Return My TimeBook a Discovery Call

Knowledge Systems

Create a Company Knowledge-Source Inventory

Organize supplied company sources into a traceable inventory of ownership, location, sensitivity, authority, freshness, and evidence gaps.

By Nick Spisak

Quick facts

Best for
Owners · Founder-operators
Prompt type
Efficiency
Expected result
A reviewable company knowledge-source inventory with source attribution, ownership, sensitivity, authority, freshness, evidence states, Unknowns, and Unresolved conflicts.
Time saved
60-90 minutes per source inventory
Required inputs
KNOWLEDGE SOURCES · SOURCE OWNERS · SYSTEMS OR LOCATIONS · SENSITIVITY · AUTHORITY · LAST-REVIEWED DATES
Works with
ChatGPT + Claude

What this prompt does

  • Produces a reviewable catalog of supplied knowledge sources and their documented governance metadata.
  • Flags missing owners, authority, dates, duplicate subjects, sensitive material, and possible conflicts without resolving them by guesswork.

When to use

  • Before an AI, automation, onboarding, or documentation project that depends on knowing where approved company knowledge lives.

When not to use

  • Do not use it to crawl unauthorized systems, change access, retire a source, update canonical records, or publish an inventory.
  • Do not place unauthorized company data or unnecessary personal, sensitive, or confidential data in an AI system.

The prompt

#CONTEXT:
Create a review-only company knowledge-source inventory from supplied records. Catalog what is provided; do not discover, access, move, or alter sources.

#INPUTS:
- Supplied source names, descriptions, and sample references: [KNOWLEDGE SOURCES]
- Documented source owners and stewards: [SOURCE OWNERS]
- Approved systems or locations: [SYSTEMS OR LOCATIONS]
- Sensitivity labels or classifications: [SENSITIVITY]
- Documented authority and source hierarchy: [AUTHORITY]
- Last-reviewed dates and review evidence: [LAST-REVIEWED DATES]

#INSTRUCTIONS:
1. Create one inventory row per supplied source. Retain its exact source name and location reference.
2. Record source attribution, owner, system or location, sensitivity, subject coverage, documented authority, last-reviewed date, and evidence status.
3. Mark missing facts Unknown. Mark competing claims or hierarchy evidence Unresolved conflict and cite each supplied source.
4. Identify duplicates and likely overlap as review flags only. Do not merge, delete, archive, rank, or declare a canonical winner.
5. Propose a named-owner verification queue ordered by documented risk signals: sensitive data, absent authority, unresolved conflict, missing owner, and missing review evidence.
6. State what data was excluded or minimized and list any additional access that a human might evaluate separately. Do not request or change access.
7. Maintain source attribution for every fact, rule, owner, authority claim, and date.
8. For each item, state its evidence status: Verified, Reported, Unknown, or Unresolved conflict.
9. Do not invent, infer, or fabricate rules, owners, authority, dates, facts, sources, or approvals.
10. Do not choose a winner or declare a source authoritative without documented supplied authority.
11. Use only authorized knowledge data in an approved AI workspace or approved AI vendor. Minimize the data; redact or omit unnecessary personal, sensitive, or confidential data. Preserve each sensitivity label or sensitivity classification and follow company retention and vendor policy.
12. Do not publish. Do not update a canonical source. Do not grant, revoke, or change access or permissions. Do not send material externally. Do not change a live system.
13. A named human owner must approve publication before action. A named human owner must approve every canonical-source update before action. A named human owner must approve every access or permission change before action. A named human owner must approve every external action or live system change before action. A named human owner must approve every policy exception before action.

#RESPONSE FORMAT:
## Knowledge-source inventory
| Source | Source attribution | Owner | System or location | Sensitivity | Coverage | Authority | Last reviewed | Evidence status |
|---|---|---|---|---|---|---|---|---|

## Unknowns and Unresolved conflicts
| Item | Supplied evidence | Missing or competing fact | Named reviewer |
|---|---|---|---|

## Human verification queue
| Priority signal | Proposed review | Named owner | Approval needed |
|---|---|---|---|

## Data-minimization note

Input checklist

  • KNOWLEDGE SOURCES
  • SOURCE OWNERS
  • SYSTEMS OR LOCATIONS
  • SENSITIVITY
  • AUTHORITY
  • LAST-REVIEWED DATES

Example input

Fictional example — KNOWLEDGE SOURCES: Northstar sales playbook, delivery checklist, pricing FAQ, and two onboarding notes. SOURCE OWNERS: Sales playbook—Ari; delivery checklist—Maya; other owners Unknown. SYSTEMS OR LOCATIONS: Approved internal drive and CRM knowledge folder. SENSITIVITY: Internal; pricing FAQ is restricted. AUTHORITY: Signed order form overrides the pricing FAQ for that customer; broader hierarchy Unknown. LAST-REVIEWED DATES: Sales playbook 2026-06-15; remaining dates Unknown.

Expected output structure

  • A reviewable company knowledge-source inventory with source attribution, ownership, sensitivity, authority, freshness, evidence states, Unknowns, and Unresolved conflicts.

Customize this prompt

  • Add stable source IDs so renamed documents remain traceable across reviews.
  • Use sensitivity labels already approved by your security or operations owner.

Guardrails

  • Maintain source attribution and an evidence status for every material claim; unsupported items remain Unknown and disagreements remain Unresolved conflict.
  • Do not invent, infer, or fabricate rules, owners, authority, dates, facts, sources, or approvals.
  • Do not choose a winner or declare a source authoritative without documented supplied authority.
  • A named human owner must approve publication before action.
  • A named human owner must approve every canonical-source update before action.
  • A named human owner must approve every access or permission change before action.
  • A named human owner must approve every external action or live system change before action.
  • A named human owner must approve every policy exception before action.
  • A named human owner and the qualified professional must approve every legal, tax, employment, or regulatory interpretation before action.
  • A named human owner must approve every payment or financial decision before action.
  • A named human owner must approve every deletion, closure, suspension, termination, revocation, deactivation, or archive action before action.
  • A named human owner must approve every promise or commitment before action.
  • Use only authorized knowledge data in an approved AI workspace or approved AI vendor; minimize data, redact or omit unnecessary personal, sensitive, or confidential data, preserve every sensitivity label or sensitivity classification, and follow company retention and vendor policy.
  • The assistant provides a reviewable draft only and must not publish, alter canonical sources, change access or permissions, act externally, or mutate a live system.

KEEP BUILDING

Related prompts

Related articles

NEXT STEP

Next step

Find out what your company's knowledge is worth.