September 2026
The model signs nothing
We built Vulcan 2.5 to read supplier documents and keep each value tied to its source. The post follows one lab report from the inbox to the person who approves it.
Industry models
Models
One per industry
We build a model for each industry, trained on the documents it runs on. Contact us about using Vulcan 2.5. Two models are in training and four are planned.
Commerce and home goods
[COM]
Contact us about access
Vulcan 2.5
Vulcan turns the lab reports, spec sheets and vendor packets your suppliers send into a product record. Every value carries the page it came from. Where a document is silent, the field stays blank for a person to check.
- Vendor operationsLulu & Georgia · Live
- Product complianceLulu & Georgia · Live
- PLMLulu & Georgia · Live
- Vendor intakeIke Behar · Scoped
- Retailer item setupShakewell
Supplier records | Vulcan 2.5
A pipeline in six stations. Files: lab reports, spec sheets and new-vendor packets arrive from suppliers. Pages: each document stays attached to the values read from it. Model: Vulcan 2.5 reads those values. Values: each value keeps its source page. Record: the product record has filled fields and a blank where the documents give no answer. Review: the record and its source pages reach a person, who decides whether to approve.
Dental and healthcare revenue cycle
[RCM]
In training
Altadena 1.5
We’re training Altadena to read eligibility, benefits, remittances, claim status and attachments. It will hand the front desk each patient’s plan, leaving blank whatever the payer didn’t say. A blank beats a guess. In its first test, on ten breakdown sheets it had never seen, it got 93.0% of all the boxes right, against 70.9% for OpenAI’s GPT-6 Luna.
- Insurance verificationHorizon Dental Care · Live
- Claims follow-upHorizon Dental Care · In build
- Claims and denialsArroyo Dental Group · In discovery
Dental breakdowns | Altadena 1.5
A pipeline in six stations. Evidence: a patient’s insurance data as the payer’s portal returns it, in machine answers, web pages and plan PDFs. Context: the patient’s whole file, read once. Model: Altadena 1.5, which is in training on sheets our AI auditors proved against the portal data and the plan’s documents. Answer heads: one per box, each choosing from that box’s list of allowed answers, blank included, so it never makes up a value. Breakdown: the sheet of about 290 boxes, filled. Review: each box carries how sure the model is; once this step is switched on, the boxes below the bar will be flagged verify for a person to check.
Accounting and payroll
[PAY]
In training
Blob 2.0
We’re training Blob to read hours in whatever form your clients send them: time sheets, attached timecards or emails. It will draft a pay line for each worker with the source beside it. A missing punch will come back as a question for your team, not a guess.
- Payroll automationLazar & Company · Live
- Email intakeLazar & Company · Live
- Client onboarding and relationsLazar & Company · In build
Payroll drafts | Blob 2.0
The work Blob 2.0 is being trained to do, shown in six stations. Inbox: hours arrive in email, attached timecards and time sheets. Hours: the figures stay on their source pages. Model: Blob 2.0 is in training, with hours beside the model on a linked inset. Pay lines: it will prepare a line for each worker with the source beside it. Questions: a missing punch stays open and becomes a question on the line. Review: a person answers the question and decides whether to approve the draft.
Real estate
[CRE]
Planned
Ridge 1.0
Ridge is planned for the rent rolls and leases a building runs on. It will hand the asset manager each date with the page it came from. We haven’t trained it yet.
- Asset managementAmoroso Companies · In build
- Investor reportingAmoroso Companies · In build
- Deal packets10mark Holdings · Live
Lease dates | Ridge 1.0
Ridge 1.0 is planned and not trained yet. The six stations show its intended job. A rent roll and lease pages arrive, with date marks on the paper. The model will read the dates, keep each date with its source page, and hand the source-linked dates to the asset manager. The last station shows the asset manager reviewing them.
Wealth management
[WM]
Planned
Arroyo 1.0
Arroyo is planned for custodian statements and the forms that open or move accounts. It will hand the advisor a report with every figure linked to its statement. Training hasn’t started yet.
Statement figures | Arroyo 1.0
Arroyo 1.0 is planned and not trained yet. The six stations show its intended reporting job. Custodian statements arrive, their figures marked on upright pages. The model will read the figures and keep each beside its source statement. They will go into a draft quarterly report. An advisor will approve the report before anything goes out.
Legal services
[LEGAL]
Planned
Phantom 1.0
Phantom is planned to read a case’s intake notes, orders and the dates inside them. It will draft from that record, and nothing it drafts is advice until an attorney makes it so. We haven’t trained it yet.
Case files | Phantom 1.0
Phantom 1.0 is planned and has not been trained. The six stations show its proposed job. Intake inquiries and the case file, including notices and orders, reach the model. It would gather the facts into a matter record, with screening for eligibility and conflicts, and put dates on the matter and calendar. It would draft letters and pleadings from that record. An attorney reviews and signs; nothing it drafts is advice until an attorney makes it so.
Live events and event media
[MEDIA]
Planned
Svengali 1.0
Svengali is planned to read an event’s contracts and expenses, from the first inquiry to the settlement. It will hand your team the holds to confirm and the settlements to check. Training hasn’t started yet.
- Booking intakeYourShot USA · In discovery
- Crew schedulingYourShot USA · In discovery
- SettlementsYourShot USA · In discovery
Bookings | Svengali 1.0
Svengali 1.0 is planned and has not been trained. The six stations show its proposed job. An inquiry from email or a web form reaches the model, with the event’s terms: the contract and its add-ons. Crew availability and skills feed it from a separate plate. It would put a hold on the calendar for a person to confirm, match the crew and draft the call sheet. After the event, it would draft the settlement from the contract, add-ons and expenses. A person checks every settlement before it goes out.
Using our models
Start with the documents you want Vulcan to read.
Vulcan 2.5 reads lab reports, spec sheets and vendor packets into a product record. Each value keeps its source page, and unanswered fields stay blank for review.
If you’re interested in using Vulcan, contact hello@mulholland.ai. Tell us what your team needs to read and where the answers should go.
The same document gets the same answer.
Better at less
One industry each.
A general model answers questions across subjects, from lab reports to poems. We train each of ours to read one industry’s documents. Altadena 1.5, the dental model we’re still training, got 93.0% of all the boxes right on ten breakdown sheets it had never seen. OpenAI’s GPT-6 Luna got 70.9%. We published the test.
No second opinions
Monday, Tuesday, next year.
A general model can give you two readings of the same lab report on different days. A lead test doesn’t have two results. Vulcan 2.5 gives one reading every run when you keep its version and settings fixed. Nobody wants a calculator with opinions.
The receipt names the model
Run it again.
Every write MarzyOS makes records the model call behind it and its version. If a provider changes or retires a rented model, that receipt may name something you can’t run again. Keeping the source document, model version and settings makes that reading traceable.
Where it runs
Your hosting needs.
Talk with us about where Vulcan would run and how your documents would reach it. We’ll work through your hosting needs and access rules with your team.
Access and review.
Talk to us about Vulcan.
If you’re interested in using Vulcan 2.5, contact hello@mulholland.ai. We’ll start with the documents you need it to read. The other models are in training or planned.
Your data follows your rules.
Your access rules still apply when a model reads a document. MarzyOS keeps customers apart, checks permissions and records the model behind each write. We list clients above to show the work we do together. Each workflow’s status comes from its client’s page, and the listing doesn’t say which model does the reading.
Every reading needs checking.
A source page lets you check what a model read; it doesn’t make the reading right. A person or a rule you wrote down must approve the result. The model signs nothing.
We still use general models.
General models handle work across MarzyOS, and each receipt names the one that did the reading. Contact us about where Vulcan 2.5 would fit in your workflow.
The work around the model
A model can read a page, but it still needs somewhere to put the answer. We build the map of your business, the receipts and the steps your team uses to approve the work. The model is one part of that work.
February 2026
The agent is the easy part
Bring us what your team still retypes.
Start
One stack of documents
Pick one stack: lab reports, benefits pages, time sheets, leases, statements, court notices or event contracts. We’ll show you what gets read and the page each value came from.
Get in touch Read about Vulcan