Live · updated as the evidence changes
Live build record
Building Yu in public.
Yu stores how you work, so your AI can work the way you do.
Yu is under active development and validation. This page changes as the evidence changes.
While I was building Yu with AI, I started using AI to catalog the build itself. This page is the public view of that record: what changed, what the evidence says, what I am testing, and what comes next.
Last updated
Sept 23, 2026
Current build focus
V4.5 is live. The assistant is usable from the beginning and helps the person build Yu, with 365 progression, Context Coins, the Store, and AI learning adding depth on top rather than gating basic usefulness.
Active research question
Does putting a working assistant first, from the first minute, make the value clear enough that people actually use Yu while it builds underneath them?
Current build
V4.5 · LIVEAssistant first. Yu builds underneath.
V4 launched publicly and produced the key learning. V4.5 is the immediate response, and it is live now. V4 proved the pieces could work together. The launch showed the next problem: people liked the education, were beginning to understand the personalization, and said the product looked great, but they still did not always understand what to do with it. The clearest signal was absurdly simple: people did not know where their text was supposed to go. V4.5 makes chat the obvious front door. The assistant is useful immediately; Yu gets deeper underneath it over time.
V4.5 is the live current version, not a future roadmap item. The product will keep evolving, and if a larger chat-first architecture eventually earns a new version number, that larger rebuild may become V5; for now that is only future uncertainty.
Current direction
Working shape, not lockedV4.5 assistant-first pivot
The V4 sprint made the pieces one system. The V4.5 pivot changes which piece the person meets first.
452+
recorded build edits since Aug 31
Implementation activity during the V4 integration sprint. It measures how much was built, not product-market traction and not company or strategy changes.
150
in the final ~28 hours
21
first-build activities connected in V4, now folded into 365 progression
V4.5
current build direction
Stated as a direction under test, not a validated result.
Sprint objective
Give a person a working assistant immediately, and make building Yu something they do with that assistant rather than something they finish before they get one.
Current result
Live now. The assistant-first structure is the current release and the current hypothesis; it has not been validated yet.
Build edits are implementation activity. They are separate from the documented company/product/strategy state changes counted below, and the two should not be read as the same thing.
125 days of moving the bottleneck
Yu has developed by repeatedly finding the uncertainty that prevents the next important question from being answered.
Working TRL values are a dated internal working assessment, not an external certification. No outside body awarded them.
- V1
Manual Yu
Working TRL 2 → 3Question
Can we actually do cognitive translation?
What existed
Paisley + Danny were effectively the system. They used a framework generator, ran the conversations, interpreted what came back, built their own system instructions, and created individualized scaffolding for other people.
What this established: Enough manual proof of mechanism to justify productizing it.
- V2
Make the idea legible
Working TRL ~3TRL barely moved, and this stage still mattered.
Question
Can people understand what Yu is and why it matters?
What existed
The marketing site, positioning work, explanation of the six applied areas, and the language and visual system for explaining Yu.
What this established: Explaining the mechanism and value was itself a product problem.
- V3
First framework MVP
Working TRL 4 → 5Intended question
Does the methodology work when users go through Yu themselves?
What happened instead: People were not reliably getting far enough through the experience to answer that question properly.
What blocked the question
Perceived chore
Response: Gamification, progression, city, rewards, visible accumulation.
Value / concepts not landing
Response: AI 101, clearer conceptual scaffolding, stronger explanation of why the work matters.
Key interpretation: The methodology test was blocked by an upstream comprehension and motivation problem. That blocker became the new critical path.
- V4
Integration sprint
Working TRL 5 → 6Working estimate.
Sprint objective
Can we remove the upstream comprehension, motivation, progression, and integration blockers so the methodology can actually be tested?
What this established: Onboarding, profile/reflection, the 21-step first build, progression, AI 101, the city, weekly delivery, AI handoff, and assistant arrival operated as one end-to-end system rather than separate product pieces. At that point the plan was beta testing the following week, and the product was publicly described as launching.
Two parallel tracks
Experience track
Understand the value → want to start → stay engaged → reach the frameworks.
Method track
Strengthen the underlying methodology through research and expert and psychologist review, so what people reach is defensible.
What V4 assumed
That the assistant should arrive after the 21-step build, as the thing the person earns.
- V4.5Current turning point
Assistant first (current direction)
Working TRL 6Working estimate. This stage is in build, not validated.
Current question
If a person has a working assistant from the first minute, does the value land clearly enough that they keep using Yu while it builds underneath them?
What happened instead: The launch happened, quietly, in September 2026 after being publicly described as coming. The founder's own read afterwards was that the product was roughly 70% there: a founder assessment, not a measured completion score. This was not a story of the launch failing. Feedback was improving. People explicitly said the educational hook was resonating, the personalization idea was beginning to make sense, and the product looked great. What their behavior showed was different: people could admire the product and understand pieces of it without understanding what they were supposed to do with it.
What blocked the question
The product was not fully landing
Response: People could see the pieces, self-awareness work, AI education, personalization, the robot, the city, without consistently seeing what the product was or what it did for them today.
People did not know where to type
Response: The clearest symptom, almost absurd in hindsight: people repeatedly did not understand where the text or input was supposed to go. The product was asking users to understand an architecture before giving them the most familiar AI interaction model there is.
Key interpretation: A product conversation on Sept 21, 2026 connected those pieces into one read: it needs to be chat. The assistant should be the obvious surface, and Yu should build underneath the conversation rather than requiring the user to understand Yu before they can use the assistant. Both V4 and this pivot are big. V4 proved the integrated world could exist; V4.5 changes the entry model around the assistant. If the implementation becomes a substantial chat-first rebuild, it may ultimately land as V5 rather than being treated as a small patch. Parts of V4 may be abandoned in the process, and that is not wasted work: V4 exposed the next constraint.
Build-in-public lesson: Always be testing something, but do not let the test freeze the product around the thing you are testing. A test is there to remove uncertainty, not to become a constraint you protect after the evidence changes. Build enough to learn, and keep moving when the critical path moves.
Two parallel tracks
Assistant first
A working assistant, Geo, from the first session.
Yu underneath
The private context the assistant works from, built from what the person approves.
365 progression
Unlocks depth over time. It does not gate basic usefulness.
Context Coins
Spendable rewards for the work a person does.
Store
Where Coins are spent.
University and AI learning
Learning how to use AI well, alongside the build.
User control
The person approves, edits, and can remove what Yu holds.
What this still has to prove
That assistant-first makes the value clearer and keeps people using Yu. It is the current hypothesis, not a validated result.
Working readiness assessment
Assessed Sept 9, 2026
A dated internal working assessment from the Yu journey-map evidence review. These are not external certifications and no outside body awarded them.
Technology Readiness Level
Working assessmentTRL 6
Technology demonstrated in a relevant environment.
1
2
3
4
5
6
7
8
9
The assessment placed Yu at TRL 6 because the full pipeline runs end to end against real external users on a production-shaped stack. It deliberately did not award TRL 7, because the system was not yet at or near operational scale in the target environment.
Caution: The missing held-out accuracy test is the biggest technical uncertainty that could change this assessment.
Innovation Readiness Level
Working assessmentIRL 4
Prototype a low-fidelity minimum viable product.
1
2
3
4
5
6
7
8
9
The assessment placed Yu at IRL 4 because user activation and willingness-to-pay evidence were still early while Yu is free to use. That is the current evidence boundary and the next thing the company is designed to learn.
2-level readiness gap
Product build has advanced faster than paid-market evidence. The next experiments are designed to close the evidence gap.
What moves the levels?
TRL: Held-out accuracy and predictive-validity evidence, plus an operational-scale environment.
IRL: Paid use, activation, retention, and willingness-to-pay evidence.
These are evidence thresholds, not promises.
The build record and the active experiment
102
documented company/product/strategy changes
Business and product evolution. Compiled through Sept 9, 2026.
4
true reversals
Compiled through Sept 9, 2026.
The meaning matters more than the number: most changes narrowed and refined the model rather than replacing it. These are company/product/strategy state changes, separate from the build-edit count in the current sprint above.
Active experiment
Does an assistant-first experience make the value clearer, and does it get people using the product while Yu builds underneath them?
Next test
Put people into the assistant-first experience and watch whether the value lands without explanation: do they use the assistant, keep returning, and approve context into Yu without the progression having to carry them.
Evidence board
Backed by current architecture, implementation, or established external research.
Person-specific context can matter to AI personalization.
Yu has a working behavior-informed assessment and translation pipeline.
The product preserves source and provenance, and the person can correct what it holds.
An active Yu hypothesis.
Behaviorally derived instructions reduce correction burden compared with generic AI or self-written custom instructions.
Translated directives transfer better across tasks.
Conditional instructions reduce misfires.
An important open question.
Which framework categories add the most incremental value.
How stable different findings are over time.
How well the benefits transfer across model providers.
SUPPORTED means supported by the current source architecture, implementation, or established external research. It is not the same as Yu being scientifically validated. The six areas (Memory, Processing, Communication, Values, Personality, Motivation) are Yu's applied taxonomy, not a validated model of the brain.
Build log
Latest meaningful changes
Sept 22, 2026
V4.5 assistant-first pivot
The assistant is now the product from the first minute and helps the person build Yu, with 365 progression, Context Coins, the Store, and AI learning adding depth instead of gating baseline usefulness. Geo is the single canonical starter assistant, replacing the nine-model roster in the active product. This is the current hypothesis and it has not been validated. If the implementation becomes a substantial chat-first rebuild, the result may ultimately be V5 rather than a patch.
Sept 21, 2026
Post-launch read and the crystallizing conversation
After the quiet launch, the founder's own read was that the product was roughly 70% there. People explicitly said the education resonated, the personalization was starting to make sense, and it looked great, yet their behavior showed they still did not understand the interaction model, including where their input was supposed to go. A product conversation on Sept 21 connected that evidence into one read: it needs to be chat, with the assistant as the surface and Yu building underneath. V4 was not wasted work; it proved the integrated world could exist and exposed the next constraint.
Sept 9, 2026
V4 integration sprint
Onboarding, profile/reflection, the 21-step first build, progression, AI 101, the city, weekly delivery, AI handoff, and assistant arrival ran as one end-to-end system rather than separate product pieces. At that point beta testing was planned for the following week.
Sept 2026
City simplification
The cognitive city was simplified so every place has one clear job and the map reads at a glance.
Sept 2026
Conditional instruction and misfire design
Instructions gained conditions: they know when they apply and stay quiet when they do not.
Sept 2026
Public methodology and taxonomy research scaffold
The working paper and this build record opened the method up to outside scrutiny.
Detailed chronology
Apr 21, 2026
The first documented precursor question
Should knowing how I think change how AI works with me?
May 11, 2026
First technical architecture
Jun 3, 2026
Mirror identified
A missing functional step between inference and instruction.
Jul 3, 2026
Raw-source and provenance architecture formalized
Aug 2026
Framework library expanded and sequenced
The methodology grew into an ordered library.
Sept 2026
Working product and research scaffold
Conditional instructions and misfire architecture, the cognitive city, and a formal research scaffold.
Sept 9, 2026
First 21-step path connected end to end
Onboarding through assistant arrival ran as one system. At the time, beta testing was planned for the following week.
Sept 2026
Quiet launch
The product had been publicly described as launching. It launched quietly. The founder's own read afterwards was that it was roughly 70% there. Feedback was improving: the educational hook resonated, personalization was beginning to make sense, and people consistently said it looked great. But behavior showed the product itself was not fully landing.
Sept 21, 2026
A product conversation connected the pieces
People could admire the product and understand its pieces without knowing what to do with it. The clearest symptom: they repeatedly did not understand where the text or input was supposed to go. The founder's read from that evidence was simple and large: it needs to be chat.
Sept 22, 2026
V4.5 assistant-first pivot
The assistant became the obvious surface from the beginning, with Yu building underneath the conversation. Current build direction, not a validated result. If the rebuild becomes a substantial chat-first architecture, it may land as V5.
The methodology paper
Cognitive Translation for Personalized AI
A Taxonomy and Methodology for Modeling Person-Specific Context
Working paper · under active validation