Skip to content
Koralis AIBook a free Scoping Review

Kovac · in beta · for bids and work-winning

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

Put AI to work on your past bids. Mark the client-name and rate columns it must not see.

Your bid library holds the method statements and case studies the next tender needs. Your rate cards and bid register hold each client's name and rates, in columns you can mark.

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.

A framework tender closes on Monday. The method statement your writer needs was written for a hospital two years ago, and it sits beside that client's rate card. So she starts from a blank page: no one wants those rates in this bid.

An illustration, not a customer's story.

One request, from your files to the result

Bids and work-winning: one request, start to finishYour material: Past method statements (a document, by end Oct 2026) and Rate cards and priced schedules (a spreadsheet). Fields you mark: Client names, Day rates, Bid and contract values. Kovac checks requests to your data against your policy. From late October 2026, the AI model you choose drafts a method statement from your past ones, 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 method statement to edit. Separately, today: A writer not cleared for day rates asks for day rates, 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 materialPast method statementsby end Oct 2026Rate cards and priced schedulesFields you markClient namesDay ratesBid and contract valuesKovac checks against your policyMarked fields masked on every AI callfrom late Oct 2026The AI model you chooseDrafta method statement from your past ones[CLIENT_1]in place of client namesUnmarked fields and Word or PDF text asthey areThe resultA first-draft method statement toeditClearance decides what a person may read.A writer not cleared for dayratesasks for day ratesRefusedKovac checks against your policy, todayRefused, and recordedA writer not cleared for day ratesasked for day ratesPeople 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

One client's rates inside a shared bid library

Your library holds a strong method statement from a hospital refurbishment, and the rate card priced for that client. A writer on a new tender asks the model to draft from it. The method statement reaches the model as it is; the client name and day rate columns you marked on the rate card reach it as placeholders. If that writer is not cleared for day rates and asks for them, the request 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
Past tender submissions and quality responses, in Word
Document
Method statements and case studies
Spreadsheet
Rate cards and priced schedules
Spreadsheet
Your bid register: bids, clients, values and outcomes

Columns this team would mark

  • Client names, on rate cards and the bid register
  • Day rates and schedule rates
  • Bid and contract values

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 first-draft method statement for a school extension, from the two you wrote for similar schools

More it could draft
  • A first draft of a method statement, from your past ones for similar work
  • Answers to a tender's quality questions, from past submissions that answered the same question

Find

The AI model does this

Past projects of similar sector and scope to cite, each with its case study

More it could find
  • Comparable past projects to cite, by sector, scope and size
  • Case studies and project references that fit what the tender asks for

Check

The AI model does this

Your draft against the tender's quality questions: any left unanswered, and any over its word limit

More it could check
  • A draft against the tender's stated requirements, listing any it does not answer
  • That every question has an answer, within its word limit

Questions your team will ask

Does it write the bid?

No. The AI model you choose drafts; your writers edit and decide what goes in. Kovac writes nothing: on the routes it covers, it checks requests against your policy on the way to the model.

Most of our library is Word documents. Is a client name in the text masked?

No. The model can draft from Word documents, but masking works on the columns you mark: a hosted model receives the text as written; your own keeps the request on your network. See the limit: where masking applies

Half our library is CVs and named project sheets. Can we use those?

Not at first: they are personal data, and a pilot on personal data has its own condition. Start with method statements, case studies and rate cards. See the limit: pilots on personal data

What to bring to the Scoping Review

No data: descriptions are enough.

  • Where your bid library lives, how it is filed and roughly its size
  • The rate-card and bid-register columns that name a client or carry a price
  • Any client-contract clause about using AI on their material

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.
  • A pilot on personal data waits for a data processing agreement, which has no date yet.
  • Today the check covers three of seven routes to data; opening raw files and previews is checked by the end of October 2026.
The other eight limits

What the check does today

  • 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

  • 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.
  • 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 your bid library, and the rate a writer must not see.

Describe the bid library and the rule it must hold, such as "a writer not cleared for day rates is refused 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.