We are looking for 2-3 AI engineers/developers to help us build/complete an AI go-to-market (GTM) tool that looks at both structured and unstructured data, runs it all through our AI engine, and provides insights and recommendations straight to sales people. The tool is able to handle large volumes of data and provide actionable insights for business decision-making. Our engine consists of a prioritization algorithm, pattern matching and sentiment analysis. We use our recommendation engine to deliver the output (insights) straight to our tool which is "Apple-simple", intuitive and gamified. No more sales time wasted on looking at dashboards and trying to agree on which insights are important and which should be acted on. What you'll do Own features end-to-end across theFastAPI backend (IEngine) and Next.js 15 / React 19 frontend— from Claude prompt design to UI polish. Extend the intelligence pipeline: meeting ingestion (Google Drive + Deepgram realtime), Claude-driven action card generation, Neo4j relationship graph, and Supabase-backed state. Build customer-facing dashboard surfaces — deals, gamification, coaching, trust graph — with TypeScript, Tailwind, shadcn/ui, and D3. Operate WebSocket transcription sessions and async job pipelines reliably under real meeting load. Instrument with Sentry, harden auth (NextAuth :left_right_arrow: JWT :left_right_arrow: FastAPI service-to-service), and keep deploy pipelines green. Build with simulators: when you can't test against live meetings, generate realistic synthetic transcripts through our simulator service. Stack you'll work in Backend: Python 3.11, FastAPI, Uvicorn, PyJWT, Anthropic SDK, Deepgram, Neo4j, Supabase (Postgres + realtime), WebSockets Frontend: TypeScript, Next.js 15 (App Router), React 19, NextAuth 5, Tailwind, shadcn/ui, D3, Stripe Infra: Fly.io, GitHub Actions, Sentry, Supabase AI: Claude (Opus/Sonnet) for transcript analysis, action card generation, and agentic dev workflows What we're looking for 4+ years building production web applications, ideally across Python and TypeScript. Comfort designing and shipping features against an LLM API — prompt iteration, structured outputs, evals, cost/latency tradeoffs. Real Claude or OpenAI production experience required. Experience with multi-tenant SaaS patterns, JWT auth, and one or more of: graph databases, realtime systems, audio/transcription pipelines. Comfort with AI-assisted development workflows (Claude Code, Cursor, etc.) — not just as a code-completion tool, but as a way to plan and ship features. Bias toward shipping. Small surface area, high ownership, no committee.

Build Private AI Chat Tool Using Anthropic Claude API — Law Firm Budget: $1,500–$3,000 fixed price Description: I'm a managing attorney at a small law firm in New York. I need a private, secure web application that gives my 4-person team access to Claude AI for document summarization and legal drafting — using the Anthropic API with Zero Data Retention so no client data is stored externally. What I need built: Browser-based chat interface (works like claude.ai but private) Per-user login (4 users) PDF upload — user uploads a document, selects a task (summarize medical records, extract key facts, etc.), Claude returns structured output Conversation history saved to our own encrypted database, tagged by case number Admin view where I can see all conversations across all users Hosted on a private server with HTTPS/SSL No data logged or stored outside our own database Clean, simple UI — non-technical staff must be able to use it Tech requirements: Anthropic Messages API (claude-sonnet-4-6) Zero Data Retention configured on the API account PostgreSQL or similar database for history Per-user authentication (JWT or similar) PDF text extraction before sending to API Encrypted database at rest You must have: Prior experience with the Anthropic Claude API specifically Experience building secure web apps with user auth and databases Portfolio or examples of similar builds Please answer this in your proposal: have you configured Zero Data Retention on the Anthropic API before? This is a fixed-price project. I own all code upon final payment.

Overview: I have a marketing site for my construction/remodeling business built in Lovable (Vite + React single-page app). The problem: it's client-side rendered, so search engines and AI crawlers (GPTBot, Perplexity, ClaudeBot) and social link previews receive an empty HTML shell with no content. Google has only indexed 6 of my 89 pages because of this. I need the site served as fully prerendered static HTML so every route returns real content in the raw HTML — no JavaScript required to see it. Scope of work: Export my existing Lovable project to GitHub (I'll authorize access). Add a build-time prerendering step (react-snap or equivalent) that generates a static HTML file per route — including all service pages and the ~58 service-area pages. Deploy to Netlify or Cloudflare Pages (your recommendation) with the prerender step running automatically on each build. Point my existing domain (www.mastersconstructiongroup.com) to the new host via DNS. I'll provide registrar access or make the changes you specify. Critical requirement: I must be able to keep editing the site in Lovable after the move. Set up the GitHub → host pipeline so that when I publish edits from Lovable, they automatically flow through and redeploy the prerendered site. I do NOT want to edit code for routine content changes. Please confirm you can preserve this workflow. Acceptance criteria (how I'll confirm it's done): Running curl (no JavaScript) on the homepage and at least 3 interior pages returns the page's real title, H1, and body content in the raw HTML. The LocalBusiness / GeneralContractor JSON-LD schema is present in the raw HTML. I can make a content edit in Lovable, publish, and see it live on the domain without developer involvement. Helpful notes: The Lovable export is already partly prepared for this: main.tsx uses hydrateRoot(), internal links render as real anchor tags, and react-helmet is wired up for per-page head tags. There's also a react-snap config recipe I can share with you. This should be a small, well-defined job. Please include in your proposal: a fixed-price quote, estimated turnaround, and a one-line confirmation that you can keep my Lovable editing workflow intact after the move.

You will work closely with our internal team and clients to develop and execute comprehensive SEO strategies across Shopify and BigCommerce storefronts. This includes technical SEO, on-page optimization, content strategy, and ongoing performance analysis. Responsibilities: SEO Strategy & Execution Own and manage SEO strategy for multiple eCommerce clients on an ongoing basis. Conduct in-depth SEO audits across: Technical SEO (site structure, crawlability, indexing, performance) On-page SEO (metadata, keyword targeting, internal linking, content structure) Content opportunities and gaps Develop and implement SEO roadmaps aligned with client business goals and KPIs. Optimize product pages, category pages, collections, and content to drive organic growth. Identify and execute opportunities to increase rankings, traffic, and conversions. Monitor algorithm updates and proactively adjust strategies. Technical SEO & Performance Optimization Analyze and improve: Site speed and Core Web Vitals Mobile performance and UX Crawl efficiency and indexing Collaborate with development teams to implement technical SEO improvements. Identify and resolve issues related to: Duplicate content Broken links Redirect chains Schema markup Ensure best practices are implemented across Shopify and BigCommerce environments. Content Strategy & Optimization Conduct keyword research based on intent, competition, and conversion potential. Build and guide SEO-driven content strategies that align with user behavior and business goals. Provide recommendations for: Landing pages Blog content Collection/category expansion Optimize existing content to improve rankings and engagement. Analytics, Reporting & Insights Track and report on SEO performance including: Organic traffic Keyword rankings Conversions and revenue impact Use tools such as Google Analytics, Search Console, Ahrefs, SEMrush, or similar. Translate data into actionable insights and strategic recommendations. Continuously identify opportunities for improvement and growth. Client Communication & Collaboration Work closely with clients to align SEO strategy with business objectives. Present findings, insights, and performance reports in a clear, strategic manner. Collaborate with internal teams across: Design Development Account Strategy Provide SEO guidance throughout projects including redesigns, migrations, and optimizations. Market Intelligence & Growth Strategy Stay ahead of SEO trends, algorithm changes, and industry best practices. Understand the competitive landscape across eCommerce verticals. Identify patterns and opportunities across client accounts to improve performance. Contribute ideas to improve internal SEO processes, frameworks, and offerings. GEO Strategy & Execution Develop and manage GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization) strategies for eCommerce clients. Identify opportunities to increase brand visibility across: Google AI Overviews ChatGPT Gemini Perplexity Claude Other AI-powered search experiences Conduct audits and analysis related to: Entity recognition and optimization Topical authority Content depth and coverage Structured data implementation AI search visibility opportunities

The Client seeks an experienced AI development team to design and build a secure web-based document intelligence platform capable of analyzing multiple related documents, extracting key information, identifying inconsistencies, and generating issue reports. The platform will support complex document sets where information must remain consistent across multiple files and versions. The initial scope focuses on document ingestion, data extraction, cross-document analysis, issue identification, and reporting. Business Objective Develop a scalable SaaS application that enables users to: • Upload and organize multiple related documents • Extract key terms, dates, parties, financial values, and references • Compare information across documents • Identify inconsistencies and missing information • Generate issue reports and review summaries • Maintain document version history • Provide an intuitive dashboard for issue management Phase 1 – Document Ingestion and Processing Requirements Develop a secure document upload module supporting: • PDF • Microsoft Word (.docx) • Microsoft Excel (.xlsx) • Text files System shall: • Extract text from uploaded files • Preserve document structure • Capture headings and section hierarchy • Process tables and schedules • Index document content for search and retrieval Phase 2 – Data Extraction Engine The platform shall automatically identify and extract: • Defined terms • Parties and entities • Dates • Numerical values • References to exhibits and schedules • Section references • Key metadata Extracted information shall be stored in a searchable database. Phase 3 – Cross-Document Consistency Review The platform shall compare extracted information across multiple documents and identify: • Inconsistent terminology • Conflicting dates • Conflicting numerical values • Missing references • Undefined terms • Duplicate provisions • Broken cross-references Examples include: • Same entity referenced using multiple names • Different numerical values for the same item • References to sections that do not exist • Missing exhibits or attachments Phase 4 – AI Review and Issue Identification The platform shall integrate a Large Language Model (LLM) to perform contextual analysis. The AI engine shall: • Summarize document contents • Identify potential drafting inconsistencies • Highlight missing information • Generate issue descriptions • Assign issue severity levels • Provide suggested corrective actions Phase 5 – Dashboard and Reporting Develop a web-based dashboard including: Transaction Workspace • Document list • Upload history • Processing status • Review status Issue Tracker • Issue category • Issue severity • Source document • Description • Resolution status Search Functionality Search by: • Term • Date • Party • Numerical value • Document name Reporting Generate downloadable reports in PDF and Excel format. Technical Requirements Frontend • React or Next.js Backend • Python • FastAPI preferred Database • PostgreSQL Vector Database • Pinecone, Weaviate, or Chroma AI Integration • OpenAI API • Anthropic API • Retrieval-Augmented Generation (RAG) architecture preferred Security Requirements • User authentication • Role-based permissions • Encrypted document storage • Audit logging • Secure API access Deliverables Functional web application Source code repository Database schema API documentation Deployment documentation Administrator guide User guide Ownership and Intellectual Property All work product, source code, documentation, specifications, workflows, business logic, prompts, training materials, and derivative works developed under this project shall be deemed works made for hire and shall be the sole and exclusive property of the Client. Contractor shall assign all intellectual property rights to the Client upon creation. Contractor shall not reuse, disclose, distribute, or commercialize any portion of the work product without the Client’s prior written consent.

Aria Technology Solutions is not a traditional B2B tech agency. We don’t build other people’s dreams or fix legacy corporate code. We are a fast-moving, asymmetric Product Factory and Venture Studio. Utilizing advanced AI agent architectures, autonomous development sandboxes (like Antigravity and Cursor), and rich datasets, we build, deploy, and operate a portfolio of programmatic micro-SaaS tools, high-yield arbitrage applications, and data-driven platforms rapidly and efficiently. Right now, our core team is lean (just the founders). We are scaling aggressively and need an AI Operations Manager to act as our technical producer, air traffic controller, and human-in-the-loop gatekeeper to keep our production conveyor belt running flawlessly. We don’t need a traditional Senior Software Engineer who wants to write hundreds of lines of boilerplate code by hand. We need a systems-oriented, tech-forward product operator. You will sit inside our AI management dashboards, directing and moderating parallel AI agent loops as they build features, handle data pipelines, and deploy code. You will be the bridge between our strategic product vision and our autonomous AI engineering engine, ensuring quality, preventing agent sprawl, and maintaining our active digital properties. Core Responsibilities AI Agent Pipeline Oversight (Air Traffic Control): Monitor parallel, multi-step autonomous agent loops across multiple workspaces. Ensure coding agents stay on track, resolve system execution blockers, and don't burn API tokens on infinite validation loops. Human-in-the-Loop Git Management: Review the AI-generated "Artifacts," preview builds, and code changes. Safely merge approved AI code into main Git branches and push updates to production via Vercel/Netlify/Google Cloud. Operational & Site Maintenance: Keep our fleet of live websites running smoothly. Monitor basic server uptimes, keep API endpoints and subscription tokens funded, and track central error logs. Property Moderation: Oversee basic user feedback loops, flag database anomalies, and keep our dynamic database updates (like SQLite/PostgreSQL automated inputs) running without data drift. What We Are Looking For Deep AI Native Literacy: You live in the modern AI tech ecosystem. You are intimately familiar with LLMs, AI coding environments (Cursor, Antigravity, Replit, GitHub Copilot Workspace), and programmatic workflows (MCP servers). Git & Stack Literacy: You must have strong Git literacy (branching, merging, PR reviews). While you don't need to be a coding wizard, you need a solid understanding of modern web stacks (e.g., Next.js, FastAPI, Python, Supabase, Tailwind) so you can spot when an AI agent is making a sloppy structural decision. Extreme Product Intuition: You can look at an AI-generated UI preview and instantly tell if it functions properly, flows logically for a human user, or if the agent cut a corner with a placeholder. The "Hacker/Founder" Mindset: You excel in high-velocity, low-friction environments. You value moving fast, testing live apps, and iterating quickly over corporate perfectionism. Why Join Aria Technology Solutions? The Future of Software: You will work on the absolute frontier of the "Vibe-Coding" economy, learning how to leverage AI to scale digital equity at a rate traditional software teams cannot match. Zero Bureaucracy: You report directly to the founders. If something works, we launch it immediately. Portfolio Variety: You won't be bored working on one legacy corporate enterprise tool for a year. You will help launch, operate, and maintain dozens of different innovative apps, keeping your days dynamic and high-impact. How to Apply To prove you are an operator who reads the details and doesn't just copy-paste an automated AI proposal, please start your cover letter with the phrase: "Ready for the conveyor belt." Briefly tell us about a time you used AI toolsets (like Cursor, custom scripts, or agents) to build or launch something quickly, and your comfort level with managing Git branches.

**About the Project** I am the founder of Tenzor AI Talent (tenzortalent.com), a relationship-driven AI staffing and executive search firm based in Raleigh, NC. I need an experienced Squarespace designer to build a polished, professional 6-page website that reflects the caliber of clients and candidates we work with. This is not a complex technical build — it is a content and design execution project. All the hard work is already done. You will have everything you need from day one. **What's Already Prepared for You** - Full website copy for all 6 pages (provided as a Word document) - Brand logo (PNG file ready to upload) - Brand color codes: Teal #3AABCD, Purple #6B3FA0, Orange #E86C2F, Gold #F5C518, Navy #0A1628 - A homepage visual mockup showing the desired layout and section flow - An active Squarespace account with the domain already connected **Pages to Build** 1. Home 2. About / Our Story 3. Services 4. AI Market Insights (Tenzor Insights) 5. Contact / Let's Talk 6. For Candidates

Build an AI Marketing Operating System for Local Business I am an orthodontist building an internal AI platform for my practice. This is NOT a website project. The platform should: * Continuously monitor public internet sources for local conversations related to orthodontics. * Use AI to determine whether a conversation is worth engaging. * Generate suggested responses in our brand voice. * Never publish automatically. * Present every suggestion in an approval dashboard where I can Approve, Edit, or Reject. * Generate blog posts, Google Business Profile posts, newsletters, Instagram captions, FAQs, and YouTube scripts. * Track analytics and improve recommendations over time. Technologies preferred: * OpenAI API * Make.com or n8n * React / Next.js * Supabase * Airtable (acceptable for MVP) * PostgreSQL * Docker Applicants should have experience with: * AI agents * Human-in-the-loop workflows * LLM integrations * Automation * Dashboard development

Website Growth, SEO & Analytics Consultant (Webflow | AI Search | Attribution) About Marvista Design + Build Marvista Design + Build is an award-winning residential design-build firm serving the Pittsburgh region. We provide architecture, interior design, project management, and construction services under one roof, specializing in kitchens, bathrooms, additions, whole-home renovations, aging-in-place solutions, and complex remodeling projects. As we continue to grow, we are building a team of specialized freelance marketing professionals who work directly with company leadership to strengthen our online presence, generate qualified leads, and position Marvista as the leading residential remodeling firm in our market. The Opportunity Like many growing businesses, we have worked with outside digital marketing firms, SEO agencies, and website consultants over the years. While we have had some success, we have often found ourselves competing for attention with dozens of other clients and waiting too long for recommendations, implementation, and strategic direction. We are ready to take a more hands-on approach. Rather than relying on a traditional agency relationship, we are building our own team of specialized freelance professionals who work directly with ownership. Our goal is to create a group of experts who understand our business, our market, and our growth objectives. We are seeking a freelance Website Growth, SEO & Analytics Consultant who can help us maximize the effectiveness of our Webflow website, improve our search visibility, strengthen our analytics and attribution systems, and help us adapt to the rapidly changing landscape of Google and AI-powered search. This is not a one-time project and it is not a traditional employment position. We are looking for a trusted freelance partner who can provide ongoing guidance, recommendations, and implementation support as we continue to grow our digital presence. Responsibilities Website Management & Optimization * Maintain and improve our Webflow website. * Implement website updates, content changes, landing pages, and ongoing enhancements. * Monitor website performance, user experience, and conversion opportunities. * Recommend improvements to navigation, service pages, landing pages, and lead-generation pathways. * Ensure the website remains technically sound, mobile-friendly, secure, and optimized for performance. * Proactively identify opportunities to improve lead generation and user engagement. SEO Strategy & Content Oversight * Help develop and execute our SEO strategy. * Collaborate with and provide guidance to our freelance SEO content writer. * Review content recommendations and ensure alignment with company goals. * Identify keyword opportunities, content gaps, and new content initiatives. * Monitor search rankings and organic traffic performance. * Recommend technical and on-page SEO improvements. * Ensure website content follows current SEO best practices. AI Search Readiness * Stay current on developments involving Google AI Overviews, ChatGPT, Gemini, Perplexity, and other emerging search platforms. * Recommend strategies to improve Marvista's visibility in AI-generated search results. * Help position our website as an authoritative resource within the residential remodeling and design-build industry. * Advise ownership on how search behavior is changing and how Marvista should adapt. Analytics, Attribution & Performance Tracking * Monitor Google Analytics 4 (GA4), Google Search Console, and related reporting tools. * Develop and maintain a consistent UTM tracking strategy across all marketing channels. * Ensure campaigns, referral sources, email marketing, social media, paid advertising, and other traffic sources are properly tagged and tracked. * Help establish accurate attribution reporting so ownership can better understand lead sources and marketing performance. * Track website traffic, lead generation, conversion metrics, and user behavior. * Provide clear monthly reporting and actionable recommendations. * Identify opportunities to improve ROI across all digital marketing efforts. * Work with ownership to continually refine dashboards, reporting, and key performance indicators. Strategic Website & Search Advisory * Meet with ownership regularly to review website performance and priorities. * Recommend short-term and long-term website initiatives. * Identify emerging opportunities related to search, content, AI, analytics, and website performance. * Help keep website and search-related initiatives moving forward. * Serve as an experienced resource on best practices and industry trends. The Right Fit We are not looking for someone who simply waits for instructions or completes website edits as requested. We are looking for a proactive consultant who brings ideas, identifies opportunities, challenges assumptions, and helps us stay ahead of industry changes. The ideal candidate understands how websites, search engines, AI-powered search platforms, analytics, attribution, and content strategy work together to drive qualified leads and business growth. We value strategic thinking, responsiveness, accountability, and proactive recommendations more than simply completing assigned tasks. Most importantly, we are looking for someone who takes ownership of outcomes and genuinely cares about helping us improve our digital presence over time. Qualifications * Demonstrated experience managing and optimizing Webflow websites. * Strong understanding of SEO, technical SEO, content strategy, and website conversion optimization. * Experience implementing and managing UTM tracking strategies and marketing attribution systems. * Strong understanding of lead tracking, conversion reporting, and marketing analytics. * Strong working knowledge of Google Analytics 4 (GA4). * Familiarity with Google Search Console, Ahrefs, SEMrush, or similar platforms. * Knowledge of AI search trends and how search behavior is evolving. * Strong communication skills and the ability to explain technical concepts in practical business terms. * Ability to work independently and proactively identify opportunities. * Experience helping service-based businesses generate leads through their website. Preferred Experience * Residential construction * Design-build firms * Architecture firms * Home services businesses * Real estate-related businesses Important Notes * This is a freelance subcontractor opportunity. * This is not a full-time position. * We anticipate an ongoing relationship measured in months and years, not weeks. * Other marketing freelancers and specialists may also support Marvista, but all contractors report directly to company ownership. * This role is expected to collaborate with other specialists but will not manage them. * We are looking for a long-term strategic partner, not a traditional agency relationship. * We are not looking for someone who simply completes tasks. We are looking for someone who helps us think strategically, stay current, and continually improve our digital marketing foundation. Success in This Role Looks Like * Increased qualified website traffic. * Improved search engine visibility. * Better visibility in AI-powered search results. * Consistent publication of high-quality content. * Improved website conversion rates. * Clear understanding of where leads originate and which marketing initiatives are producing results. * Reliable attribution and reporting through consistent UTM implementation. * Improved visibility into marketing ROI and decision-making. * Clear reporting and measurable marketing results. * A website that continues to evolve as a lead-generating asset for the business. To Apply Please provide: 1. Examples of Webflow websites you currently manage. 2. Examples of SEO results you have helped achieve. 3. Your experience with AI search optimization and emerging search technologies. 4. Your experience with analytics, attribution, GA4, and UTM implementation. 5. Your preferred monthly engagement structure and availability. 6. Why you believe you would be a good fit for this opportunity. 7. Describe how you would improve lead generation for a residential design-build firm with a Webflow website and an active content strategy. Please note: We are not looking for a traditional SEO agency or website vendor. We are looking for a proactive freelance consultant who can become a trusted long-term partner and help us continuously improve our website, search visibility, analytics, attribution, and digital marketing performance.

# Full-Stack AI Engineer — Semantic Search + Next.js + Supabase (Long-Term, Contract-to-Hire) ## About We're building an AI-native platform that makes a large archive of recorded talks genuinely discoverable and useful: need-based semantic search over transcribed media, with a subscription product built around it. We have a clear product vision and architecture and are looking for a lead engineer to build the first version and grow with us long-term. Full product details are shared with shortlisted candidates under NDA — this post focuses on the engineering and the skills we need. ## The engineering challenge You'll build a two-part system that shares one database: 1. **A content pipeline (Python):** ingest recorded talks, transcribe them, chunk and enrich the transcripts with metadata using an LLM API, generate embeddings, and store everything in Postgres. 2. **A web app (Next.js):** fast, crawler-friendly, SEO-strong content pages with structured data; retrieval-based search that returns relevant source material with links/citations; user accounts; and Stripe-gated paid content. We care a lot about retrieval *quality* and clean, maintainable architecture — this is a real product, not a prototype. ## Required tech stack - **App:** Next.js (App Router), TypeScript, Vercel. Strong SSR/SSG, SEO, and JSON-LD structured-data experience. - **AI/backend:** Python; production RAG (embeddings, chunking, retrieval quality); LLM API integration. - **Data:** Postgres + **pgvector** (via Supabase); embeddings via a hosted model (Voyage/OpenAI). - **Auth & gating:** Supabase Auth with row-level security. - **Payments:** Stripe (subscriptions + one-time). ## Required skills - Shipped production Next.js (App Router) + TypeScript apps with strong SSR/SEO. - Built a real RAG / vector-search system in production — not a tutorial clone. - Comfortable in Python for data pipelines. - Postgres + pgvector and Supabase in production. - Stripe integration. - Plans before building; communicates clearly in writing. ## Nice to have - Audio/video transcription experience (Whisper / faster-whisper / Deepgram / AssemblyAI). - Agentic coding workflows (e.g., Claude Code). - Content-heavy SEO products or media libraries. ## Engagement - Hourly, contract-to-hire. ~20–40 hrs/week to start; long-term for the right person. - We start finalists on a **small paid test project** (a single self-contained slice of the pipeline) before the full engagement — that's how we evaluate fit. ## Confidentiality This is a proprietary product. Shortlisted candidates sign a mutual NDA before we share full scope and context. Please don't expect complete product details in the first exchange — strong technical applicants will have everything they need to be evaluated, and the rest follows the NDA. ## How to apply Applications that skip these are ignored: 1. **Start your proposal with the word `pgvector`** so we know you read this. 2. Link **two** projects: one live Next.js/SSR app, and one RAG/embeddings or LLM-integration project. Tell us what *you* personally built. 3. Answer briefly: *An offline embedding pipeline and a live search query must use the same embedding model — why does that matter, and how would you guarantee it?* 4. One line on your approach to chunking long-form audio/video transcripts for good retrieval.