A pathologist’s assistant, not a reporting tool.
Cogit is Voicebrook’s co-intelligence assistant. It is focused on the pathologist’s case review — everything that surrounds the diagnosis, not the diagnosis itself. It removes the searching, the remembering, the re-reading, and the assembling: the work that sits on either side of the diagnostic moment and competes with it for attention.
A report comes out of that. It is not what the product is for.
Beta, late 2026.
This is computational co-intelligence: systems that make pathologists better at what only pathologists can do, rather than attempting to do it for them.
Pathology doesn’t suffer from a lack of information. It suffers from fragmentation.
Pathologists are handed cases with almost no context, and the diagnostic work is surrounded on both sides by work that isn’t diagnostic.
The search before the diagnosis is slow, but the worst cost is ambiguity — the absence of a prior finding is itself meaningful, so the pathologist checks multiple places for multiple things and then double-checks the ones that came back empty.
None of this requires a pathologist’s training. All of it consumes a pathologist’s attention. The cost isn’t only time — it’s that the attention spent here is attention not spent on the slide.
What changes on every case.
Preparedness
“When I start a case, the clinical context is immediately clear and apparent, so the questions that normally lead to searching across systems never come up.”
Confidence
“I know the information in my reports is clear and accurate without having to re-read or double check.”
Focus
“My time, attention, and mental energy are focused where I am most valuable — slide interpretation, diagnostic judgment, and therapeutic guidance.”
What stays yours.
Each of these is a deliberate design decision, and together they are what make everything else here trustworthy.
The read stays yours
We don't touch the slide. No image interpretation, no suggested diagnosis — the interpretation is the part of this job that belongs to a pathologist.
The words stay yours
What you say routes the workflow and shapes the report. It never decides what you should conclude.
Every value is yours to confirm
Each generated element is editable, and every derived value — staging included — is presented for your confirmation rather than applied silently.
Your systems stay your systems
This isn't a replacement for the LIS, the EHR, or your image management system. It's the connective layer across them.
Cogit gives the pathologist everything they need to interpret the case — and then gets out of the way.
Nothing is asserted without its basis.
Everything on screen is labeled — both the context that arrived from your other systems, and what Cogit understood from your own words.
Every piece of context is labeled with where it came from.
The case opens with the clinical picture already assembled: why this case exists, what the prior biopsy found, what was measured at the bench. Each block carries its source — EHR for the order and history, LIS for the prior biopsy, PRO for the grossing detail.
A pathologist deciding how much weight to give a summarized finding needs to know where it came from. A system that presents assembled context without attribution is asking to be trusted rather than earning it.
And you can see what it understood, line by line.
Each sentence is analyzed the moment it commits, and the clinical entities detected in it appear beneath it. Nothing about the interpretation of the case is hidden until the report is generated.
Reword or remove any sentence and the annotation is redone, so what Cogit understands always reflects the current text rather than the original transcript.
A derived value offered without justification asks for trust. A derived value offered with its basis invites judgment — which is the only version a pathologist should accept.
Completeness tracked as you speak, not audited at sign-out.
Cogit tracks what has been said against what the case requires, in real time. The pathologist sees completeness at a glance without stopping to read the protocol, and required items are visually distinct from optional ones.
Staging is derived rather than asked for. It is a summary of what the pathologist has already said elsewhere, so asking separately is asking twice. The stage is calculated and then presented for confirmation — the question is whether it is correct, not what the answer should be.
Simple cases stay simple. A routine biopsy handled today in a single spoken phrase is never more work than it was before.
Derived staging, with its basis
The calculated stage, what it was derived from, and the confirm-or-override control in one frame. Best single proof of the line above — Cogit inviting judgment rather than asking for trust.
Every claim traces to something demonstrable.
Across fifteen body-system categories, from Breast and Central Nervous System through Skin and Thorax. Every tenant starts with the full set seeded.
The link is the diagnosis code, not the protocol source. CAP protocols come pre-built and pre-linked; a hospital's own protocol, a specialty society's, or one we author participates the same way.
Conflicts, ambiguity, and unaddressed items are surfaced before a report is generated. Perineural invasion described as absent in one place and focally present in another is caught before it reaches a report.
An addendum carries the ancillary findings, not a restatement of the original checklist. Duplicating a checklist across two reports creates divergence, and divergence in a synoptic can affect treatment.
When the pathologist calls for MMR, KRAS, or BRAF while working the case, the order goes into the LIS. They don't finish the case and then go somewhere else to order what they just asked for.
A pilot that does not wait on an interface project. Integrations deepen the available context, and depth is the point — but every capability works without them.
The validation pass
The forced-choice screen catching an inconsistency before the report is generated. Stage the perineural-invasion example if you can — absent in one place, focally present in another. This is the check pathologists don’t currently have.
Where it sits today, and where it’s going.
The connective layer across your systems.
It sits across the AP system, the digital pathology platform, and the EHR at once — which is where a pathologist’s day actually spans. An EHR vendor’s own AI is deep inside one system and confined to it. That difference is the whole of our advantage, and it exists now.
You ask, instead of navigating.
Rather than moving between those systems, the pathologist asks for what they need and Cogit reaches across them — and acts, placing the order rather than saying where to place it.
The boundary holds in both. Asking what the prior colonoscopy showed, or asking for a stain to be ordered, is Cogit working as intended. Asking what the diagnosis is falls on the wrong side of it — and always will.
The pressures this is pointed at.
The case for computational co-intelligence in a department is not that it saves time on a case. It is that the pressures below are not answerable by hiring.
Anatomic pathology carries the highest overall vacancy rate of any laboratory department. Filling an AP supervisory vacancy takes more than twelve months.
Laboratory staff, not pathologists.
ASCP 2024 Vacancy Survey — Garcia et al., Am J Clin Pathol 164:759, November 2025
Commission on Cancer accreditation requires 90% of eligible cancer pathology reports to follow CAP synoptic format — an audited number the chair is accountable for. CAP allows eight months from a protocol's posting before a laboratory risks a deficiency.
Protocol currency is a standing burden, not a one-time project.
Commission on Cancer · CAP
Pathologist supply is projected to decline 7% against a 16% increase in demand by 2037 — roughly 3,000 more pathologists needed, against about 600 entering the profession each year.
The argument is not that we save time. It's that hiring is not an available answer.
HRSA workforce projections
Joined at the seam, by design.
Cogit does not support the gross room. The PA workflow stays in VoiceOver PRO®, and sites run both — PRO handling grossing, Cogit handling case review.
Which is why grossing detail flowing from PRO into an assistant case is architecture rather than a demo convenience. What is on each slide, which sections came from the tumor, the measurements taken at the bench: it arrives in the case, labeled as coming from PRO, without anyone restating it.
With PRO you dictate the report. Here you talk through the case, and the report is assembled from it.
Tell us what your pathologists need.
This is being built against real practice rather than against assumptions about it. Strategic Partners get first access to the Beta in late 2026, seats on the Reference Advisory Committee, and direct input into what gets built next.
We ask for active participation in shaping it. You become a design partner, not just a customer.
Draft note: the live page also promises two advisory seats, quarterly business reviews, and capped contract pricing for the full term. Confirm all three still hold before any of this ships.