Enterprise Decision Intelligence · Advanced Knowledge Management

SPOCK

A knowledge engine that remembers the way people do

It consolidates what has been confirmed, lets go of what goes unused, and updates what has changed.
RAG finds documents. SPOCK remembers what your organization knows.

SPOCK recall view: a single question brings up the memories connected to it
The moment of recall · actual screen. The white ring is the question. The brightened branches are the memories that came up along its cues.

SPOCK = Synthesis Platform for Operational Cognition & Knowledge

STATEMENT 01

It remembers the way people do

Storing documents and pulling out similar ones is search. SPOCK consolidates what has been confirmed, lets unused knowledge fade, and keeps what is certain apart from what is hearsay.

01

It consolidates

Knowledge confirmed again and again moves up, one stage at a time, until it becomes organizational knowledge. In RAG, every chunk has the same weight.

02

It forgets

Knowledge that is not confirmed again gradually moves into the background. Knowledge that people have curated is never deleted.

03

It tells fact from hearsay

Every relation is tagged as fact, plan or proposal. A "planned adoption" in a proposal does not turn into a signed contract.

04

People confirm

When the AI proposes, people approve sentence by sentence. The veto always stays with people.

Four stages of memory

Seen once
Confirmed
Common sense
Core principles

The more often knowledge is confirmed across documents and the more it is used, the higher it rises. If it is not confirmed again, it comes back down. The higher the stage, the fewer the items and the longer they last.

STATEMENT 02

It sees time

What is valid now, and what was valid then. Every fact carries the period during which it is valid. A revision replaces the old value, and the old version stays as history.

QuestionSPOCKRAG
What is the travel allowance now?KRW 100,000 per day version 3 · since 2025-07Passages for KRW 70,000, 80,000 and 100,000 can be retrieved together and get mixed
What was it in March last year?KRW 80,000 per day version 2 · valid at that timeFilters "March last year" only by document creation date
What changed, and when?2024-07: KRW 70,000 → 80,000. 2025-07: KRW 80,000 → 100,000No link between versions, so the LLM guesses the comparison

The example policy and amounts are illustrative.

It reads the date the document states

It looks first at dates in the title, cover page and revision history. The file creation date does not fool it.

Old versions are never deleted

They are replaced but stay as history. For an audit, it restores the policy exactly as it was at that time.

Time becomes a signal

Overdue, gone quiet and forgotten all come from this axis. Each fact needs a point in time before it can be counted.

STATEMENT 03

It connects documents

An organization's answers are rarely in one document. SPOCK keeps documents linked to each other, and answers by gathering facts scattered across them.

Example question: "How were the findings from this year's security audit addressed?"

How SPOCK puts the answer together
  1. 1 · Finds the findings in the audit report
  2. 2 · Gathers the action taken on each item from the action plan, meeting minutes and replies linked to that report
  3. 3 · Answers item by item, with every document it used attached as a source

The example is illustrative.

It gathers scattered facts

Facts written separately in reports, plans and meeting minutes come together in one answer.

It shows all the evidence

Every document used in the answer is attached as a source. You can go straight back to the original text.

We do not throw out RAG

Source text search stays as it is, and a layer that links documents sits on top of it.

STATEMENT 04

It knows the state of the organization

What has stalled, and what is about to. It counts stalled work and missing knowledge, and also the early signs of a stall. It raises them as signals before they turn into problems.

Today's signals

OverdueDue soonGone quietOpen riskAwaiting approval

These signals are extracted by reading documents. It also catches work that should be moving but has not been mentioned for a while.

Missing knowledge

It shows the topics employees asked about but that had no evidence, with how often each was asked. Write a document right there, and the next question gets an answer.

Early signs of a stall

Connections concentrated on one task, one result that many pieces of work depend on, documents where confirmed and proposed content diverge. It points to work, not to people, and people confirm anything that conflicts.

STATEMENT 05

One engine, as many apps as you need

Every function is open through a standard API. Employees build their own work apps on the company's memory, and a new use case does not have to wait for custom development from a vendor.

Included apps

  • AI chat: answers with sources
  • Wiki: AI assembles it, people refine it
  • Home · today's signals: what to follow up, what is waiting
  • Projects · RFP: automatic progress, requirement assessment

Apps built by employees · examples

  • Department chatbot: only our department's policies and FAQ
  • Product description draft helper: marketing copy from development material
  • Approver recommendation: policy × org chart to settle on one person
  • Groupware and portal widgets: features inside existing screens

Your existing repositories, as they are

It connects to the repositories you already use, such as groupware, drives and wikis, with the originals left in place. Documents are not moved.

Employee apps follow the same rules

In-house apps and AI agents go through the same permission checks as people, and every call is recorded in the audit log.

It grows without a vendor

Customers build new use cases themselves. Customers also choose between an in-house LLM and an external LLM, and switch without redeploying.

STATEMENT 06

Where it works

Anywhere work leaves documents behind. There is one engine. What changes from one area to the next is the documents you connect and the apps you use.

Policy and internal rules

Finance · public sector

"Rules are revised often, so old clauses get mixed into answers"

A revision replaces the old version. Ask about any point in time and it answers with the clause that was valid then.

Proposals and bids

Public projects · SI

"People check hundreds of RFP items one by one"

It finds supporting evidence for each requirement and assesses it, and flags the items a person needs to write.

Project deliverables

Manufacturing · construction · SI

"Deliverables are scattered, and no one knows what has been produced"

It links the planned deliverables of each schedule stage to the documents actually produced, and opens the latest version directly.

News and content archives

Press · media

"Archived articles can be searched, but they are not connected"

It connects people, events and relations across articles, and drafts pieces that answer questions from readers.

Internal wiki and groupware

All industries

"Documents pile up, and no one organizes them"

As documents come in, the wiki assembles and corrects itself. Permissions follow the org chart.

Records classification and retention

Public sector

"Records are classified by hand"

It reads the type and nature of each document, suggests a classification that fits the institution's scheme, and a person confirms it.

On your own servers, even air-gapped

Your core systems stay as they are, and SPOCK reads on top of them. Remove it and your systems keep running.

Tested on a standalone air-gapped server

It has run on real documents on a single server with no internet access.

On-prem LLM only

It can run on an in-house LLM alone, so documents never leave your network.

Originals stay as they are

Documents are not moved or modified. SPOCK connects to the original repositories and reads from them.

See it with your own documents

In a demo, we show you what SPOCK remembers and connects from your documents.

Request a demo

Advanced Resource Planning is handled by WARP.