An AI lab that publishes its denominators.

OptiVis AI Labs is the product and research arm of OptiVis, an AI engineering firm in Sugar Land, Texas. Every figure here is a recorded run, shown with its count, its window and its source.

Readings4 readings, 3 recorded
  1. Recorded

    Agreement between a distilled student classifier and Jev, the judge it was trained from

    89.0%
    student, in-KBn = 4,387 passages
    80.0%
    student, unseen KBn = 1,301 passages
    52.1%
    zero-shot Laya, in-KBn = 4,387 passages
    49.3%
    zero-shot Laya, unseen KBn = 1,301 passages
    • Trained on 68,828 deduplicated, decontaminated passages labelled by Jev; evaluated on 4,387 in-KB and 1,301 unseen-KB passages.
    • Source: internal run, 2026-10-05
    • Protocol v1.0
    • How the deck was graded

    Agreement with the teacher judge, not accuracy against ground truth. Run receipts are not yet published. Each figure is the mean agreement over 16 of the judge's questions. Jev is the judge model OptiVis runs on its own copy and decisions. The student is a small classifier trained on Jev's labels; Laya is the local decision model it is compared against, with no training on those labels. In-KB labels come from knowledge bases the student saw in training; unseen-KB labels come from knowledge bases it did not.

  2. Recorded

    Share of sessions that completed checkout, by referral source, at one auto-parts store

    12.6%
    ChatGPT, 19 of 151 sessions
    1.9%
    Google search, 76 of 3,988 sessions
    • Window: July 1 to September 30, 2026
    • Source: Shopify attribution, queried 2026-10-04
    • Read the study

    Attribution, not proof that ChatGPT caused the sales. One store, one quarter, small numbers. 19 orders is few enough that a handful either way would move the ChatGPT rate a lot. The store agreed to publication and is not named.

  3. Recorded

    Product pages whose surfaces state different prices, in a frozen panel of 40 public Shopify pages

    22 of 37
    flagged by our reader
    2 of 37
    true disagreements after review
    • n = 40 pages, 37 with a price on at least two surfaces
    • Source: Fact Split, one fetch per page, 2026-10-07 UTC
    • Protocol v1.0
    • Read issue 0

    One reviewer, not independent. A disagreement does not mean a store loses sales. A hand-picked panel of well-known stores, not a sample of Shopify. Most flags were false alarms from the reader's own price and stock rules, and both counts are published. No store is named.

  4. Counted

    This build, counted from the repository

    7
    free tools
    335 of 335
    unit tests passing at build

    Counts, not telemetry. The tools are counted from the site's own registry and the tests from the run that gated this build. Nothing on this page updates live, and no visitor or customer numbers are collected.

How to read the ledger

A reading is a recorded run. Each shows its value, its denominator, its date and its source, and says what it is not. Nothing here is live telemetry. A tool with no run behind it appears in the table of work as not yet measured, with the denominator it will publish.

Eight figures, one sentence each

Interactive illustrations of how the tools and systems work. Each one teaches a single sentence and keeps its state in the address, so a view can be linked. How to read them.

  1. 01 · Illustration

    Pull a sentence out from under the answer

    If a fact survives deleting its source sentence, the answer did not depend on that sentence.

  2. 02 · Illustration

    Three sheets that should stack

    A page can tell a person one price and a crawler another.

  3. 03 · Illustration

    A highlighter that paints only what is on the page

    A citation is a verbatim range, or it is not one.

  4. 04 · Illustration

    Teacher stamps, student copies, a held-out deck grades the copy

    Agreement with the judge, not understanding.

  5. 05 · Illustration

    Eight lanes, one shard list

    A shard is the unit you can afford to lose.

  6. 06 · Illustration

    The answer lights only the quoted span

    A retrieved page is not evidence until the answer's words are a span of it.

  7. 07 · Illustration

    The words become a vehicle first

    A fitment search settles the vehicle before it looks for a part.

  8. 08 · Illustration

    The rebuild that refuses to ship

    A scheduled rebuild publishes only when its change looks like an ordinary day.

Table of work

Everything the lab has built, what each one has measured, and when it last changed. Figures appear only after a run; until then the row says so.

Research, free tools and products, with the figure each has published and when it was last updated
NameWhat it doesFigurenUpdated
ResearchMeasurements with their denominators, windows and sources, and a section on what each one does not show.
ChatGPT referrals at an auto-parts store, Q3 2026Share of sessions that completed checkout, by referral source, in Shopify attribution, at one store over one quarter.12.6% vs 1.9%ChatGPT vs Google search19 of 151 and 76 of 3,988 sessionsRecorded 2026-10-04
Shelf Ledger, issue 0: do a product page's surfaces state the same price?A frozen panel of 40 public Shopify product pages, each read once: how often the structured data, the visible text and the Shopify product JSON state different prices, before and after a read of each flag.2 of 37pages with a true price disagreement after review; 22 of 37 flagged by the reader40 pages in the panel, 37 with a price on two surfacesRecorded 2026-10-07
How AI Shelf Check measures readinessEvery check, its weight, its confidence level and the published sources it rests on.MethodNo published figure
How Fact Split and Span decide a matchHow Fact Split compares structured data, visible text and Shopify JSON, and how Span stamps a clause as a verbatim span. Every normalization and limit stated.MethodNo published figure
Explainers: eight mechanisms, one sentence eachInteractive illustrations of Falsify, Fact Split, Span, the Jev distillation, the gpur router, span-verified retrieval, fitment search and the gated fitment rebuild. Invented example text; the only recorded figures are the Jev reading.IllustrationsNo published figure
Free toolsInstruments anyone can run without an account. None has a published figure yet; each names the denominator it will publish after a run.
AI Shelf CheckEnter a store address and see whether AI shopping answers can read and cite its products, with the exact fix for each finding.Not yet measuredWill publish: A readiness score per store, out of 100, with six weighted areas. No aggregate across stores is published.
Fact SplitPaste a product page address and see whether its structured data, visible text and Shopify JSON state the same price, stock and identifiers. Raw strings shown, no score.Not yet measuredWill publish: Of P product URLs where at least two surfaces stated a price, D had normalized prices that differed. P, D, the fetch date and the sampling rule are published together.
SpanPaste a sentence and a page address. Each clause is stamped as a verbatim span of the page, with its byte offset, or as not a verbatim span.Not yet measuredWill publish: Of C clauses checked against pages that returned HTTP 200, V were verbatim. V, C, the splitter version and the date are published together.
FalsifyRemove or replace the sentence that holds a fact and see whether a small model running in your browser still states it. Your text stays on your device.Not yet measuredWill publish: Answers that state a removed fact, of answers per condition, per named model and prompt, with the control condition reported beside it and the sample of passages stated.
Context CliffCompress your JSON or log five ways and see which of your questions a small model in your browser can still answer. When one breaks, test which omitted block repairs it.Not yet measuredWill publish: Answers correct at full text but not at level L, of questions answered correctly at full text, per named model, with the data sample and question sampling rule stated; and repairs found, of failures searched, with the trial cap.
Compression ReceiptPaste JSON or a log, mark the exact strings that must survive, and see which compression rules keep them at a fixed token budget. No model runs.Not yet measuredWill publish: Gold spans preserved, of all gold spans, per compressor and token budget, with the input sample and the rule for choosing spans stated.
TripwirePaste an agent's instructions, scan them for known tricks, then watch a small model try them against a made-up workspace. Turn permissions off one at a time to see which switch stops what.Not yet measuredWill publish: Boundary-crossing attempts, of seeded attack scenarios, and task completions, of benign scenarios, per named model and permission configuration, with raw receipts saved.
ProductsSystems OptiVis builds and runs for businesses. Status is stated in the words the product page uses.
Fitment Search EngineVehicle fitment search and catalog engine for Shopify auto-parts stores. Every part that fits, grouped by type, with live stock.In productionNo published figure
LITIGATORLitigation document intelligence for a Texas personal injury practice. Checks every quote against its source, character for character.3,579case findings in the library33 motion builders, 75 discovery setsRecorded 2026-10-04
PI ENGINEIntake responder for personal injury firms, designed to answer new leads within a minute and hand off to a person.In pilot with one Texas firmNo published figure

Updated is the date of the last content change, taken from the repository history. How each tool is verified and what changed, by date.

Which tools can I use now, and which require a quote or pilot discussion?

OptiVis AI Labs offers products at different stages. The Fitment Search Engine is in production and uses a quoted setup and monthly arrangement. LITIGATOR is litigation document intelligence, while PI ENGINE is in pilot with one firm. AI Shelf Check is free. Buyers should use the individual product page to distinguish an available tool from a pilot or a scoped deployment.

Fitment Search Engine · LITIGATOR · PI ENGINE · AI Shelf Check

Facts reviewed October 6, 2026.

Operated by OptiVis LLC

OptiVis LLC, founded in 2024 by Abdullah Siddiqui in Sugar Land, Texas, runs four properties: OptiVis (AI engineering), OptiVis Marketing (small-business marketing), OptiVis AI Labs (products and research) and OptiVis Logistics (applied AI in logistics).