# Frequently asked questions > Answers to the most common questions about Bookbag — what it is, how it stays accurate, what it costs, the channels and languages it supports, security and data handling, bring-your-own keys, and migrating from Chatbase. Quick answers to the questions we hear most. If you don't find what you need here, the section docs go deeper — start with [Getting started](/docs/getting-started/introduction). ## About Bookbag **What is Bookbag?** Bookbag is an AI customer-support platform built for ecommerce. You connect your store's knowledge — help center, product data, policies, past tickets — and Bookbag builds an AI agent that resolves customer questions 24/7 across chat, email, and social. Every answer is grounded in sources you control. See the [introduction](/docs/getting-started/introduction). **How is it different from a generic chatbot?** A generic chatbot guesses from its training data. A Bookbag agent answers **only from your real data** using retrieval-augmented generation, with citations back to the sources used — so it resolves order, returns, shipping, and product questions accurately instead of making things up. **What can a Bookbag agent do besides answer questions?** It can take real actions — collect leads, escalate to a human, look up an order, or call your own API. It can run a full help desk (tickets, assignment, takeover, saved views), reach out proactively with outbound campaigns, and render interactive [widgets](/docs/widgets/overview) like order cards and product carousels inside the chat. **Do I need to be technical to use it?** No. You can describe your agent in plain language and the builder drafts the prompt and settings, crawl your website to train it, and paste a one-line snippet to deploy. Developers get a full [REST API](/docs/api/overview) and webhooks when they want them. ## Accuracy & hallucinations **How does Bookbag avoid making things up?** When a customer asks something, Bookbag first **retrieves** the most relevant chunks from your indexed sources, then asks the model to answer using only those chunks. The facts come from your data, not the model's imagination. See [Response quality](/docs/getting-started/response-quality). **What happens when the agent doesn't know the answer?** A well-configured agent says it doesn't know and offers to connect the customer with a human, rather than guessing. You set the fallback message and can pair it with the [Escalate to a human](/docs/actions/escalate-to-human) action so the conversation lands in your help desk. **Can I guarantee an exact answer for high-stakes questions?** Yes — add a **Q&A pair**. Q&A sources take priority over crawled text, so for refund windows, warranties, and shipping promises, the exact wording you approve is what customers get. See [Best practices](/docs/getting-started/best-practices). **How do I measure my agent's accuracy?** Two ways: **Analytics** tracks resolution rate and escalation trends over time, and the free [Support Audit](/docs/audit/overview) scores transcripts for hallucination rate, policy violations, quality, and resolution. ## Data sources & training **What can I train my agent on?** Crawl your website, upload files (PDFs, docs, spreadsheets), paste text snippets, or write Q&A pairs. Bookbag chunks and embeds each source into a vector index. See [Data sources](/docs/agents/data-sources). **How do I keep the agent's knowledge current?** Re-crawl or re-upload when your content changes; on higher plans you can schedule automatic retraining. Stale data is the most common cause of wrong answers, so refresh sources when policies change. **How many sources can I add?** It depends on your plan — from 10 sources per agent on Free up to thousands on Pro, and unlimited on Enterprise. See [Plans & billing](/docs/workspace/billing). ## Pricing & credits **How much does Bookbag cost?** There are five plans — **Free, Hobby, Standard, Pro, and Enterprise** — each with a monthly credit allotment and its own limits on agents, seats, and channels. See [Plans & billing](/docs/workspace/billing) and the [pricing page](/pricing) for current prices. **Is there a free plan?** Yes. The Free plan includes 100 monthly credits, one agent, and the website widget plus API, so you can build and test a grounded agent end to end at no cost. **What is a credit?** A credit is the unit of usage. Each AI reply costs credits based on the model it uses, so cheaper, faster models stretch your allotment further. Your plan refreshes a monthly allotment, and you can see usage and remaining balance in billing. See [Credits & usage](/docs/agents/credits). **What happens if I run out of credits?** You can upgrade your plan or enable **auto-recharge**, which tops up your balance automatically when it drops below a threshold you set. See [Plans & billing](/docs/workspace/billing). ## Channels **Where can my agent answer?** A single agent can answer across a website widget, email, WhatsApp, Slack, Instagram, and Facebook Messenger — consistently, from the same knowledge. See [Deploy & channels](/docs/deploy/overview). **How do I add the chat widget to my store?** Copy the one-line embed snippet from Deploy → Website widget and paste it before the closing body tag in your theme (on Shopify, that's theme.liquid). See [Website widget](/docs/deploy/web-widget). **Are all channels available on every plan?** No. Free includes the website widget and API; Hobby adds Slack and email; Standard adds WhatsApp, Messenger, and Instagram; Pro and Enterprise include all channels. See [Plans & billing](/docs/workspace/billing). ## Security & data handling **Who can see my workspace data?** Only members of your workspace, scoped by their role — Owner, Admin, Editor, or Viewer. Roles control exactly what each teammate can see and change. See [Members & roles](/docs/workspace/members). **Is the agent limited to my data?** Yes. Grounded answers come only from the sources you add, with citations you can inspect. You control the system prompt and guardrails that tell the agent what it must never do — invent policy, prices, or order details. **Can the agent expose sensitive information?** You set guardrails to prevent it. The [Support Audit](/docs/audit/overview) also flags policy issues like PII exposure in existing transcripts so you can close those gaps before deploying. **Can I self-host Bookbag?** Yes — Bookbag has an open-source build you can run yourself, with unlimited local entitlements and no metered billing. The hosted cloud handles credits, billing, and scaling for you. ## Models & bring-your-own keys **Which AI models can I use?** Bookbag supports multiple models (including OpenAI and Anthropic families). You pick the model per agent from a dropdown, balancing speed, cost, and reasoning ability. See [Models & model choice](/docs/agents/models). **Can I bring my own API key?** Yes. With **bring-your-own keys** enabled for your workspace, your agents run on your own provider key and those replies aren't metered against your Bookbag credits. See [Bring your own API keys](/docs/agents/byo-keys). **How do per-model costs work?** Each model has a configured credit cost per reply. Cheaper models consume fewer credits, so routing routine questions to a fast model and reserving a larger model for complex cases keeps usage efficient. See [Credits & usage](/docs/agents/credits). ## Languages **Does Bookbag support multiple languages?** Yes. The underlying models are multilingual, so your agent can understand and reply in many languages. Provide knowledge in the languages your customers use for the most accurate, grounded answers. **Can my help desk translate conversations?** Yes — the help desk includes translation so your team can read and reply across languages. See [Help Desk → Translation](/docs/help-desk/translation). ## Getting started **How do I create my first agent?** Follow the [first-agent walkthrough](/docs/getting-started/your-first-agent): create an agent, add data sources, test it in the playground, and deploy the widget — about ten minutes end to end. **Can I try it before signing up?** Yes. The [live trial](https://app.bookbag.ai/try) spins up a working agent on your own website in under a minute — paste your URL, we crawl it, and you can chat with a grounded agent immediately, no account required. **How do I add my team?** Invite teammates by email and assign a role. Existing Bookbag users join immediately; new emails get a pending invitation that expires after 24 hours. See [Invitations](/docs/workspace/invitations). ## Migrating from Chatbase **I use Chatbase today — is Bookbag a drop-in replacement?** Bookbag covers the same core surface — grounded agents, data sources, a playground, deployable widget, actions, and contacts — and adds ecommerce-focused features like a full help desk, outbound campaigns, interactive widgets, and a free support audit. You can rebuild your agent in minutes by re-crawling the same sources. **Should I audit my current Chatbase bot first?** Yes — that's exactly what the free [Support Audit](/docs/audit/overview) is for. Paste your current bot's transcripts, get a scored report on hallucinations, policy violations, quality, and resolution, and use it as a baseline to measure the improvement after switching. **How do roles map from Chatbase?** Chatbase's "Member" maps to Bookbag's **Editor**. Bookbag adds a distinct read-only **Viewer** role for stakeholders. See [Members & roles](/docs/workspace/members). **Can I keep using my own model keys after migrating?** Yes. Enable [bring-your-own keys](/docs/agents/byo-keys) so your agents run on your provider key, just as you may already do elsewhere. ## Still need help? - [Getting started](/docs/getting-started/introduction) — Build and deploy your first grounded agent. - [Response quality](/docs/getting-started/response-quality) — How Bookbag keeps answers accurate and trustworthy. - [Run a support audit](/docs/audit/overview) — Score your current support for free, no signup.