{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e8846453c7c74e6b8162478eb37b9713\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e8846453c7c74e6b8162478eb37b9713-6de67974e8bdbfb5.gif","duration":595.606,"title":"BuildFlow AI — Construction Bid &amp; Billing Workflow Assistant | Gen AI Portfolio | Apollo Sebastian","description":"🏗️ BUILDFLOW AI\nConstruction Bid & Billing Workflow Assistant\nPowered by AWS Bedrock (Claude Haiku)  ·  Generative AI Bootcamp  ·  Instructor: Matt Dancho\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n🚨 THE PROBLEM\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSmall to mid-size general contractors lose 10–30% of potential revenue every year from broken back-office workflows. Bid preparation alone takes\n8–15 hours per project — that is $600 to $2,250 in estimator labor before winning a single contract. No standard Scope of Work. No risk analysis.\nNo automated billing.\n\nBuildFlow AI solves all of it — from one project description — in under 15 minutes.\n\n  ⏱  8–15 hours per bid → under 15 minutes\n  💸  Up to $2,250 in labor saved per project\n  📉  10–30% revenue loss recovered annually\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n📄 WHAT IT GENERATES — 4 DOCUMENTS + AI CHAT (ONE PROJECT DESCRIPTION)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nTAB 1  ·  Trade-Level Bid Estimate\n         Itemized by trade — Category, Description, Unit, Qty, Unit Cost, Total Subtotal  ·  Contingency %  ·  Total Bid card  ·  Download JSON\n\nTAB 2  ·  Scope of Work (7-Section Legally Protective Document)\n         Project Overview  ·  Inclusions  ·  Exclusions  ·  Milestones\n         Payment Terms  ·  Change Order Policy  ·  Warranties  ·  Download TXT\n\nTAB 3  ·  AIA-Style Progress Invoice\n         Completion % slider (10–100%)  ·  Previously Billed input 4 live metric cards  ·  Automatic 10% retainage  ·  Download JSON\n\nTAB 4  ·  Risk & Change Order Report\n         Risk registry: Category  ·  Severity  ·  Probability  ·  Mitigation\n         Change Order table with cost impacts  ·  Contractor Protections  ·  Download JSON\n\nTAB 5  ·  GC AI Assistant — Live Multi-Turn Chat  ⭐\n         Full project context injected: client, location, sqft, timeline, total bid 16 sample questions across 4 categories\n         Powered by AWS Bedrock Converse API\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n⚙️  AI TECHNIQUE — STRUCTURED PROMPT CHAINING + JSON EXTRACTION\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nClinic 2 — Generative AI Bootcamp with Matt Dancho\n\n3-step sequential chain — each step passes its output as context to the next:\n\n  generate_bid()  →  generate_scope()  →  generate_risk_flags()\n\nAnimated progress bar shows all three AWS Bedrock calls running live. Claude Haiku returns structured JSON extracted with _strip_fences() and\n_safe_json_loads() with built-in repair logic for clean rendering.\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n🎯  COURSE SKILLS DEMONSTRATED — BOOTCAMP RUBRIC\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nC1 · Structured Prompt Chaining                                    10 pts\n     3-step chain: generate_bid → generate_scope → generate_risk_flags. Each step's JSON output feeds the next as live context.\n     Animated progress bar confirms all 3 Bedrock calls in real time.\n\nC2 · JSON Extraction                                               10 pts\n     Claude Haiku returns structured JSON inside markdown code fences. App uses _strip_fences() + _safe_json_loads() with repair logic.\n     Bid Estimate table and Risk Registry rendered entirely from parsed JSON.\n\nC3 · AI Chat Completions — AWS Bedrock Converse API                 8 pts\n     Tab 5 GC AI Assistant: run_assistant() → _bedrock_converse(). Full project context (client · location · sqft · timeline · total bid)\n     + full conversation history injected into system prompt. Multi-turn.\n\nC4 · Cloud Deployment — Live on Render.com                          6 pts\n     Journey: AWS App Runner (shut down Apr 30, 2026 — external event) → Azure App Service (CI/CD built; WebSocket/Gunicorn incompatibility)\n            → Render.com — deployed first attempt, GitHub auto-deploy active. \n     Live at: buildflow-ai-aws.onrender.com\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n🔗  LIVE LINKS\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n☁️  Live App (Render.com — Primary Cloud):\n    https://buildflow-ai-aws.onrender.com\n\n📺  Live App (Streamlit Mirror):\n    https://buildflowai.streamlit.app\n\n💻  GitHub:\n    github.com/ASebastianAiX/buildflow-ai-aws\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nGenerative AI Bootcamp  |  Instructor: Matt Dancho  |  Apollo Sebastian  |  May 2026\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"}