We are seeking an experienced Workflow Automation Specialist to design and implement a scalable email automation system that streamlines the processing of inbound requests and outbound communications for Data Subject Rights Requests. Our team currently handles a moderate-to-high volume of incoming emails from multiple sources. Much of the workflow involves repetitive administrative tasks, including reviewing emails, extracting key information, manually logging data, and sending standardized responses. We are looking for a consultant/developer who can evaluate our existing process (combination of GMail & Monday.com), recommend the best tech to use, and build a solution that significantly reduces manual effort while maintaining accuracy, visibility, and auditability (this is key!). Full job & project details in the attached PDF

# Founding AI Operations Architect | Build the Future of Home Services ## About EPIC EPIC Septic & Service is one of the fastest-growing septic and wastewater companies in America. We are a veteran-owned organization with operations expanding across multiple states and an ambitious vision to become the first nationally recognized brand in the septic and wastewater industry. But we're not just building a septic company. We're building the operating system behind it. Our mission is to create the first AI-powered Virtual Back Office (VBO) for the septic and wastewater industry—combining customer service, dispatching, sales, inspections, maintenance agreements, reporting, and franchise support into a single scalable platform. We believe the future of home services is not simply hiring more people. We believe the future is AI-powered operations supported by exceptional field teams. ## The Opportunity We are seeking a Founding AI Operations Architect to help design, build, and implement the technology infrastructure that will power EPIC's next phase of growth. This is not a traditional software development role. This is a systems architecture and operational design role focused on leveraging AI, automation, and modern technology to transform how a service business operates. You will work directly with the founder and executive team to map processes, identify opportunities for automation, and build the foundation for a platform that can scale across company-owned locations, franchisees, and strategic partners nationwide. We are looking for a builder, an operator, and a visionary who enjoys solving complex operational challenges with technology. ## What You'll Build ### Customer Experience Systems * AI-powered call answering * Lead qualification and routing * Appointment scheduling * Customer communication workflows * Automated follow-up sequences ### Revenue Operations * AI sales agents * Estimate and proposal generation * Maintenance agreement enrollment * Payment collection workflows * Customer retention programs ### Field Operations * Dispatch automation * Technician scheduling * Inspection workflows * Service reminders * Work order management ### AI Agent Ecosystem * Customer Service Agent * Dispatcher Agent * Sales Agent * Collections Agent * Inspection Report Agent * Franchise Support Agent * Internal Operations Assistant ### Reporting & Intelligence * Executive dashboards * Operational scorecards * Franchise performance reporting * KPI monitoring * Business intelligence systems ## Current Technology Stack We are currently evaluating and implementing technologies including: * Jobber * Claude * UJET * Make * n8n * Zapier * Airtable * Retool * Custom APIs and integrations We are open to recommendations from the right candidate. ## First 90-Day Objectives ### Phase 1 – Discovery & Architecture * Audit current EPIC workflows * Map customer journeys from lead to completion * Identify automation opportunities * Design overall system architecture * Create implementation roadmap ### Phase 2 – MVP Development * AI phone answering workflows * Lead qualification automation * Scheduling automation * Estimate generation workflows * Customer communication systems ### Phase 3 – Virtual Back Office Launch * Dispatch automation * Maintenance agreement workflows * KPI dashboard implementation * Reporting framework * Initial franchise-ready operating model ## Ideal Experience You have successfully built or implemented: * AI agents and automation systems * Contact center automation * CRM integrations * Workflow automation platforms * Field service management systems * Operational software for service businesses * Multi-location or franchise support systems Bonus experience includes: * Jobber * ServiceTitan * Home service businesses * Plumbing, HVAC, electrical, septic, or wastewater industries * Franchise operations * AI-powered customer support systems ## What We're Not Looking For Please do not apply if you are: * A website designer * Looking for simple development tasks * An agency that outsources work * Someone without hands-on AI automation experience * Someone who has never built operational systems that drive real business outcomes We are looking for someone who can think strategically, architect systems, and execute. ## Why This Opportunity Is Different Most companies use AI to make small improvements. We are using AI to reimagine how an entire industry operates. Our goal is to create the first fully AI-enabled septic and wastewater platform in America and ultimately build the infrastructure that powers operators nationwide. This is an opportunity to help build something from the ground up, have a direct impact on the direction of the platform, and work alongside a team that is committed to innovation, execution, and long-term growth. ## To Apply Please include: 1. Examples of AI systems you have designed or built. 2. Relevant automation or operational projects. 3. CRM or field-service integrations you have implemented. 4. Your preferred technology stack and why. 5. How you would approach building an AI-powered Virtual Back Office for a service business. 6. What excites you most about this opportunity. We are looking for a long-term partner who wants to help build something meaningful, scalable, and industry-defining.

About the role We've built an internal tool that automatically generates creative product imagery for e-commerce listings (Amazon, Walmart, Target) — style guides, creative briefs, and finished creative images produced by an AI pipeline. Our client success managers run it day-to-day. What we're looking for is an expert eye above them: someone to audit the output, hold a quality bar, and advise on the technical fixes when the AI gets it wrong. This is an auditor + advisor role, not a production seat. You review and direct; our team executes. What you'll do - Audit AI-generated creative in batches and grade it against a professional standard: composition, hierarchy, typography, color, brand consistency, product fidelity (does the render still look like the real product?), and commercial polish. - Help define and maintain what "ship-ready" looks like, and flag what falls short — and why — in clear, actionable written feedback. - Consult on the technical fixes. When an image comes out wrong (warped product, off-brand palette, bad text rendering, weird "before/after" artifacts), diagnose why at the model/prompt level and prescribe the fix: prompt adjustments, reference-image strategy, model choice, parameters, or editing/inpainting approach. - Partner with our team to translate design problems into technical direction they can implement. You're a strong fit if you have - A professional graphic design background with a portfolio (e-commerce, product, or advertising work strongly preferred) — enough authority to be the one grading the work. - Hands-on experience with modern AI image tools (e.g. Midjourney, DALL-E / GPT image, Stable Diffusion, Flux, Nano Banana / Gemini image, ComfyUI, inpainting/editing, ControlNet or reference-conditioning). - The ability to articulate why an AI image fails and how to steer it — prompt engineering, reference images, seeds, model selection, post-editing. - Strong written communication; your deliverable is critique and direction, so it has to be precise. - Bonus: familiarity with Amazon listing imagery standards, Photoshop/Figma, or light scripting. Not a fit if you only do hand-crafted design and treat AI tools as a black box, or you can generate AI images but can't critique them like a professional designer. We need both — the eye and the technical fluency. Engagement Ongoing, part-time / as-needed advisory. Remote and async-friendly. We'll start with a small paid trial: we share a set of generated outputs, you audit them, deliver written critique against a quality bar, and prescribe technical fixes for the weakest ones. How to apply Send a short Loom video (3-5 min) in which you: 1. Introduce yourself and your design background (share portfolio links). 2. Critique one AI-generated image — walk us through how you assess its quality. 3. Show one AI image that came out wrong and explain how you'd diagnose and fix it at the model/prompt level. 4. Tell us which AI image models/tools you know best and why. Applications that include a Loom video will be prioritized.

# Zapier & AI Automation Specialist for Growing Coffee Catering Company ## Overview Pretty Good Coffee Company is a premium mobile coffee catering company based in Raleigh, NC. We serve corporate events, employee appreciation events, universities, weddings, brand activations, and private events throughout North Carolina. We're looking for an experienced automation specialist to help us build practical systems using Zapier, AI tools, Gmail, and our existing software stack. Our goal is not simply to automate tasks. We want to create systems that improve client experience, increase sales conversion, reduce administrative workload, and help us scale operations without sacrificing hospitality. ## Primary Project: Quote Follow-Up Automation Our highest priority is building an automated quote follow-up system. Current workflow: * Lead submits inquiry * Quote is created and sent through booking platform * Follow-up is currently handled manually Desired workflow: * Detect when a quote is sent * Extract relevant quote details * Use AI (Google AI Studio/Gemini) to generate personalized follow-up emails * Create Gmail drafts (not auto-send) * Trigger additional follow-ups after specific time periods * Maintain a natural, human, hospitality-focused tone We have already begun building this workflow but need an expert to finish and optimize it. ## Future Automation Opportunities After the initial project, we'd like help building additional automations such as: ### Sales * Lead response automation * Quote follow-up sequences * Lead scoring and prioritization * Client re-engagement campaigns * CRM updates and pipeline tracking ### Operations * Automatic event briefs * Staff communication workflows * Event assignment notifications * Calendar and scheduling automations * Inventory forecasting ### Marketing * Review request automation * Testimonial collection * Client nurture campaigns * Social media/content workflows * Monthly reporting dashboards ### Executive Reporting * Weekly business summaries * Lead tracking * Conversion reporting * Revenue dashboards * Operational KPI reporting ## Current Tech Stack * Flashquotes * Zapier * Gmail / Google Workspace * Google AI Studio (Gemini) * Google Sheets * Google Drive Additional platform recommendations are welcome if they simplify operations. ## What We're Looking For * Strong Zapier experience * Experience with AI integrations (Gemini, OpenAI, Claude, etc.) * Experience troubleshooting API and webhook workflows * Ability to think through business processes, not just build automations * Clear communication and documentation * Ability to recommend simpler solutions when appropriate ## To Apply Please include: 1. Examples of similar automation projects you've built. 2. Your approach to quote follow-up and sales automation. 3. Your preferred hourly rate or fixed-price estimate for the initial project. 4. Any recommendations you would make based on the information above. We're looking for a long-term automation partner, not just a one-time freelancer.

We are seeking an experienced Claude AI Trainer based in or near Los Angeles, CA to deliver role-based AI training for approximately 120 employees across multiple departments. Audience Finance – 20 employees Development / Campaign – 25 employees Programs (multiple teams) – 40 employees HR & IT – 12 employees Leadership – 5 employees Facilities / Administration – 20 employees Training Structure Phase 1: AI Foundations (2 Hours) All employees will receive a shared foundation covering: - Claude AI fundamentals - Responsible and effective AI usage - Prompting best practices - Organizational AI guidelines and governance - Common business use cases Phase 2: Department-Specific Workshops Following the foundation session, each department will participate in hands-on workshops (approximately 2 hours per team). Workshops should focus on real-world applications relevant to each group's responsibilities, such as: - Finance reporting and analysis - Fundraising and campaign communications - Program operations and documentation - HR and IT workflows - Executive productivity and decision support Training Style We are looking for a highly interactive approach: - Hands-on learning - Brief demonstrations followed by guided exercises - Participants applying Claude to their own work - Real business scenarios and practical outcomes - Participants will be encouraged to bring one or two actual work tasks to complete during the session. Delivery Los Angeles-based trainer preferred In-person delivery preferred Remote delivery may also be considered Requirements - Demonstrated experience training professionals on Claude AI and/or enterprise generative AI tools - Experience designing and delivering role-based AI training programs - Strong facilitation and workshop leadership skills - Ability to customize examples and exercises for different business functions Compensation Please share your expected range of hourly and daily rate To Apply Please provide: - A summary of your relevant AI training experience - Examples of previous corporate AI training engagements - Your location and availability - Your proposed training approach for this audience

I need a quality AI how to video. Must be able to start from scratch with .jpg files. I would like a motion film. -Detailed project scope and deliverables - Stays within the established requirements for the project. -Sticks with Deadline expectations -Required AI Video creation experience -Independent thinker and creator -I value creative suggestions and opinions to help bring my product to life. -Open communication is a must! -Must stay within established contract budget

We are seeking an AI receptionist to manage client interactions for our restaurant. The role involves handling phone calls, emails, and messages, ensuring timely responses and maintaining client satisfaction. The ideal candidate will have experience in customer service and be able to work independently. Familiarity with restaurant operations is a plus. We have a GHL account - for consideration explain your processs to ensure top quality for our accounts. We also need a set price per account set up.

Looking for a trainer to deliver the "Claude AI for Workflow Automation and Productivity Training Course" for a Corporate Training Engagement We are seeking an experienced instructor to deliver a hands-on corporate training focused on using Claude AI for workflow automation and productivity enhancement. The ideal trainer should be comfortable teaching business users and technical professionals how to leverage AI tools to streamline operations, automate repetitive tasks, and improve collaboration. This is an instructor-led training engagement to corporate participants. Training Topics Include: Introduction to Claude AI and AI-driven workflow automation Using Claude AI to improve productivity and task management Automating business processes such as: Email and document workflows Meeting notes and follow-ups Content generation and reporting Enhancing team collaboration with AI-assisted workflows Integrating Claude AI with business platforms and automation tools Workflow automation using tools such as: Zapier Trello Asana Notion CRM and customer support platforms AI best practices, governance, privacy, and ethical considerations Future trends in AI-powered business automation Ideal Trainer Profile: Strong hands-on experience with Claude AI or similar generative AI platforms Experience delivering workflow automation or productivity-focused training Familiarity with AI integrations and no-code/low-code automation tools Comfortable teaching both conceptual and practical hands-on sessions Prior corporate training experience preferred Ability to customize examples and exercises for business audiences Training Format: Instructor-led live training Interactive discussions and hands-on exercises Corporate audience Beginner-friendly but practical and business-oriented

I have an existing audio file. It is a parody of the YMCA song entitled AARP (American Association of Retired Persons) Need an AI generated music video created using this audio file and images you would create. I will provide a variety of scenes that can be incorporated and a description of the main characters to be used, not overly specific. I will also provide the lyrics as I want them mdisplayed (like closed caption). The song is 3:34 long. Might cut it down to a shorter clip depending on costs. I'd like to get some sort of rough estimate before going further to see if this is practical.

We are looking for an expert backend developer and automation engineer to extend an existing, production-grade Model Context Protocol (MCP) server and overhaul its orchestration layer. The headline correction for this project: the existing Lawfather MCP is to be retained and extended, not rebuilt. It already exposes deterministic, parameterized Playwright tools for every required county portal (District Clerk, HCSO, HCDAO) and a client database. Those backend tools are the reliable layer and are not the source of the instability this project exists to fix. The instability lives entirely in the orchestration layer — the model-driven layer that decides when and how to call the tools. The fix is to move deterministic control out of model-followed prose and into code, and to host the agent on an always-on machine with persistent memory. Core Project Principles • Extend, Don't Rebuild: Retain and extend the existing MCP; do not re-implement portal scrapers from scratch. • Code Over Prompts: Deterministic logic lives strictly in tool code, never in instructions the model must remember each session. • No Caller Loops: Batch operations must run to completion server-side. No operation may require the caller (model) to loop. • Agnostic Architecture: The system must remain model-agnostic and host-agnostic. No single provider — Anthropic, OpenAI, Z.ai/GLM, or Nous — may be a hard dependency. • Privilege First: Client data stays on owned hardware; the model is never the gatekeeper of which case a file belongs to. Existing Tool Inventory (To Be Inherited As-Is) The following tools already exist on the production MCP (containerized on a local Synology NAS) and are in daily use. Re-deriving their behavior is completely out of scope: • hcdc_get_docket: Court settings by date range + bar number (District Clerk). • hcdc_check_filings: Per case: standard defense filings present vs. missing. • hcdc_download_filings: Images-tab documents: bulk OR selective by filters; dest_subfolder; dry_run. Note: The parameterized download tools already cover most retrieval requests. "All filings," "this filing," "all subpoenas," "all resets," and "everything filed that day" are argument combinations on this tool, not separate features. • hcso_locate: Defendant custody location (facility / floor / pod) by SPN. • hcdao_grab_file: Download a single named file from the DA portal Files tab. • hcdao_download_discovery: Batch / delta discovery download from the DA portal. • hcdao_download_media_alert: Batch-download files listed in a 'New Media Available' portal email. • hcdao_case_summary: Scrape the Case Jacket quick summary / DAO narrative. • hcdao_plea_offer: Scrape current plea offer + full offer history. • hcdao_assigned_ada: Assigned ADA name / email / phone on a case. • lookup_client / list_clients: Resolve / list clients from the shared client database. Scoped Work (Paid Deliverables) 1. County Case Resolver (New Tool): Find a case from partial identifiers — any subset of (name, SPN, DOB, court, cause). Searches county systems (not just the local client DB). MUST return a ranked candidate list for the user to choose from; MUST NEVER auto-select. Wrong-defendant selection is a privilege failure, not a cosmetic bug. 2. Latest-Version Retrieval: Add scope=latest to hcdao_grab_file so 'most recent' selects the newest among supplements instead of the first match. 3. Async Transcribe Tool (Skill to Tool Promotion): Build a deterministic MCP tool using Gemini 3.1 Pro Preview for transcription, followed by a second pass that sends the transcript back with case context for cleanup (speaker mapping, defense-moment preamble). Long-running: implement as an async job (submit to job id to poll to fetch), NOT a synchronous call. 4. OCR Tool (Skill to Tool Promotion): Implement a readability check on ingest. If a document is not cleanly readable, FLAG it and ASK before sending to Gemini 3.1 Pro Preview for OCR. OCR must be gated and confirmed, never automatic. 5. Server-Side Batch Jobs: Move all chunk, loop, delta, and throttle logic OFF the caller and INTO the tool code. One call runs the batch to completion. 6. Queued HCDAO Fixes: For hcdao_download_discovery, add a portal_ids filter for targeted single-file pulls and a custom output-path / Drive-folder destination feature. Known Portal Quirks to Handle from Day One • hcdc_get_docket returns a broader date range than requested; results must be filtered to the requested window. • hcdao_download_discovery delta detection is blind to files organized into dated subfolders and must be explicitly handled. • Court DG7 does not surface through standard bar-number docket lookup and requires separate handling. • The Playwright Node.js driver subprocess can die silently while database tools respond; you must health-check the driver proactively. Orchestration, Host Layer, & Deployment Topology • Target Host: Hermes Agent (Nous Research) running as the persistent shell, providing persistent memory, the scheduler, and messaging surfaces. The MCP server will plug directly into it. • Agnostic LLM Routing: Default the agent/dispatch role to the most reliable tool-calling model (currently Claude Opus). Route bulk, non-critical generations (draft summaries, transcript cleanup) to a cheaper model (e.g., GLM-5.2). No provider may be hard-wired. Per-tool pins are allowed strictly for transcription/OCR tasks (pinned to Gemini 3.1 Pro Preview). • Memory Fencing: Hermes's persistent memory and learning loops must remain enabled to accumulate facts and user preferences. However, the agent must be strictly fenced from self-editing or rewriting its own mechanical execution paths (portals, downloads, filings), which must remain frozen in MCP tool code. • Hardware Deployment Infrastructure: • Always-on Brain: M1 Pro MacBook Pro (16 GB, mains-powered, lid open) running the Hermes gateway, Messages.app, and a BlueBubbles iMessage bridge. Must be fully automated via launchd services to handle headless crash recovery, auto-login, and sleep prevention (pmset autorestart / caffeinate). • Tools and Storage: Synology NAS (10.0.0.149) hosting the Lawfather MCP container, local client folders, and Drive sync. • Private Network: Tailscale mesh across all devices for secure remote access without open inbound ports. Acceptance Criteria for Sign-Off • No batch operation requires the caller to iterate. • The case resolver returns ranked candidates and never auto-selects. • Transcription runs seamlessly as an async two-stage job surviving multi-hour files without timing out. • OCR never fires automatically on low-readability files without gated confirmation. • Zero regressions on the existing MCP tool inventory. • The Resiliency Test: The full stack successfully restarts completely unattended after a host reboot or simulated power loss, and is reachable via iMessage/SMS immediately after. • Self-editing is fenced on mechanical download/filing paths. Hard Guardrails • Privilege: Downloads route strictly to the correct client folder; a wrong-case match is treated as a severe defect, not a warning. Privileged audio/discovery data stays on owned hardware where the chosen model allows. • Determinism: Repeatable steps live entirely in tool code, never in prompts. • Agnosticism: Model and host layers must remain fully swappable without modifying the core MCP tools. Before quoting "done," you will be expected to confirm live portal behaviors regarding District Clerk document labels, DA portal stable identifiers, and county search surfaces. How to Apply Please submit a proposal detailing your specific experience with MCP architectures, Playwright browser automation, and macOS/Docker DevOps automation. Anti-Bot Filtering: To prove you read this entire scope, please start your application with the phrase "PROTECT THE LAW" in all caps. Automated or generic copy-paste applications will be instantly rejected.