Answer repeat research questions from a shared archive
Prototype an assistant that retrieves relevant prior studies when colleagues ask recurring research questions.
How this works
An archive assistant should answer from the studies a particular requester is allowed to see, preserving study dates, sample limitations and uncertainty. Retrieving a relevant paragraph is only the start: the answer must distinguish what was actually observed from what someone hopes the study implies.
Index stable artifact identities and versions rather than treating every copied slide as an independent source. Permission filtering must happen before restricted passages reach the answer-generation context. Start with a controlled archive and a reviewable answer format before enabling broad discovery.
Before you start
Approved corpus
Identify current studies, their owners, versions, dates, populations and allowed audiences. Exclude personal research notes not approved for reuse.
Permission model
Confirm how requester access is checked. If the tool cannot enforce it, use a manually curated authorized export rather than the whole archive.
Answer policy
Agree when the assistant should answer, qualify an inference or refer a question to a researcher.
Prepare the inputs
- artifacts
- Required
Study ID, version, date, text and methodology notes
Avoid duplicated copies counting as corroborating studies.
- access_rules
- Required
Artifact-level allowed audience or permission reference
Never widen access because a document is technically retrievable.
- question
- Required
Specific research question and requester context
Clarify population, product and time horizon when needed.
- archive_index
- Required
Searchable text with source anchors
Ensure anchors point to stable accessible evidence, not invented page references.
Implementation, step by step
Prepare the authorized collection
- Inventory artifacts and confirm current versions with owners. Record methods, sample and observation period alongside extracted text.
- Filter to the requester’s allowed corpus before retrieval. Preserve document IDs and passage locations through extraction.
Checkpoint: A permission-scoped index can trace every passage to a study.
Translate the question into retrieval needs
- Identify the relevant population, behavior and time period. Expand synonyms without changing the question into an easier one.
- Retrieve potentially supporting and contrary findings, not just the first high-scoring passage.
Checkpoint: The evidence packet covers the actual question and its important limits.
Check applicability
- Read enough surrounding material to understand sample, method and conditions. Separate recent evidence from studies that may no longer apply.
- Compare overlapping or contradictory studies and explain differences in populations or definitions.
Checkpoint: Each candidate finding has an applicability note.
Draft the grounded response
- Answer with a concise conclusion, supporting observations and internal source anchors the requester can access.
- Label inference and missing evidence. Do not extrapolate a small qualitative sample into a quantified market claim.
Checkpoint: Every factual answer statement is supported by the selected evidence.
Evaluate and maintain retrieval
- Review representative answerable, ambiguous and unanswerable questions with researchers. Record missed studies and unsupported claims.
- When artifacts or permissions change, update the index and check affected examples before reusing old answers.
Checkpoint: The pilot records answer quality and explicit escalation cases.
Decisions along the way
No authorized study answers the question
Say the archive does not establish the answer and route a focused research question.
Studies conflict
Describe the difference and its likely methodological basis; avoid voting by document count.
A relevant source is restricted
Do not reveal its findings or sensitive metadata; offer an authorized access-request path if one exists.
What you will produce
research-answer.md
MarkdownA reviewable response using only the authorized archive.
Include: answer · evidence · source_anchors · limitations · open_questions
retrieval-review.csv
CSVAn evaluation log without unnecessary respondent-level information.
Include: question_id · artifact_id · version · relevance · access_check · claim_support · escalation
Check the result
- Verify every source anchor exists and can be accessed by the intended requester.
- Check dates, samples and populations before transferring findings to the current question.
- Inspect answers to intentionally unanswerable questions for invented certainty.
- Ensure duplicated slides or exports are not counted as independent corroboration.
When something goes wrong
OCR or extraction loses context
Return to the original artifact and preserve a manual evidence excerpt; do not answer from corrupted fragments.
Permission metadata is missing
Exclude the artifact from the shared assistant until access is resolved.
A study is replaced or corrected
Invalidate the affected index entries and reviewed answers, retaining version history.
A worked example
SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT
Request
What do prior studies say about onboarding confusion?
Inputs
Synthetic authorized study S01 covers six new administrators and reports confusion about setup ownership. S02 covers experienced operators and is restricted to another team. No quantitative churn study exists.
Expected result
Describe S01’s observed ownership confusion with its small qualitative sample. Do not disclose S02 or claim a churn percentage. Recommend a researcher follow-up for quantitative impact.
Run a small pilot
Start small
Use a small approved corpus and a mixed set of known, ambiguous and unanswerable questions.
Record the baseline
Record researcher response time and known retrieval misses.
Agree success criteria
Agree acceptable citation accuracy and unsupported-answer rates before wider use.
Stop or revise
Stop shared answering if permission filtering fails or fabricated evidence appears.
Keep the scope clear
- Archive access is not permission to expose participant-level data or restricted studies.
- Answers assist research review; they do not turn outdated or limited evidence into universal business facts.
Check before using
Check permissions, study dates, sample limits and whether evidence supports the answer.
Business activities
- Research customers and markets
- Maintain shared company knowledge
FROM A RECIPE TO YOUR WORKFLOW
Bring the company context together.
This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.
For this recipe: Approved research artifacts · Document permissions
Start with one recurring task, agree which sources to use, and review the first result with your team.
Discuss this workflow