aftrveiltruth is fractalJoin the beta
in beta · spring 2026

Find the cause,not just the symptom.

An AI that shows its work. Line by line, source by source, so you can check every step and decide for yourself what to do next.

Join the betaHow it works
I.What it does, in three sentences

A reasoning engine, not a chatbot. Built for the questions where surface answers fail.

Medical mysteries, institutional behavior, environmental signals. Boaz investigates questions that require more than retrieval -- they require reasoning about what is missing, what is contradictory, and what would change if it were wrong.

01

Traces the cause

Follows evidence chains from symptom to source. Every link is cited, every inference is flagged.

02

Checks for distortion

Looks for the ways evidence can mislead: selection bias, confounders, missing data, motivated reasoning.

03

Maps what is missing

Identifies the evidence that does not exist yet -- and tells you what would change the answer if it did.

II.How it works, briefly

Six steps. Each one is a deterministic operation you can replay.

STEP 1
Read
Understand the question -- its words, its structure, what is actually being asked.
STEP 2
Translate
Restate the question in a precise internal form so nothing is lost or fudged.
STEP 3
Look for patterns
Search for both honest signal and signs of distortion in the available evidence.
STEP 4
Compose
Build candidate explanations from the patterns, ranking by evidence strength.
STEP 5
Reason
Test each candidate against what would need to be true, and what would disprove it.
STEP 6
Explain
Return the surviving candidates with sources, confidence, and what to check next.
Worked example
Worked examplesample trace
The question

Why does my joint pain return, almost without fail, on Tuesdays?

How to check which one is true

Move whatever you do on Mondays by two days. If the pain shifts to Thursday, it is candidate #1.

III.What we believe, out loud

What we will always do

  1. Plain language first. Jargon is a last resort.
  2. Show the work. Every claim has a way to check it.
  3. Short sentences for the scary parts. Long sentences for the careful parts.
  4. Name the limit before someone asks.
  5. Never sell. State, and let the work pull.

What we believe, out loud

  • We believe environmental exposures are under-studied.
  • We believe patient testimony is evidence, not anecdote.
  • We believe institutional inertia causes real harm.
  • We believe falsifiability is the price of admission.
The one rule

If we cannot show the path to a sentence, we do not write the sentence.

Founder
Kate Ayelet Benediktsson
ORCID 0009-0002-4216-6351

Independent researcher working at the intersection of AI philosophy, medical epistemology, and computational reasoning. Published in neuro-symbolic AI and phenomenological methods for contested diagnoses.

IV.Publications

The work so far

Published research, datasets, and manuscripts in preparation. Every claim is sourced. Every method is documented.

Manuscripts
2026
Chronic Dermopathy with Anomalous Material Properties in a Familial Cluster: An 8-Year Case Study
Preprint · In submission
2026
Phenomenological Translation: Bridging Lived Experience and Clinical Evidence in 161 Morgellons Cases
Preprint · In submission
2026
Layer 0: A Meta-Epistemic Framework
Working paper · Forthcoming
Beta · Spring 2026

Join the beta.
Run a question through Boaz.

Limited cohort. Bring a real question -- medical, institutional, environmental, historical -- and a willingness to read the trace.

We read every application. No marketing list. No reselling.