> ## Documentation Index > Fetch the complete documentation index at: https://devdocs.aiconnected.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kb generator onboarding screen plan # Knowledge Base Generator — Onboarding Screen Plan The first-time user experience after login. This flow collects only the inputs the automated generation pipeline needs to build the knowledge base. The user does not wait for generation to finish — once it starts, they land in their dashboard. All review and editing of the generated output (services, AI knowledge, brand voice, conversation starters, etc.) happens later inside the dashboard. *** ## Design Principles 1. **Collect inputs, not reviews** — onboarding gathers what the pipeline needs to run; the user reviews the output from the dashboard after generation completes 2. **Don't make them wait** — generation runs in the background; get them to their dashboard fast 3. **One thing per screen** — each screen has a single clear purpose and a single primary action 4. **As few questions as possible** — only ask what the system cannot figure out on its own *** ## Flow Summary ``` Screen 1: Business Identity ↓ Screen 2: Website URL ↓ Screen 3: Additional Knowledge Sources ↓ Screen 4: Launch → Dashboard ``` The entire onboarding is 4 screens. Screens 1–3 collect input. Screen 4 kicks off the generation pipeline and sends the user straight to their dashboard. *** ## Screen 1 — Business Identity **Purpose:** Capture the core facts the generation pipeline needs as seed data — the business name, its physical location (used by the AI for accuracy and local context), and the industry category (used to select the right extraction prompts, concern maps, and industry-specific enhancements). ### Content * Headline: "Let's set up your AI" * Subhead: "Tell us a bit about your business so we can build the smartest assistant possible." * Form fields (see table below) * Primary button: "Continue" ### Fields | Field | Input Type | Required | Notes | | --------------------------- | ----------------------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `business.name` | Text input | Yes | Business name | | `business.type` | Dropdown / segmented selector | Yes | Industry category. Options: `med_spa`, `salon`, `dental`, `fitness`, `restaurant`, `retail`, `professional_services`, `other`. This drives industry-specific prompting throughout the pipeline (extraction templates, concern map presets, brand voice defaults) | | `business.location.address` | Text input | Yes | Street address | | `business.location.city` | Text input | Yes | | | `business.location.state` | Dropdown | Yes | | | `business.location.zip` | Text input | Yes | | ### Behavior * No async work starts yet — this is pure data collection. * Validation on "Continue": all required fields must be filled. * Selecting `other` for business type could optionally reveal a free-text field for the user to describe their industry. *** ## Screen 2 — Website URL **Purpose:** Collect the website that the pipeline will crawl to extract services, pricing, descriptions, contact info, and brand signals. ### Content * Headline: "What's your website?" * Subhead: "We'll scan your site to find your services, pricing, and brand voice — then use AI to build a complete knowledge base." * Single input field: URL (prefilled with `https://`) * Helper text: "We'll crawl your entire site. This works best with a live, public-facing website." * Primary button: "Continue" * Secondary link: "I don't have a website" — skips this screen (the pipeline will rely entirely on the additional sources from Screen 3 and manual entry from the dashboard) ### Fields | Field | Input Type | Required | Notes | | -------------------- | -------------- | -------------- | ---------------------------------------------------------------------------------------------------------------------------- | | `training.sourceUrl` | URL text input | No (skippable) | Validated as a well-formed URL. Does not need to be reachable at this point — the pipeline handles crawl failures gracefully | ### Behavior * No crawl starts yet. The URL is saved and passed to the pipeline on Screen 4. * If the user skips, `training.sourceUrl` is set to `null` and the pipeline adjusts accordingly (heavier reliance on uploaded documents + manual dashboard entry). *** ## Screen 3 — Additional Knowledge Sources **Purpose:** Let the user supplement the website with internal documents and external sources the crawler can't reach — pricing sheets, SOPs, training manuals, brand guides, employee handbooks, menus, etc. This is especially important if the website is thin or missing key information. ### Content * Headline: "Add extra knowledge" * Subhead: "Got documents your website doesn't cover? Upload them here so your AI knows everything. You can always add more later from the dashboard." * Three source options, displayed as a tabbed or segmented control: #### Tab A — File Upload * Drag-and-drop zone + file picker button * Accepted formats: PDF, DOCX, TXT, MD, CSV * Max file size: 25 MB per file #### Tab B — Google Drive * "Connect Google Drive" button (OAuth flow) * After connecting: file/folder picker showing the user's Drive * Selected items appear as removable chips below the picker #### Tab C — GitHub * "Connect GitHub" button (OAuth flow) * After connecting: repo/file browser * Selected items appear as removable chips below the picker ### Shared Constraint * A **shared counter** is visible at all times: **"X / 10 sources added"** * The limit of 10 is pooled across all three source types (any combination). This cap keeps generation time reasonable and reduces the chance of pipeline failure. * When 10 sources are reached, all add/upload controls disable with the message: "You've hit the 10-source limit. Remove a source to add a different one." * All added sources are listed below the tabs in a unified list showing: source icon (file/Drive/GitHub), name, size, and a remove button. ### Fields | Field | Input Type | Required | Notes | | ------------------------------ | -------------------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | `training.additionalSources[]` | File upload / OAuth picker | No | Array of up to 10 items. Each records: `type` (`file` / `gdrive` / `github`), `name`, `reference` (file path, Drive ID, or GitHub path), `sizeBytes` | ### Behavior * This screen is **entirely optional** — the user can skip it. * Primary button: "Continue" (always active, whether or not sources are added) * Secondary link: "Skip — I'll add these later" *** ## Screen 4 — Launch **Purpose:** Confirm everything, kick off the generation pipeline, and transition the user to their dashboard without waiting. ### Content * Headline: "Ready to build your AI" * Quick summary card showing what was collected: * Business name + location + industry * Website URL (or "No website provided") * Number of additional sources (or "None added") * Primary button: "Build My AI" * Microcopy below button: "This usually takes 5–10 minutes. We'll let you know when it's ready." ### Fields None. This is a review/confirmation screen. ### Behavior * Pressing "Build My AI" triggers the full automated pipeline: 1. Website crawl (Firecrawl) 2. Entity extraction (business info, services, brand signals) 3. Additional source ingestion and extraction 4. Service enhancement (education, concern mapping, self-ID triggers, FAQs, differentiators — per service) 5. Concern → service relationship mapping 6. Conversation starter generation 7. System prompt generation 8. Assessment quiz generation 9. Service guide compilation * The user is **immediately redirected to their dashboard** — they do not wait. * On the dashboard, a persistent **status card** shows real-time generation progress and updates to "Ready" with a CTA to review and test the AI when done. * An **in-app notification** (toast/banner) fires when generation completes. * An **email** is also sent: "Your AI assistant is ready." *** ## Screen Map at a Glance | # | Screen | User Does | Fields Collected | | - | ------------------ | --------------------------------------------------- | ------------------------------------------------------- | | 1 | Business Identity | Enters name, location, selects industry | `business.name`, `business.type`, `business.location.*` | | 2 | Website URL | Enters URL (or skips) | `training.sourceUrl` | | 3 | Additional Sources | Uploads files / connects Drive or GitHub (or skips) | `training.additionalSources[]` | | 4 | Launch | Reviews summary, clicks "Build My AI" | None — triggers pipeline and redirects to dashboard | **Total user inputs: 7 fields + 1 optional URL + up to 10 optional source uploads.** *** ## What Happens After Onboarding Everything the previous spec described as onboarding review screens (service list review, AI knowledge editing, brand voice tuning, conversation starter customization) becomes available **inside the dashboard** once generation completes. The dashboard surfaces these through a guided "Review Your AI" experience attached to the status card — same content, but the user engages with it on their own time, not as a gate before they can use the platform. *** ## Data Model Addition The new `additionalSources` field to be added to the knowledge base schema: ```javascript theme={null} training: { sourceUrl: "https://example.com", // or null if skipped crawledAt: "2026-03-10T...", pagesAnalyzed: 24, lastUpdated: "2026-03-10T...", version: 1, // NEW additionalSources: [ { type: "file", // "file" | "gdrive" | "github" name: "pricing-sheet-2026.pdf", reference: "/uploads/abc123.pdf", // internal path, Drive file ID, or GitHub path sizeBytes: 245000, status: "processed", // "pending" | "processing" | "processed" | "failed" addedAt: "2026-03-10T..." } // ... up to 10 items total ] } ```