Authentic Ignorance

Building State with AI

I built State to find out whether a project's current understanding could stay trustworthy as new information kept arriving, instead of being reconstructed from history every time someone needed it. Building it showed me how much control a product actually needs around AI interpretation.

My role Product owner, UX direction, evaluation & final decisionsAI collaborator Product, design, engineering & QA supportStatus AI-integrated product
The problem

Project history could be saved. Current understanding still had to be maintained.

Working with AI let me move through projects much faster, but it also created more context than I could reliably carry from one chat to the next. I started exploring whether AI could help maintain that current understanding instead of forcing me to reconstruct it each time.

I compared raw history, stronger reconstruction instructions, and a maintained summary. The maintained approach worked best, but an early failure exposed a deeper problem: preserving the conclusion wasn't enough if the source evidence and decisions that made it trustworthy were lost. That shifted the project from reconstructing context to deciding which parts of maintaining it should belong to AI at all.

What changed for me

The problem was no longer just preserving context.

I realized I didn't want important project truth to depend on what an AI remembered or reconstructed at all.

Looking at how AI teams handle context, I found the same underlying problem: finding information is one thing; knowing what should still be treated as current is another.

I needed an external record that kept new evidence separate from what a person had actually accepted as the project's current understanding.

I kept going because I wanted to understand a harder question: where should AI help, where should software enforce the rules, and where should people stay in control?

What I built

State maintains a current, trustworthy, human-approved understanding of a project as new information arrives.

The core loop is simple:

Something happensEvidenceAI interpretsHuman decidesState records the outcome

New Evidence is interpreted into a Review, and a person decides whether Current State should change. A Review can instead leave Current State unchanged or keep an unresolved Question visible. The rest of State supports that same boundary between what came in and what the project has actually accepted.

NotesWhat came in

Meeting notes and other approved sources are preserved as evidence.

Current StateWhat the team relies on now

What the project currently treats as true. New evidence only becomes Current State after a person authorizes it.

ReviewWhat may need to change

AI proposes what new evidence means. A person decides whether Current State should change.

Open ItemsWhat still needs attention

Reviews, blockers, and open questions stay visible without being mistaken for facts.

HistoryHow the understanding changed

Accepted changes preserve what changed and why.

AskHow the context gets used

Answers keep accepted facts separate from pending or unresolved information.

A good answer is not enough if you lose the evidence behind it.

State keeps the evidence, AI interpretation, human decision, and resulting change traceable.

Only approved Slack channels are evaluated automatically into Evidence. Other Evidence is added manually.

The key product decisions

AI can interpret what changed. It cannot decide what becomes true.

I expected a product like this to lean on the model for more of the work. Instead, AI was useful for interpreting messy evidence while software was better at enforcing rules. Consequential changes still needed a person's sign-off. Knowing where not to use AI became as important as deciding where to use it.

Authority stays outside the modelThe authority model

AI can propose changes to Current State, but only a person can authorize them. Future agents could investigate questions or gather evidence, but the maintained truth would stay behind that same boundary.

AI interpretssoftware enforcespeople authorize
Valid output can still be wrongUnknown became 0%

Early on, the model turned an unresolved automation target into a confident 0%. It fit the schema perfectly but stated a decision the project had never made. That failure made the distinction between technically valid output and trustworthy product behavior concrete.

Review workloadHuman review can become its own failure mode

State first filters for consequential changes, then separates only the decisions that need independent judgment. Otherwise human review can become more work without adding more control.

Lingering Questions

Building State was a genuinely useful learning exercise. If State were used by a real team, a few questions would still be open.

Review burdenHow does review burden scale?

State now filters for consequential changes and groups them into decision-sized Reviews. Real use by a larger team would still be needed to know whether that workload stays manageable.

Source completenessDoes State have enough of the project to stay trustworthy?

Whether the sources I approved capture the decisions and corrections someone would actually go looking for later.

The obvious pushbackWhy not just use a Claude Project?

A Claude Project could probably handle my immediate personal need by keeping the source material and instructions together. I kept going because State let me explore the harder product problem: how to maintain an explicit current understanding when new evidence arrives, while keeping the decision about what becomes authoritative outside the model.

Where I landed

State is most useful when a team needs more than a plausible summary.

It fits best when project context changes often and earlier decisions may need to be revised without losing track of what currently counts as true. State also changed how I think about AI products. I started out assuming I'd use AI in more of the system and came away believing that using it well often means restraint. AI can interpret change, but people decide what becomes true.

Explore State