Frequently asked questions.
Operator-level detail across onboarding, quality, billing, embedding, and trust. Everything you'd want to know before paying us, answered without marketing fluff.
Onboarding.
How do I create my first bot?
Sign up, then the onboarding wizard asks for a bot name. Once that’s saved, go to Dashboard → Sources tab and add at least one source (URL, PDF, or pasted text). When ingestion finishes (status flips to ready), the bot is live and you can grab the embed snippet from the Install tab.
Can I add multiple sources to one bot?
Yes — that’s the normal case. Free is 3 sources/bot, Starter 10, Pro 25, Business 100. The bot retrieves from all sources at once, so adding more good material almost always improves answers; adding noisy or contradictory material can hurt them.
What file types and source types are supported?
Today: public website URLs (HTTP/HTTPS), text-based PDFs uploaded to us, and plain text you paste in. We can’t ingest scanned PDFs (those need OCR — coming later) or pages that require a password to view. Sitemap-based whole-site crawl is also coming later; for now, add the important URLs one at a time.
Do you support sites that require login (auth-protected pages)?
Not yet. Our ingest only fetches what an unauthenticated visitor would see, with a 10-second timeout and up to 5 redirect hops. If your content lives behind login, the workarounds today are: export the content to a public URL, paste the raw text, or upload it as a PDF. Auth-protected crawl is a Phase 5 item — not committed.
How long does ingestion take?
Most single URLs and short PDFs finish in 10–60 seconds. Large PDFs (50+ pages) or long pages take longer because each chunk has to be embedded by OpenAI (we batch 100 chunks at a time with 1-2-4-second retry backoff if their API hiccups). If a source sticks at pending for more than 5 minutes, refresh — it’s probably already done. If it shows error, the message in the status tells you what went wrong (usually: blocked by the target site, or a scanned PDF).
Quality.
Why isn’t my bot answering correctly?
Three usual reasons. One: the information isn’t actually in your sources — add the page or paste the text that answers the question. Two: the relevant chunk doesn’t pass our similarity threshold for that exact phrasing — try asking the question the way a real visitor would, and consider rewording your source content to use the same words. Three: the bot is correctly saying "I don’t know" because the answer genuinely isn’t there — that’s the bot doing its job (better than hallucinating).
Can I edit the bot’s answers directly?
Not via a "preferred answer" override yet. The bot composes its reply from your sources at query time — so the way to change what it says is to change what it can read. Add a clearer FAQ page, paste a "house style" note, or remove a source that’s confusing it. Direct answer-editing is on the roadmap.
How do citations work?
Every answer ships with the source chunks that informed it. We retrieve the top 5 most similar chunks (cosine similarity over OpenAI’s 1536-dim embeddings, filtered to your bot), and the answer cites which ones it used. If a question can’t be answered from your sources at all, the bot says so explicitly instead of making something up — that fallback is non-negotiable.
What AI model powers the bot?
Free tier bots run Claude Haiku 4.5. Starter, Pro, and Business bots run Claude Sonnet 4.6 by default. Business owners can override to Haiku per bot (useful for high-volume, cost-sensitive flows). Opus is on the 2026 roadmap but not currently shipped. Embeddings are always OpenAI’s text-embedding-3-small.
Billing.
What’s the difference between the tiers?
Free: 1 bot, 3 sources, 50 messages/mo, locked to Haiku 4.5. Starter ($19/mo): 2 bots, 10 sources/bot, 1,000 messages/mo, Sonnet 4.6. Pro ($49/mo): 5 bots, 25 sources/bot, 3,500 messages/mo, Sonnet 4.6. Business ($199/mo): 25 bots, 100 sources/bot, 15,000 messages/mo + metered overage, Sonnet 4.6. Yearly billing on any paid tier is 10× monthly (about 17% off).
What happens when I hit my monthly message limit?
On Free, Starter, and Pro: the bot stops answering new visitors until the next billing cycle, with an upgrade hint in the error. On Business: $0.02 per extra message kicks in (capped at $200/period), so the bot keeps working through a spike. Usage resets at the start of each Dodo billing period.
Can I cancel anytime?
Yes, anytime, from the customer portal (Dashboard → Billing → Manage). Cancellation takes effect at the end of the current billing period — you keep access until then, no penalty, no contract. Your data stays accessible during that grace window.
Do you offer refunds?
If you upgrade and decide within 7 days that saavos is not right for you, email support@5minbot.com and we will refund the charge in full — no questions asked. After 7 days, cancellation stops future charges but past periods are not refunded. The Free tier exists precisely so you do not need to gamble money to evaluate.
How does overage work?
Only the Business tier has overage; on Free, Starter, and Pro the bot just pauses at the cap (no surprise bill — ever). On Business, every message above 15,000/mo is $0.02, capped at $200/period — so the maximum you can pay in one billing period is the plan price + $200. Overages are tracked server-side and will appear on your invoice. Note: automated per-message billing for Business overage is in beta — current overages are absorbed by saavos until metered billing is confirmed stable (target 2026-06).
Embed.
How do I embed the bot on my site?
Copy one <script> tag from the Install tab in the dashboard, paste it before </body> on your site. Works on any HTML site — WordPress, Webflow, Framer, Shopify, plain HTML. The widget loads asynchronously, so it doesn’t slow your page; the chat itself opens in an iframe at /embed/<your-bot> only when a visitor clicks the launcher.
Can I customize the colors and look?
Limited customization today: a primary color and the launcher position (bottom-right or bottom-left) on the dashboard’s Customize tab. Logo, full theme tokens, and CSS overrides are coming later. If you need pixel-level control before that ships, the embed iframe is just a URL — you can build your own launcher and iframe it yourself.
Does it work on mobile?
Yes. The widget is responsive — on small screens it opens full-bleed so visitors aren’t squeezed into a corner. Tested on current iOS Safari, Android Chrome, and the major in-app browsers (Instagram, LinkedIn). If you find a host site or browser where it misbehaves, send us the URL and we’ll fix it.
Do you have live chat or human handoff?
saavos is AI-only by design — we don’t run a live-chat product. When the bot can’t confidently answer (or a visitor explicitly asks for a person), the fallback routes them where you configure it: a support email, a calendar link, a help-desk URL, or a custom "we’ll get back within X hours" message. The intent is that you don’t need to sit in a chat queue. The bot handles the routine volume, the fallback handles the rest. If you actually need live agents, queue management, or shared operator inboxes, pick Crisp or Intercom — they have years of polish on that surface. saavos is built for the solo founder or 2-person team who’d rather sleep.
Trust.
Is my customer data private?
Conversation data is tenant-isolated at the database level — we use Postgres row-level security so one bot’s chats are physically unreachable from another bot’s queries, not just hidden by app code. Service-role access is restricted to the Dodo webhook handler and internal admin scripts; nothing in the user-facing app uses it. We don’t sell, share, or train models on your data, and we don’t pass your data to any model provider for training (Anthropic and OpenAI’s no-train enterprise terms apply to all calls we make on your behalf).
Are you GDPR-compliant?
Yes for the requirements we control. We store the minimum data needed to run the bot (auth email, bot config, sources you uploaded, conversation logs). You can export and delete everything from the dashboard. We’re not a Data Processor in a contractual sense yet (no signed DPA template) — if you need a DPA, email founder@5minbot.com and we’ll send one. Cookies on our marketing pages: functional only, no third-party analytics that ride in cookies.
Where is my data stored?
Application data (bots, sources, chunks, conversations): Supabase Postgres, currently in the AWS us-east-1 region. File uploads (PDFs): Supabase Storage in the same region. Embeddings are sent to OpenAI and answers to Anthropic in real time; neither provider stores prompts or completions for training under the enterprise terms we operate under. EU-region hosting is a Phase 5 item — not committed yet; if it’s a blocker for you, tell us now and it moves up the list.