Open research · SP Jain EMBA · Applied Research Project

AI systems see everything. They understand almost nothing.

Netflix processes 500 billion events per day and still cannot tell why a viewer abandoned an episode. YouTube detects that you watched three political videos and floods your feed for weeks — because it reads behaviour without reading state. Spotify maps your mood from two billion listening sessions and adjusts in real time. Three platforms. Three different layers. One framework to explain the difference.

Take the practitioner survey
Let us know you are interested.
We will follow up to schedule. In the meantime, the survey takes five minutes and contributes directly to the same research.
Survey responses
Interviews done
9
Project day of 27
53
References mapped
The business challenge

The data is there. The interpretation is not.

Three structural reasons explain why this gap persists. Actions are easy to measure. Internal states are not. The research that could help is scattered across fields that do not talk to each other. And business incentives favour optimisation over understanding.

Forrester found that 73% of companies struggle to use behavioural data for anything beyond basic segmentation. McKinsey found that companies excelling at personalisation generate 40% more revenue than average. The distance between those two numbers is the gap this framework addresses.

Read the full paper
500B
events per day at Netflix. The system logs the pause. It cannot tell confusion from careful thinking.
73%
of companies cannot use behavioural data beyond basic segmentation. Forrester, 2022.
40%
more revenue for companies that personalise well. McKinsey, 2021. Most do not get close.
78–84%
Clickstream patterns predict student dropout this accurately. The signals exist. Most systems do not use them.
The ABSD framework

Four layers from action to motivation.

Most AI systems operate at Layer 1. A few reach Layer 2. Almost none attempt Layer 3 or 4. The framework gives you a map of where you are, and what moving one layer deeper looks like.

Layer 01
Action
What the user does. Clicks, submissions, navigation, session duration. What most AI systems capture today with high fidelity.
Click · Submit · Navigate · Timestamp
Layer 02
Behaviour
How the user does it. Patterns across actions over time. Hesitation, retries, navigation strategies, help-seeking tendencies.
Hesitation · Thrashing · Regression · Flow
Layer 03
State
What the user feels. Confusion, confidence, frustration, curiosity. Not directly observable. Inferred from behavioural patterns.
Confusion · Flow · Frustration · Confidence
Layer 04
Drive
Why the user does it. The underlying psychological needs. Competence, autonomy, relatedness. Stable over time, shaping every response to challenge.
Competence · Autonomy · Relatedness
Trace a signal → Explore the framework
Three ways to read the same paper

Built for the taxi, the desk, or the projector.

Get involved

Open research. You can take part.

This work needs practitioner input. If you build AI products in customer experience, education, or anywhere AI meets users, your perspective sharpens the framework. The survey takes five minutes. The interview takes twenty.

Live project roadmap

19 May to 14 June 2026. Four weeks.

Activities run in parallel. This bar moves with today's date.

Day 9 of 27
Phase 01
19–23 May
Lock the instruments
Finalise the framework, interview protocol, and survey. Outreach to 10 to 12 interview candidates.
Phase 02
24–30 May
Interviews and survey live
Five expert interviews, roughly one per day. Survey deployed and accepting responses.
Phase 03
26 May–3 Jun
Case analysis
Two AI systems analysed through the ABSD lens using public documentation.
Phase 04
1–8 Jun
Coding and synthesis
Thematic analysis. Cross-method refinement of the framework.
Phase 05
6–14 Jun
Draft, review, submit
Mentor review cycles. Final revisions. Submission 14 June 2026.
Contributors
Practitioners who have shaped this research.
See all →

For when the conversation goes deeper.

Everything on predictwhy.com

Framework
ABSD Framework Four Traditions Signal Library Case Studies Compare
Knowledge
Knowledge Map References Glossary
Domains
Customer Experience Educational Technology
Participate
Survey Voice Interview Get Involved Contributors
Live
Findings Research Log
About
About Press What's Next FAQ How to Cite Ethics Contact