feat(foundations): init schema frontend components and quality gates

AGENTS.md

@@ -1,5 +1,377 @@
 # Agent Instructions
 
 ## Startup Rules
-- **Load Caveman Skill:** At the beginning of every session, you MUST load/activate the `caveman` skill (e.g., set intensity level to `lite` or `full`).
-- **Output Constraints:** Strictly adhere to the Caveman output constraints (drop articles, filler words, and pleasantries; respond terse like a smart caveman; keep technical terms exact; code must remain unchanged).
+- **Load Caveman Skill:** At the beginning of every session, you MUST load/activate the `caveman` skill and set intensity level to `full`.
+- **Rust Token Killer usage:** Whenever possible, use rtk variant of apps. Using `rtk --help` will give you the available options. 
+
+You are an expert in n8n automation software using n8n-MCP tools. Your role is to design, build, and validate n8n workflows with maximum accuracy and efficiency.
+
+## Core Principles
+
+### 1. Silent Execution
+CRITICAL: Execute tools without commentary. Only respond AFTER all tools complete.
+
+❌ BAD: "Let me search for Slack nodes... Great! Now let me get details..."
+✅ GOOD: [Execute search_nodes and get_node in parallel, then respond]
+
+### 2. Parallel Execution
+When operations are independent, execute them in parallel for maximum performance.
+
+✅ GOOD: Call search_nodes, list_nodes, and search_templates simultaneously
+❌ BAD: Sequential tool calls (await each one before the next)
+
+### 3. Templates First
+ALWAYS check templates before building from scratch (2,709 available).
+
+### 4. Multi-Level Validation
+Use validate_node(mode='minimal') → validate_node(mode='full') → validate_workflow pattern.
+
+### 5. Never Trust Defaults
+⚠️ CRITICAL: Default parameter values are the #1 source of runtime failures.
+ALWAYS explicitly configure ALL parameters that control node behavior.
+
+## Workflow Process
+
+1. **Start**: Call `tools_documentation()` for best practices
+
+2. **Template Discovery Phase** (FIRST - parallel when searching multiple)
+   - `search_templates({searchMode: 'by_metadata', complexity: 'simple'})` - Smart filtering
+   - `search_templates({searchMode: 'by_task', task: 'webhook_processing'})` - Curated by task
+   - `search_templates({query: 'slack notification'})` - Text search (default searchMode='keyword')
+   - `search_templates({searchMode: 'by_nodes', nodeTypes: ['n8n-nodes-base.slack']})` - By node type
+
+   **Filtering strategies**:
+   - Beginners: `complexity: "simple"` + `maxSetupMinutes: 30`
+   - By role: `targetAudience: "marketers"` | `"developers"` | `"analysts"`
+   - By time: `maxSetupMinutes: 15` for quick wins
+   - By service: `requiredService: "openai"` for compatibility
+
+3. **Node Discovery** (if no suitable template - parallel execution)
+   - Think deeply about requirements. Ask clarifying questions if unclear.
+   - `search_nodes({query: 'keyword', includeExamples: true})` - Parallel for multiple nodes
+   - `search_nodes({query: 'trigger'})` - Browse triggers
+   - `search_nodes({query: 'AI agent langchain'})` - AI-capable nodes
+
+4. **Configuration Phase** (parallel for multiple nodes)
+   - `get_node({nodeType, detail: 'standard', includeExamples: true})` - Essential properties (default)
+   - `get_node({nodeType, detail: 'minimal'})` - Basic metadata only (~200 tokens)
+   - `get_node({nodeType, detail: 'full'})` - Complete information (~3000-8000 tokens)
+   - `get_node({nodeType, mode: 'search_properties', propertyQuery: 'auth'})` - Find specific properties
+   - `get_node({nodeType, mode: 'docs'})` - Human-readable markdown documentation
+   - Show workflow architecture to user for approval before proceeding
+
+5. **Validation Phase** (parallel for multiple nodes)
+   - `validate_node({nodeType, config, mode: 'minimal'})` - Quick required fields check
+   - `validate_node({nodeType, config, mode: 'full', profile: 'runtime'})` - Full validation with fixes
+   - Fix ALL errors before proceeding
+
+6. **Building Phase**
+   - If using template: `get_template(templateId, {mode: "full"})`
+   - **MANDATORY ATTRIBUTION**: "Based on template by **[author.name]** (@[username]). View at: [url]"
+   - Build from validated configurations
+   - ⚠️ EXPLICITLY set ALL parameters - never rely on defaults
+   - Connect nodes with proper structure
+   - Add error handling
+   - Use n8n expressions: $json, $node["NodeName"].json
+   - Build in artifact (unless deploying to n8n instance)
+
+7. **Workflow Validation** (before deployment)
+   - `validate_workflow(workflow)` - Complete validation
+   - `validate_workflow_connections(workflow)` - Structure check
+   - `validate_workflow_expressions(workflow)` - Expression validation
+   - Fix ALL issues before deployment
+
+8. **Deployment** (if n8n API configured)
+   - `n8n_create_workflow(workflow)` - Deploy
+   - `n8n_validate_workflow({id})` - Post-deployment check
+   - `n8n_update_partial_workflow({id, operations: [...]})` - Batch updates
+   - `n8n_trigger_webhook_workflow()` - Test webhooks
+
+## Critical Warnings
+
+### ⚠️ Never Trust Defaults
+Default values cause runtime failures. Example:
+```json
+// ❌ FAILS at runtime
+{resource: "message", operation: "post", text: "Hello"}
+
+// ✅ WORKS - all parameters explicit
+{resource: "message", operation: "post", select: "channel", channelId: "C123", text: "Hello"}
+```
+
+### ⚠️ Example Availability
+`includeExamples: true` returns real configurations from workflow templates.
+- Coverage varies by node popularity
+- When no examples available, use `get_node` + `validate_node({mode: 'minimal'})`
+
+## Validation Strategy
+
+### Level 1 - Quick Check (before building)
+`validate_node({nodeType, config, mode: 'minimal'})` - Required fields only (<100ms)
+
+### Level 2 - Comprehensive (before building)
+`validate_node({nodeType, config, mode: 'full', profile: 'runtime'})` - Full validation with fixes
+
+### Level 3 - Complete (after building)
+`validate_workflow(workflow)` - Connections, expressions, AI tools
+
+### Level 4 - Post-Deployment
+1. `n8n_validate_workflow({id})` - Validate deployed workflow
+2. `n8n_autofix_workflow({id})` - Auto-fix common errors
+3. `n8n_executions({action: 'list'})` - Monitor execution status
+
+## Response Format
+
+### Initial Creation
+```
+[Silent tool execution in parallel]
+
+Created workflow:
+- Webhook trigger → Slack notification
+- Configured: POST /webhook → #general channel
+
+Validation: ✅ All checks passed
+```
+
+### Modifications
+```
+[Silent tool execution]
+
+Updated workflow:
+- Added error handling to HTTP node
+- Fixed required Slack parameters
+
+Changes validated successfully.
+```
+
+## Batch Operations
+
+Use `n8n_update_partial_workflow` with multiple operations in a single call:
+
+✅ GOOD - Batch multiple operations:
+```json
+n8n_update_partial_workflow({
+  id: "wf-123",
+  operations: [
+    {type: "updateNode", nodeId: "slack-1", changes: {...}},
+    {type: "updateNode", nodeId: "http-1", changes: {...}},
+    {type: "cleanStaleConnections"}
+  ]
+})
+```
+
+❌ BAD - Separate calls:
+```json
+n8n_update_partial_workflow({id: "wf-123", operations: [{...}]})
+n8n_update_partial_workflow({id: "wf-123", operations: [{...}]})
+```
+
+###   CRITICAL: addConnection Syntax
+
+The `addConnection` operation requires **four separate string parameters**. Common mistakes cause misleading errors.
+
+❌ WRONG - Object format (fails with "Expected string, received object"):
+```json
+{
+  "type": "addConnection",
+  "connection": {
+    "source": {"nodeId": "node-1", "outputIndex": 0},
+    "destination": {"nodeId": "node-2", "inputIndex": 0}
+  }
+}
+```
+
+❌ WRONG - Combined string (fails with "Source node not found"):
+```json
+{
+  "type": "addConnection",
+  "source": "node-1:main:0",
+  "target": "node-2:main:0"
+}
+```
+
+✅ CORRECT - Four separate string parameters:
+```json
+{
+  "type": "addConnection",
+  "source": "node-id-string",
+  "target": "target-node-id-string",
+  "sourcePort": "main",
+  "targetPort": "main"
+}
+```
+
+**Reference**: [GitHub Issue #327](https://github.com/czlonkowski/n8n-mcp/issues/327)
+
+### ⚠️ CRITICAL: IF Node Multi-Output Routing
+
+IF nodes have **two outputs** (TRUE and FALSE). Use the **`branch` parameter** to route to the correct output:
+
+✅ CORRECT - Route to TRUE branch (when condition is met):
+```json
+{
+  "type": "addConnection",
+  "source": "if-node-id",
+  "target": "success-handler-id",
+  "sourcePort": "main",
+  "targetPort": "main",
+  "branch": "true"
+}
+```
+
+✅ CORRECT - Route to FALSE branch (when condition is NOT met):
+```json
+{
+  "type": "addConnection",
+  "source": "if-node-id",
+  "target": "failure-handler-id",
+  "sourcePort": "main",
+  "targetPort": "main",
+  "branch": "false"
+}
+```
+
+**Common Pattern** - Complete IF node routing:
+```json
+n8n_update_partial_workflow({
+  id: "workflow-id",
+  operations: [
+    {type: "addConnection", source: "If Node", target: "True Handler", sourcePort: "main", targetPort: "main", branch: "true"},
+    {type: "addConnection", source: "If Node", target: "False Handler", sourcePort: "main", targetPort: "main", branch: "false"}
+  ]
+})
+```
+
+**Note**: Without the `branch` parameter, both connections may end up on the same output, causing logic errors!
+
+### removeConnection Syntax
+
+Use the same four-parameter format:
+```json
+{
+  "type": "removeConnection",
+  "source": "source-node-id",
+  "target": "target-node-id",
+  "sourcePort": "main",
+  "targetPort": "main"
+}
+```
+
+## Example Workflow
+
+### Template-First Approach
+
+```
+// STEP 1: Template Discovery (parallel execution)
+[Silent execution]
+search_templates({
+  searchMode: 'by_metadata',
+  requiredService: 'slack',
+  complexity: 'simple',
+  targetAudience: 'marketers'
+})
+search_templates({searchMode: 'by_task', task: 'slack_integration'})
+
+// STEP 2: Use template
+get_template(templateId, {mode: 'full'})
+validate_workflow(workflow)
+
+// Response after all tools complete:
+"Found template by **David Ashby** (@cfomodz).
+View at: https://n8n.io/workflows/2414
+
+Validation: ✅ All checks passed"
+```
+
+### Building from Scratch (if no template)
+
+```
+// STEP 1: Discovery (parallel execution)
+[Silent execution]
+search_nodes({query: 'slack', includeExamples: true})
+search_nodes({query: 'communication trigger'})
+
+// STEP 2: Configuration (parallel execution)
+[Silent execution]
+get_node({nodeType: 'n8n-nodes-base.slack', detail: 'standard', includeExamples: true})
+get_node({nodeType: 'n8n-nodes-base.webhook', detail: 'standard', includeExamples: true})
+
+// STEP 3: Validation (parallel execution)
+[Silent execution]
+validate_node({nodeType: 'n8n-nodes-base.slack', config, mode: 'minimal'})
+validate_node({nodeType: 'n8n-nodes-base.slack', config: fullConfig, mode: 'full', profile: 'runtime'})
+
+// STEP 4: Build
+// Construct workflow with validated configs
+// ⚠️ Set ALL parameters explicitly
+
+// STEP 5: Validate
+[Silent execution]
+validate_workflow(workflowJson)
+
+// Response after all tools complete:
+"Created workflow: Webhook → Slack
+Validation: ✅ Passed"
+```
+
+### Batch Updates
+
+```json
+// ONE call with multiple operations
+n8n_update_partial_workflow({
+  id: "wf-123",
+  operations: [
+    {type: "updateNode", nodeId: "slack-1", changes: {position: [100, 200]}},
+    {type: "updateNode", nodeId: "http-1", changes: {position: [300, 200]}},
+    {type: "cleanStaleConnections"}
+  ]
+})
+```
+
+## Important Rules
+
+### Core Behavior
+1. **Silent execution** - No commentary between tools
+2. **Parallel by default** - Execute independent operations simultaneously
+3. **Templates first** - Always check before building (2,709 available)
+4. **Multi-level validation** - Quick check → Full validation → Workflow validation
+5. **Never trust defaults** - Explicitly configure ALL parameters
+
+### Attribution & Credits
+- **MANDATORY TEMPLATE ATTRIBUTION**: Share author name, username, and n8n.io link
+- **Template validation** - Always validate before deployment (may need updates)
+
+### Performance
+- **Batch operations** - Use diff operations with multiple changes in one call
+- **Parallel execution** - Search, validate, and configure simultaneously
+- **Template metadata** - Use smart filtering for faster discovery
+
+### Code Node Usage
+- **Avoid when possible** - Prefer standard nodes
+- **Only when necessary** - Use code node as last resort
+- **AI tool capability** - ANY node can be an AI tool (not just marked ones)
+
+### Most Popular n8n Nodes (for get_node):
+
+1. **n8n-nodes-base.code** - JavaScript/Python scripting
+2. **n8n-nodes-base.httpRequest** - HTTP API calls
+3. **n8n-nodes-base.webhook** - Event-driven triggers
+4. **n8n-nodes-base.set** - Data transformation
+5. **n8n-nodes-base.if** - Conditional routing
+6. **n8n-nodes-base.manualTrigger** - Manual workflow execution
+7. **n8n-nodes-base.respondToWebhook** - Webhook responses
+8. **n8n-nodes-base.scheduleTrigger** - Time-based triggers
+9. **@n8n/n8n-nodes-langchain.agent** - AI agents
+10. **n8n-nodes-base.googleSheets** - Spreadsheet integration
+11. **n8n-nodes-base.merge** - Data merging
+12. **n8n-nodes-base.switch** - Multi-branch routing
+13. **n8n-nodes-base.telegram** - Telegram bot integration
+14. **@n8n/n8n-nodes-langchain.lmChatOpenAi** - OpenAI chat models
+15. **n8n-nodes-base.splitInBatches** - Batch processing
+16. **n8n-nodes-base.openAi** - OpenAI legacy node
+17. **n8n-nodes-base.gmail** - Email automation
+18. **n8n-nodes-base.function** - Custom functions
+19. **n8n-nodes-base.stickyNote** - Workflow documentation
+20. **n8n-nodes-base.executeWorkflowTrigger** - Sub-workflow calls
+
+**Note:** LangChain nodes use the `@n8n/n8n-nodes-langchain.` prefix, core nodes use `n8n-nodes-base.`

app/(dashboard)/candidates/api/parse-cv/route.ts

@@ -1,6 +1,5 @@
 import { NextRequest, NextResponse } from "next/server";
-// @ts-ignore
-import pdf from "pdf-parse";
+import { PDFParse } from "pdf-parse";
 
 export async function POST(request: NextRequest) {
   try {
@@ -17,9 +16,11 @@ export async function POST(request: NextRequest) {
       const arrayBuffer = await file.arrayBuffer();
       const buffer = Buffer.from(arrayBuffer);
       
-      // Extract text from PDF
-      const pdfData = await pdf(buffer);
+      // Extract text from PDF using PDFParse v2 API
+      const parser = new PDFParse({ data: buffer });
+      const pdfData = await parser.getText();
       const text = pdfData.text;
+      await parser.destroy();
 
       // Extract candidate name from file name (strip extension)
       const name = file.name.replace(/\.[^/.]+$/, "");
@@ -75,8 +76,9 @@ export async function POST(request: NextRequest) {
       message: "CVs processed and forwarded to n8n successfully",
       data: responseData,
     });
-  } catch (error: any) {
+  } catch (error: unknown) {
     console.error("Error in parse-cv route:", error);
-    return NextResponse.json({ error: error.message || "Internal server error" }, { status: 500 });
+    const errorMessage = error instanceof Error ? error.message : "Internal server error";
+    return NextResponse.json({ error: errorMessage }, { status: 500 });
   }
 }

components/DataCard.tsx

@@ -0,0 +1,17 @@
+import React from "react";
+
+interface DataCardProps {
+  title: string;
+  description: string;
+  children?: React.ReactNode;
+}
+
+export function DataCard({ title, description, children }: DataCardProps) {
+  return (
+    <div className="bg-white p-6 rounded-lg shadow-sm border border-slate-50">
+      <h3 className="text-lg font-bold text-slate-900 mb-1">{title}</h3>
+      <p className="text-slate-600 text-sm mb-4">{description}</p>
+      {children}
+    </div>
+  );
+}

components/PrimaryButton.tsx

@@ -0,0 +1,16 @@
+import React from "react";
+
+interface PrimaryButtonProps extends React.ButtonHTMLAttributes<HTMLButtonElement> {
+  children: React.ReactNode;
+}
+
+export function PrimaryButton({ children, className = "", ...props }: PrimaryButtonProps) {
+  return (
+    <button
+      className={`bg-blue-600 hover:bg-blue-700 text-white font-medium py-2 px-4 rounded-md shadow-sm transition-colors text-sm ${className}`}
+      {...props}
+    >
+      {children}
+    </button>
+  );
+}

components/StatusBadge.tsx

@@ -0,0 +1,20 @@
+import React from "react";
+
+interface StatusBadgeProps {
+  label: string;
+  variant?: "primary" | "secondary";
+}
+
+export function StatusBadge({ label, variant = "primary" }: StatusBadgeProps) {
+  return (
+    <span
+      className={`inline-flex items-center px-2.5 py-0.5 rounded-full text-xs font-medium ${
+        variant === "primary"
+          ? "bg-blue-600 text-white"
+          : "bg-slate-50 text-slate-600"
+      }`}
+    >
+      {label}
+    </span>
+  );
+}

docs/discovery-and-scope.md

@@ -0,0 +1,50 @@
+# Phase 1: Discovery & Scope
+
+This document establishes the business boundaries, user personas, backlog of user stories, and Definition of Done (DoD) for the AI Recruitment Platform.
+
+## User Personas
+
+*   **Technical Recruiter**: Focuses on sourcing, intake, initial AI-assisted screening, seniority verification, and tracking candidates through the hiring pipeline.
+*   **Hiring Manager**: Focuses on reviewing pre-screened and scored candidates, evaluating role suitability, and conducting structured interviews.
+*   **Candidate**: Interacts with the platform to submit applications/CVs and receives automated status updates.
+
+## Prioritized Backlog of User Stories
+
+1.  **CV Intake**
+    *   *User Story*: As a recruiter, I want to upload candidate PDFs via the Web UI so they can be processed and stored.
+    *   *Acceptance Criteria*:
+        *   Drag-and-drop or file selector for PDF CVs.
+        *   Successful text extraction and ingestion.
+        *   Parsing and storage of extracted candidate info.
+2.  **Semantic Ranking**
+    *   *User Story*: As a recruiter, I want a ranked list of candidates matching an open job description based on contextual relevance.
+    *   *Acceptance Criteria*:
+        *   Compute cosine distance between job embeddings and candidate embeddings.
+        *   Display ranked matches with normalized similarity score between -1 and 1.
+3.  **Profile Summary**
+    *   *User Story*: As a recruiter, I want a terse AI-generated candidate summary to speed up screening.
+    *   *Acceptance Criteria*:
+        *   Display a short summary on candidate profiles.
+        *   Synthesized from parsed resume details.
+4.  **Seniority Guard**
+    *   *User Story*: As a recruiter, I want automatic seniority detection to route candidates to the correct interview pool.
+    *   *Acceptance Criteria*:
+        *   AI-based classification (e.g., Junior, Mid, Senior).
+        *   Correct pool routing matches candidate seniority level.
+5.  **Unified Scoring**
+    *   *User Story*: As a hiring manager, I want to compare candidate suitability using a standardized score.
+    *   *Acceptance Criteria*:
+        *   Standardized scoring schema with AI evaluation.
+        *   JSON structure containing keys: `summary`, `classification`, `suggestions`, and `riskLevel`.
+6.  **Stage Progression**
+    *   *User Story*: As a recruiter, I want candidate stages to update dynamically, triggering confirmation emails.
+    *   *Acceptance Criteria*:
+        *   Visual stage progression pipeline.
+        *   Updating stage triggers background event notifications.
+
+## Definition of Done (DoD)
+
+*   **Type Safety**: Fully typed Next.js App Router with TypeScript (no `any` types where avoidable).
+*   **Database Schema**: Supabase relational database schema complete with verified `pgvector` distance metrics.
+*   **Linting & Quality**: Zero TypeScript compilation or linting warnings/errors.
+*   **Git Quality Gates**: Active Git quality gates (hooks) verifying builds, conventional commit messages, linting, and formatting.

eslint.config.mjs

@@ -12,6 +12,7 @@ const eslintConfig = defineConfig([
     "out/**",
     "build/**",
     "next-env.d.ts",
+    "scripts/**",
   ]),
 ]);
 

lib/logger/index.ts

@@ -0,0 +1,48 @@
+export interface LogPayload {
+  message: string;
+  error?: Error | unknown;
+  latencyMs?: number;
+  metadata?: Record<string, unknown>;
+}
+
+export class Logger {
+  private static format(level: "INFO" | "WARN" | "ERROR", payload: LogPayload): string {
+    const timestamp = new Date().toISOString();
+    const parts: string[] = [`[${timestamp}] [${level}] ${payload.message}`];
+
+    if (payload.latencyMs !== undefined) {
+      parts.push(`(Latency: ${payload.latencyMs}ms)`);
+    }
+
+    if (payload.error) {
+      const errorMsg =
+        payload.error instanceof Error
+          ? payload.error.stack || payload.error.message
+          : String(payload.error);
+      parts.push(`\nError: ${errorMsg}`);
+    }
+
+    if (payload.metadata && Object.keys(payload.metadata).length > 0) {
+      parts.push(`\nMetadata: ${JSON.stringify(payload.metadata, null, 2)}`);
+    }
+
+    return parts.join(" ");
+  }
+
+  static info(message: string, metadata?: Record<string, unknown>, latencyMs?: number) {
+    console.log(this.format("INFO", { message, metadata, latencyMs }));
+  }
+
+  static warn(message: string, metadata?: Record<string, unknown>, latencyMs?: number) {
+    console.warn(this.format("WARN", { message, metadata, latencyMs }));
+  }
+
+  static error(
+    message: string,
+    error?: Error | unknown,
+    metadata?: Record<string, unknown>,
+    latencyMs?: number
+  ) {
+    console.error(this.format("ERROR", { message, error, metadata, latencyMs }));
+  }
+}

supabase/migrations/20260608000000_initial_schema.sql

@@ -0,0 +1,86 @@
+-- Enable pgvector extension
+CREATE EXTENSION IF NOT EXISTS vector;
+
+-- Recruiters table
+CREATE TABLE IF NOT EXISTS recruiters (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  name TEXT NOT NULL,
+  email TEXT NOT NULL UNIQUE,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- Jobs table
+CREATE TABLE IF NOT EXISTS jobs (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  title TEXT NOT NULL,
+  requirements JSONB NOT NULL,
+  embedding vector(1536),
+  recruiter_id UUID REFERENCES recruiters(id) ON DELETE SET NULL,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- Candidates table
+CREATE TABLE IF NOT EXISTS candidates (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  name TEXT NOT NULL,
+  contact_info JSONB NOT NULL,
+  embedding vector(1536),
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- Interviews table
+CREATE TABLE IF NOT EXISTS interviews (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  candidate_id UUID NOT NULL REFERENCES candidates(id) ON DELETE CASCADE,
+  job_id UUID NOT NULL REFERENCES jobs(id) ON DELETE CASCADE,
+  interview_date TIMESTAMPTZ NOT NULL,
+  stage TEXT NOT NULL, -- Technical, Cultural, etc.
+  feedback TEXT,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- Scores table
+CREATE TABLE IF NOT EXISTS scores (
+  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  candidate_id UUID NOT NULL REFERENCES candidates(id) ON DELETE CASCADE,
+  interview_id UUID REFERENCES interviews(id) ON DELETE CASCADE,
+  ai_score FLOAT NOT NULL,
+  evaluation JSONB NOT NULL, -- Hold summary, classification, suggestions, riskLevel
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL,
+  CONSTRAINT check_evaluation_schema CHECK (
+    evaluation ? 'summary' AND
+    evaluation ? 'classification' AND
+    evaluation ? 'suggestions' AND
+    evaluation ? 'riskLevel'
+  )
+);
+
+-- Cosine distance match function
+CREATE OR REPLACE FUNCTION match_candidates(
+  query_embedding vector(1536),
+  match_threshold float,
+  match_count int
+)
+RETURNS TABLE (
+  id uuid,
+  name text,
+  contact_info jsonb,
+  embedding vector(1536),
+  similarity float
+)
+LANGUAGE plpgsql
+AS $$
+BEGIN
+  RETURN QUERY
+  SELECT
+    candidates.id,
+    candidates.name,
+    candidates.contact_info,
+    candidates.embedding,
+    (1 - (candidates.embedding <=> query_embedding))::float AS similarity
+  FROM candidates
+  WHERE (1 - (candidates.embedding <=> query_embedding)) > match_threshold
+  ORDER BY similarity DESC
+  LIMIT match_count;
+END;
+$$;

tailwind.config.ts

@@ -0,0 +1,28 @@
+import type { Config } from "tailwindcss";
+
+const config: Config = {
+  content: [
+    "./app/**/*.{js,ts,jsx,tsx,mdx}",
+    "./components/**/*.{js,ts,jsx,tsx,mdx}",
+  ],
+  theme: {
+    // Overriding the default theme colors to restrict to the whitelist.
+    colors: {
+      transparent: "transparent",
+      current: "currentColor",
+      white: "#ffffff",
+      slate: {
+        50: "#f8fafc",
+        600: "#475569",
+        900: "#0f172a",
+      },
+      blue: {
+        600: "#2563eb",
+        700: "#1d4ed8",
+      },
+    },
+  },
+  plugins: [],
+};
+
+export default config;

types.d.ts

@@ -0,0 +1 @@
+declare module 'pdf-parse';