hallucination instructions

Quality criteria:

  • • Parsimony (minimal redundancy)
  • • Consistent abstraction level
  • • Non-overlapping categories
4

Theme Synthesis with Full Traceability

Codes are organized into themes, with every connection preserved. Ask about any theme and trace it back to the specific participant utterances that contributed to it.

Theme: "Communication Gaps During Care"

↓

Code: "Uncertainty about wait status"

↓

Cluster: 847 extracts about waiting + communication

↓

Sample extracts: "No updates during wait", "Didn't know if forgotten"...

↓

Source utterances: [Patient 142, Patient 891, ...]

Published Research

Peer-Reviewed & Validated

The GATOS methodology is documented in peer-reviewed research

GATOS Methodology Paper

Thematic Analysis with Open-Source Generative AI and Machine Learning: A Worked Example

arXiv:2410.03721 →

Validation Study

Evaluating GATOS Workflow on Complex Qualitative Data

EDM 2025 →

See It In Action

Ready to Experience Traceable AI Analysis?

Explore our case studies to see how GATOS delivers trustworthy insights across industries.

View Case StudiesGet in Touch