Klarum

Knowledge (Org Knowledge Graph and Packages)

Generally available
Supplier and issuer
From free

The org-specific context substrate. It turns a pile of PDFs into a structured capability graph with evidence, plus a searchable knowledge corpus and shareable packages the rest of the AI stack reads from.

Catalogue id
knowledge

Description

What it is

Klarum's firm-specific knowledge layer: the system of record for everything a firm knows and has done - company profile, project references, project detail sheets (PDS), consultant CVs, past EOIs, collateral - turned from a pile of PDFs/DOCX into a structured, queryable capability graph plus a searchable knowledge corpus. Three things live here:

  1. Firm Knowledge Graph: uploaded docs are chunked, embedded, and LLM-tagged with capabilities (e.g. road_safety_audit, pavement_management). Result: a tree Firm to Category to Capability to evidencing Documents, each capability carrying a confidence label (explicit/implied), evidence score, passage counts, and sample quotes.
  2. Knowledge Items: curated records (title + markdown body + a kind like standard/whitepaper/ICP/case study), org-scoped and semantically searchable.
  3. Knowledge Packages: named, versioned bundles of items, shareable via public link, exportable (ZIP / branded PDF), installable into a workspace or another tenant ("playbooks"/marketplace).

It is the firm's context substrate: the matching engine, EOI/document generator, and workspace agent all draw on it. Without it, those AI features run cold.

What it helps users do

Make the firm's track record machine-usable (dump 5-10 reference docs to an auto-derived capability inventory); power matching with firm-specific signal; draft better EOIs faster (past EOIs/PDS become retrievable, citable context with page provenance); surface deployable personnel (bulk-uploaded CVs to a Team Composition view by role/seniority); audit ingest health (per-document status, retry/bulk-retry/reingest); package and share institutional knowledge; and search the org semantically.

Capabilities

  • Firm knowledge graph

    Generally available

    An org to category to capability to evidencing document tree, where every has_capability edge points back at the exact passage, page and confidence that justifies it.

  • Knowledge items

    Generally available

    Curated org-scoped records with a title, markdown body and a kind. A sweep embeds them every 30 minutes, so a new item is keyword-findable at once and vector-findable at the next sweep.

  • Knowledge packages

    Generally available

    Named, versioned bundles of items, exportable as ZIP or branded PDF and installable into a workspace or another tenant. Cross-tenant public packages form a marketplace.

  • Team composition

    Generally available

    Bulk-uploaded CVs are extracted for job title and seniority and rolled up into a view of who the org can actually deploy.

  • Ingest health

    Generally available

    Per-document parse and tag status with retry, bulk retry and reingest, and status synthesised defensively so the UI never shows a perpetual spinner.

Integrations

  • Astaroth capability sidecar The graph-construction brain: a doc-level capability compiler plus a per-chunk tagger, both over AWS Bedrock Converse, constrained to the seeded capability vocabulary.

Keywords

knowledge-graph, capabilities, astaroth, packages, marketplace, cv, pds, mephiston

Provenance

This page renders a published artifact. Read the same records as JSON if you would rather check the source than the page.