Skip to content
Koralis AIBook a free Scoping Review

Kovac · in beta · for marketing

AI for your whole workforce, one team at a time.

Marketing that can see the money.

Which campaigns and segments turn into profitable work? The margin behind that answer sits with finance, which decides what it releases. A pilot starts with one dataset: finance's released aggregates, or your CRM's opportunity export.

Book a free Scoping Review← Other teams

With both founders, no data. Pilots from £5,000 + VAT + your AI model's usage. Half at the start, and half when we send your payback report.

At the quarterly budget review, leadership asks the marketing director which campaigns made money. Marketing has the spend, the leads and the opportunities; the margin sits with finance. Without it, the honest answer is about volume, not profit.

An illustration, not a customer's story.

One request, from your files to the result

Marketing: one request, start to finishYour material: Last quarter's campaign plan (a document, by end Oct 2026) and Revenue and margin by segment (a spreadsheet). Fields you mark: Client names, Staff cost rates, Margin by client. Kovac checks requests to your data against your policy. From late October 2026, the AI model you choose drafts the campaign review from released figures, working through that check. On every AI call the fields you mark reach it masked: Client names arrives as [CLIENT_1]. Unmarked fields, and the text inside Word and PDF documents, arrive as they are. The result: A first-draft campaign review to edit. Separately, today: A marketer not cleared for margin asks for margin by client, a marked field. Kovac refuses the request and records the refusal. People search that record today; from late October 2026, the AI model can also draft from it. Solid lines work today; dashed lines are dated.Your materialLast quarter's campaign planby end Oct 2026Revenue and margin by segmentFields you markClient namesStaff cost ratesMargin by clientKovac checks against your policyMarked fields masked on every AI callfrom late Oct 2026The AI model you chooseDraftthe campaign review from releasedfigures[CLIENT_1]in place of client namesUnmarked fields and Word or PDF text asthey areThe resultA first-draft campaign review toeditClearance decides what a person may read.A marketer not cleared formarginasks for margin by clientRefusedKovac checks against your policy, todayRefused, and recordedA marketer not cleared for marginasked for margin by clientPeople search it today.From late Oct 2026, the AI model candraft from it.
  • Works today
  • The AI model's part, from late Oct 2026; Raw files and previews, by end Oct 2026
The detail: the example, what it works on, and what stays governed

Which segments carried margin last year?

The marketing director asks which segments carried margin last year, to plan the next campaign. Finance has released revenue and margin by segment as a spreadsheet, with client names and staff cost rates marked sensitive. The model receives the segment figures as they are, and client names and cost rates as placeholders. A campaign executive not cleared for client names who asks for that column is refused, and the refusal is recorded.

Fields you mark sensitive reach the AI model masked with placeholders; fields you don't mark reach it as they are. The same value always gets the same placeholder, so masked data can still be linked to a person and remains personal data.

On records loaded into Kovac, someone not cleared for a column you have marked who asks for it is refused, and the refusal is recorded.

Clearance decides what a person may read. It never unmasks a field for the AI model: a marked field reaches the model masked on every call, whoever asks.

What it works on

Document
Campaign plans and briefs
Document
Case studies and client stories in draft
Spreadsheet
Revenue and margin by segment, campaign or product, as finance releases it
Spreadsheet
Opportunity exports from your CRM, with the campaign each one came from

Columns this team would mark

  • Margin by individual client
  • Client names
  • Staff cost rates
  • Fee rates and discounts agreed with a client

What the AI does for this team

From late October 2026, the AI model you choose, working through Kovac's check. That model does the work below. Kovac does not draft or search; its check decides what the model may see.

Draft

The AI model does this

A campaign review for the budget meeting: revenue and margin by campaign, from finance's released figures

More it could draft
  • A campaign review: revenue and margin against each campaign, from the figures finance has released
  • A segment review for the leadership team: which segments carried margin and which carried only volume

Find

The AI model does this

The segments that carried margin last year, and the ones that carried only volume

More it could find
  • Which campaigns and segments carry margin, in the revenue and margin by segment that finance releases
  • The opportunities a CRM export credits to each campaign, and which of them closed

Check

The AI model does this

A case study's figures against finance's release, listing any it cannot match for you to check

More it could check
  • A claim in a case study or campaign plan against the figures finance has released, before it goes out
  • The figures in a draft review against finance's release, listing any it cannot match, for marketing to check

Questions your team will ask

Will finance actually release the figures we need?

That is finance's decision, under its own policy. What it releases reaches the model as it is; the fields it marks, such as margin by client, reach it masked.

Can we join our CRM export to finance's figures?

Not in the first step. It starts with one of the two, chosen by the question you most need answered and what finance will release. See the limit: what the first step is

What about contact lists and other personal data?

Contact lists are personal data, and a pilot on them waits, for the reason in the limits. Aggregates by segment or campaign carry no contacts. See the limit: pilots on personal data

What to bring to the Scoping Review

No data: descriptions are enough.

  • The question leadership keeps asking marketing, in their own words
  • A description of finance's revenue and margin export, and how it is split
  • What finance would mark, such as client names or margin by client

What it does not do yet, and what a pilot is

  • Masking works on the fields you mark: the columns of a spreadsheet or record set. It does not reach into the text of a Word or PDF document.
  • The first step is one team: a four-week pilot on your own machines, with one dataset, supplied as files, one workflow, and the AI model you choose working through Kovac's check from late October 2026.
  • A pilot on personal data waits for a data processing agreement, which has no date yet.
The other eight limits

What the check does today

  • Today the check covers three of seven routes to data; opening raw files and previews is checked by the end of October 2026.
  • Three failure cases still let a request through when they should stop it: a deploy whose policy call fails, a read of a record whose clearance lookup errors, and a plan that cannot be signed, which runs unsigned rather than halting. Every route blocks a request when the policy check cannot run, by the end of October 2026.
  • Kovac's record holds the decisions on the routes it checks: refusals today; permitted requests too by the end of October 2026.
  • The record is searchable, but any signed-in user can add an entry in anyone's name, and entries are not signed or linked together when written. By the end of October 2026, only Kovac itself can write to the record; by then, every entry is signed and linked to the one before it as it is written, permitted requests as well as refusals.

What a pilot is

  • Reading straight from your database tables comes in December 2026.
  • Kovac does not sit in front of Microsoft Copilot, Gemini for Google Workspace or web chat assistants.

What we do not hold yet

  • Kovac is in beta. Koralis AI holds no certification today.
  • Professional indemnity insurance is not held today.

Bring the question marketing wants answered, and the figures finance will release.

We go through which figures finance is content to release, aggregates first, and what marketing would ask of them. Both founders, no data, a written pack within 48 hours.

The terms

  • The Scoping Review is free. It signs you to nothing.
  • Four-week paid pilots, with Kovac on your own machines, from late October 2026.
  • Quick-Start, for mid-sized businesses: £5,000 + VAT, fixed.
  • Proof Pilot, for regulated and larger organisations: £7,500 + VAT, fixed.
  • The pilot's job is to give you a payback figure, measured on your own work.
  • Half at the start, and half when we send your payback report. By invoice.
  • You pay for your AI model's usage, either to its provider directly or passed through by us.
  • Stop at the day-five go/no-go and you pay only the first half.
  • If you subscribe within 90 days of the pilot ending, the pilot fee you've paid is credited against your first year's subscription.
  • Your contract is with Koralis AI Limited (company number 16558134).
  • Kovac is not yet in production anywhere.
Book a free Scoping Review

Rather write first? enquiries@koralis.ai reaches both founders. Or message Dylan or Marko on LinkedIn.