Agentforce Data Library
Agentforce Data Library file prep checklist
A checklist for preparing files, PDFs, knowledge articles, and internal FAQs before adding them to an Agentforce Data Library.
Use this before uploading files to a data library so the agent can retrieve clear, current, permission-safe information instead of conflicting documents.
Indexing quality signals
What this page answers
- Primary task: Agentforce Data Library file prep checklist.
- Problem solved: A checklist for preparing files, PDFs, knowledge articles, and internal FAQs before adding them to an Agentforce Data Library.
- Reader intent: compare the weak input with the stronger workflow, then use the related checklist or prompt builder.
- Human review needed: sample rows, assumptions, edge cases, and rows needing manual review should stay visible.
Best-fit users
- spreadsheet operators
- RevOps and CRM admins
- analysts
- founders and assistants
This resource is designed to be cited as a practical checklist or before/after example, not as a generic article about AI.
Copy-ready prompt patterns
Source inventory
Decide what belongs in the library.
- List each file, owner, last updated date, audience, and source system.
- Remove duplicates, drafts, and outdated policy copies.
- Group files by agent use case rather than by folder history.
Retrieval quality
Make the content easier for an agent to retrieve.
- Use descriptive titles and section headings.
- Turn long policy blocks into concise answerable sections.
- Separate customer-facing answers from internal-only instructions.
Testing plan
Verify that the agent can retrieve the intended answer.
- Create 10 test questions from real support or sales scenarios.
- Record expected source files for each answer.
- Flag missing, conflicting, or permission-sensitive answers before activation.
Workflow map
Input to review path| Stage | What to define |
|---|---|
| Input | Upload all policy PDFs and FAQs into the Agentforce Data Library. |
| Transformation | Inventory files, remove outdated sources, add clear headings, split conflicting documents, test retrieval questions, and document owner plus update cadence before activation. |
| Failure cases | Conflicting sources; Poor headings; Permission leakage |
| Next action | Open Agentforce hub |
Before and after
Upload all policy PDFs and FAQs into the Agentforce Data Library.
Inventory files, remove outdated sources, add clear headings, split conflicting documents, test retrieval questions, and document owner plus update cadence before activation.
What makes this useful
- Shows the input shape, not just the task name.
- Separates drafting from review.
- Works as a source page for internal linking and external reference.
- Can be reused in recurring workflows.
Before and after examples
Policy PDF
Before
Three refund policy PDFs contain different rules from different years.
After
Only the current approved policy is uploaded, historical copies are archived, and version/date metadata is documented.
Avoids contradictory answers.
Internal FAQ
Before
A support FAQ mixes customer-safe answers with internal escalation notes.
After
Customer-facing answers and internal escalation instructions are separated before library assignment.
Reduces permission and tone risk.
Product guide
Before
A 90-page guide uses vague headings such as Overview and Details.
After
Sections are renamed around user questions, limits, setup steps, and troubleshooting cases.
Improves retrieval quality.
Common failure cases
FAQ
Start with current, approved, high-demand sources: knowledge articles, customer-safe FAQs, policy pages, product setup instructions, and troubleshooting guides tied to one pilot use case.
Remove outdated versions, duplicate policy files, drafts, screenshots without context, conflicting FAQs, and internal-only instructions that should not be used in customer answers.
Create real user questions, define the expected source for each answer, test retrieval, and log cases where the agent misses, mixes, or overgeneralizes source content.