Skip to content
AskVault Docs
Try Free →

Q&A pairs in AskVault knowledge management

Written by , Founder, AskVault · Reviewed by Aashiq
Last updated: · 4 min read

What Q&A pairs are

Most AskVault knowledge comes from crawled documents or uploaded files. Q&A pairs are different. They're hand-curated question-answer entries that the bot prefers over retrieval-based answers.

Three patterns where Q&A pairs fit:

  1. Tribal knowledge that never made it into a doc. "What's our policy on bringing pets to work?" might never have been written down. A Q&A pair captures it.
  2. Overriding ambiguous content. Your docs say two different things about refund timelines. A Q&A pair resolves the canonical answer.
  3. Frequently-misanswered questions. The bot keeps getting a question wrong because retrieval finds a slightly-related chunk. A Q&A pair forces the right answer.

Q&A pairs are higher-priority than crawled documents. When a customer's question matches a Q&A pair within 90% similarity, the bot uses the pair's answer verbatim. Below that threshold, the bot falls back to standard retrieval.

Setup

Two ways to create Q&A pairs.

Manual entry

  1. Open Knowledge > Add Source > Q&A Pairs in AskVault.
  2. Click Add Pair.
  3. Enter the question and answer. Question is what a customer would type; answer is what the bot should say.
  4. Optionally add audience tags.
  5. Save.

The new pair indexes within seconds. Test it by asking the bot the exact question (or a paraphrase). Should get the pair's answer verbatim.

Auto-generation from existing content

For workspaces with substantial indexed content (50+ documents), AskVault can auto-generate Q&A pairs:

  1. Knowledge > Q&A Pairs > Auto-generate.
  2. Pick how many to generate. Default 25; up to 500 per run on Business.
  3. Click Generate.

AskVault scans your indexed content and produces candidate Q&A pairs covering the most common topics. Review and approve before they go live. Useful when you've imported a lot of content and want to surface the high-traffic questions.

Auto-generation counts against your monthly query quota. Generating 100 pairs uses about 100 queries.

Q&A pair structure

Each pair has:

  • Question. What the customer asks. Phrase it naturally, the way a real customer would type it.
  • Answer. What the bot says. Markdown supported. Length usually 50 to 300 words.
  • Synonym questions (optional). Alternative phrasings of the same question. Improves match rate.
  • Audience tags (optional). Restrict to specific verified users.
  • Source URL (optional). A URL the bot cites alongside the answer.

Synonym questions are underrated. Adding 3 to 5 variations per pair lifts match rate noticeably. Example:

  • Primary: "What's your refund policy?"
  • Synonyms: "Can I get my money back?", "How do I request a refund?", "Are refunds available?"

Retrieval priority

When a customer's question comes in, AskVault evaluates in this order:

  1. Q&A pair match (90%+ similarity). If matched, use the pair's answer verbatim.
  2. Q&A pair match (70 to 89% similarity). Use the pair's answer as the primary source, augmented with retrieval from other content.
  3. Standard retrieval. Q&A pairs treated as one source among many.

The 90%+ threshold ensures the bot uses curated answers for clear matches without overriding for tangentially-related questions.

Configure the thresholds under Knowledge > Q&A Pairs > Settings > Match Thresholds.

When NOT to use Q&A pairs

Three patterns where Q&A pairs are the wrong tool:

  • The answer changes over time. Pricing, contact info, support hours. These should live in your docs and be re-crawled regularly, not in static Q&A pairs.
  • The answer is long. Q&A pairs work best for short, factual answers. For multi-paragraph explanations, write a doc and let retrieval handle it.
  • You'd write hundreds of pairs. If you have 200+ Q&A pairs, you're better off writing a FAQ doc and letting retrieval work. Q&A pairs are for the top 20 to 50 questions; beyond that, retrieval scales better.

Limits

  • Per-workspace cap. 100 Q&A pairs on Free, 500 on Starter, 1,500 on Growth, 5,000 on Business.
  • Per-pair length. Question up to 500 characters, answer up to 2,000 characters.
  • Synonym count. Up to 10 synonyms per pair.

Combining with FAQ Builder

The FAQ Builder (under Dashboard > FAQ Builder) is a separate feature that builds a public FAQ page from Q&A pairs. Use it when you want the same Q&A content to surface as both bot answers and a static FAQ page on your site.

Configure under Dashboard > FAQ Builder > Source = Q&A Pairs. Growth+

Common pitfalls

Bot doesn't pick the right Q&A pair. Customer's phrasing is too different from the pair's question. Add synonyms.

Q&A pair answer is outdated. Edit the pair directly under Knowledge > Q&A Pairs > [pair] > Edit. Changes apply within seconds.

Auto-generated pairs are low quality. The auto-generator works from your indexed content. If your content is thin, the generated pairs will be thin. Better to write a few high-quality pairs by hand than to bulk-generate dozens of weak ones.

Conflicting answers between Q&A pair and document. The pair wins on high-similarity match. The retrieval-based answer wins on lower-similarity match. If you have a conflict, update both to agree.

FAQ

Are Q&A pairs better than crawled docs?

Different tools. Q&A pairs are for the high-traffic top-20 questions you want guaranteed-correct answers on. Crawled docs are for the long tail. Use both.

Can I import Q&A pairs from a CSV?

Yes. CSV columns: question, answer, synonyms (semicolon-separated), audience (semicolon-separated), source_url. Upload under Knowledge > Q&A Pairs > Import CSV.

Do Q&A pairs count toward my content storage cap?

Marginally. Each pair is about 1 to 3 KB. 1,000 pairs = 1 to 3 MB.

Can the bot generate a new Q&A pair when a knowledge gap is detected?

Not automatically. The knowledge.gap_detected webhook flags gaps for human review. Your team writes the Q&A pair that fixes the gap.

How do I see which Q&A pairs are matching most often?

Analytics > Q&A Pair Usage shows match counts and helpful-vote rates per pair. Useful for refining synonyms or rewording answers.

Was this page helpful?