NobleProg is seeking an experienced AI Trainer to deliver a live, instructor-led remote training focused on helping technical professionals integrate Agentic AI and RAG systems into their existing workflows. This opportunity is designed for participants with strong technical backgrounds (Data Engineering and Workflow Automation) but limited formal AI experience, with the goal of applying AI to real-world systems rather than learning theory. Engagement Details Location: Remote Duration: 2 days Audience: Data Engineers and Workflow Developers Participants: 4+ Daily Rate $1,100 per day Course Scope This training focuses on practical, hands-on development of AI-powered systems using Retrieval-Augmented Generation (RAG) and agent-based architectures. The course will follow a Core & Split approach, starting with shared foundational concepts, moving into role-specific deep dives, and concluding with an integrated session demonstrating how AI systems are built and applied across workflows and data pipelines. NobleProg SOP - https://share.synthesia.io/a0788c6e-56d5-4da8-92c6-0d5c03ad6d52 Key Topics Include - Practical introduction to LLM applications and AI system architecture - Retrieval-Augmented Generation (RAG) design and implementation - Data preparation, embeddings, and vector database concepts - Agentic AI fundamentals (tools, decision-making, multi-step workflows) - Orchestration frameworks such as LangChain, LangGraph, or similar - Role-based applications: RAG pipelines for data engineers and AI-driven workflows for workflow developers - End-to-end system integration (RAG + agents + automation) Trainer Responsibilities - Deliver engaging, instructor-led remote training with strong hands-on focus - Translate AI concepts into practical applications for non-AI technical professionals - Structure delivery using a Core & Split model to address different roles - Provide real-world exercises aligned with data pipelines and workflow automation - Facilitate an integrated session demonstrating how different components work together - Prepare training materials (trainer retains ownership of content) Required Qualifications - Hands-on experience building LLM-based applications, including RAG systems and agent-based workflows - Strong proficiency in Python and experience with APIs, data pipelines, or automation systems - Experience with frameworks such as LangChain, LangGraph, or similar - Proven experience delivering technical training to engineering audiences - Ability to simplify AI concepts and connect them to real-world use cases Nice to Have - Background in data engineering, workflow automation, or solutions architecture - Familiarity with MCP or emerging agent orchestration frameworks - Experience designing modular or role-based training programs preferred - Experience building production-grade AI applications preferred https://docs.google.com/document/d/184VlJipyixkLNJ_HnP3aPt4YToedTUAlji_LxkuLhRU/edit?usp=sharing Please review and approve this tentative outline. We will be meeting with the client to determine whether they prefer a 1-day or 2-day delivery format. The agenda may require some adjustments based on the client's specific objectives, technical background, and areas of interest, which can be finalized during the trainer-client consultation call. Could you please review the proposed outline and let us know if you see any red flags, gaps, concerns, or topics that may require immediate attention? We would also appreciate any recommendations regarding scope, level of technical depth, hands-on exercises, or prerequisite knowledge that should be addressed before presenting this to the client. Thank you for your feedback. How to Apply Please include - A brief overview of your experience with Agentic AI and RAG systems - Your experience delivering technical or AI-focused training - Examples of AI systems or applications you have built - Your approach to teaching participants without formal AI background - Availability for remote delivery

Project: Exponentials – AI-Powered Personalized Discovery Platform Overview Exponentials is an AI-powered personalized discovery platform built around a simple but ambitious idea: The internet is optimized for search, advertising, and recommendation systems that push information toward users. We believe the next major category is personalized discovery: AI systems that understand intent and help users discover the most relevant products, services, experiences, education, healthcare resources, media, travel opportunities, software, and knowledge. We have already built a working investor-facing prototype: https://pull-discovery-core.base44.app The current demo allows users to enter natural-language queries and receive AI-generated discovery recommendations across multiple categories. Rather than simply returning traditional search results, the platform attempts to identify user intent, explain why recommendations were selected, and surface relevant discoveries spanning products, experiences, education, media, travel, wellness, software, and more. The visual design and core concept are strong. The next stage is transforming the prototype into a compelling investor-ready product while building the systems, automation, and fundraising infrastructure needed to support rapid growth. This is not a typical freelance coding project. We am looking for someone who can operate as a founding-level contributor and help bridge product development, investor readiness, fundraising operations, and strategic execution. Primary Mission Your primary mission is to help Exponentials become significantly more attractive to investors, strategic partners, and future customers. This includes strengthening the product itself, improving investor confidence, and creating the operational systems needed to raise capital efficiently. Primary Responsibilities Investor Readiness and Fundraising Infrastructure This is the highest-priority responsibility. Help design and implement systems that support fundraising, including: Investor CRM Investor pipeline management Investor segmentation Relationship tracking Outreach automation Follow-up systems Meeting scheduling workflows Investor updates Data room organization Due diligence preparation Fundraising dashboards Pipeline analytics Experience with tools such as HubSpot, Airtable, Clay, Notion, Apollo, Instantly, Zapier, Make, Gmail automation, and similar platforms is highly valuable. Investor Demo Optimization The Exponentials demo is intended to help investors understand the long-term vision of personalized discovery. Responsibilities include: Improving demo quality Strengthening credibility Improving recommendation quality Eliminating weak or broken experiences Creating compelling investor journeys Improving onboarding Improving first impressions Increasing confidence in the product vision The goal is to create a demo that immediately communicates why Exponentials could become an important platform category. Discovery Engine Improvement The product currently attempts to identify intent and recommend discoveries across multiple industries. Areas of focus include: Intent detection Entity discovery Recommendation quality Result ranking Trust and credibility Explanation systems Entity resolution Verified recommendations Multi-category discovery experiences Categories include: Ecommerce Education Healthcare Media Travel Experiences Restaurants Wellness Software Consumer products Experience with recommendation systems, search, retrieval, ranking, AI workflows, knowledge systems, or discovery products is highly desirable. Exponentials Investment Thesis Why this is inevitable — 8 core arguments 1 Exponentials is solving the AI backlash via the co-evolution of AI and humans in the service of human needs, and thus moving from the current extraction model of AI to a collaborative model. For Exponentials, this is moving past discovery silos to create unified discovery across (initially, $25 trillion TAM) Ecommerce, healthcare, education and media. This is accomplished through the combination of Search, LLM's and World models 2 AI can't be (optimally) successful if too many of its (potential) customers are fearful of or dislike AI 3 AI is feared and disliked (in addition to loved), as customers are smart enough to realize that AI is employing an extraction model on humans rather than a collaborative model with humans in the service of human needs 4 Major tech CEO's telling the public that they are wrong to have negative views about AI is insulting one's customer 5 If the AI industry wants to get into a war with the public it will be a stalemate at best. AI has enough perceived benefits already and the AI companies are powerful enough that they can impose their will on the public to a certain degree, but 6 It is inevitable that the AI companies who actually give the customers what they want and what truly benefits them, by flipping from the push to the pull model, will have a sustainable competitive advantage, with both inevitability and defensibility. 7 Famously, the future is already here. It is just not evenly distributed. And famously, there is nothing more powerful than an idea whose time has come. 8 We are not selling technology. We are not selling a model of AI. We are selling an empowered path for humanity that is inevitable and defensible because the AI backlash is real and not sustainable long term.

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.

We have a free to paid Conversational Voice Ai service for the Insurance Industry. We are generating a lot of interest in free trails but are having a hard to converting to paid. Need my marketing automation workflow reviewed for suggestions and ways to optimize so we convert free to paid.

**Overview** We are a fast-growing SaaS company with a lean engineering team (~10 devs) utilizing a modern Python (FastAPI/Django) and Node.js backend, React frontend, and PostgreSQL stack. We have already deployed an initial multi-model agent stack—Claude Code, LiteLLM gateway, Git worktrees, and MCP integrations. We need an expert to run an intensive architecture review and optimization session for our current infrastructure. We are not looking for someone to build a full-time, weeks-long project from scratch. Instead, we need a seasoned engineer who has shipped this exact type of infrastructure end-to-end to audit our setup, identify architectural gaps, and guide our team on hardened implementation. This project must move fast. If your timeline is measured in weeks, please do not apply. We want someone who looks at this scope, jumps into a review session, and delivers actionable architectural guidance in days. This starts as a focused, urgent consultation. However, we expect ongoing advisory work—follow-ups, architecture adjustments, and enhancement reviews—as the AI tooling landscape shifts. For the right engineer, this will turn into a recurring relationship. We are completely open to a fixed price per milestone or an hourly structure. **What You Need to Have Actually Shipped and Can Review (Not Just Read About)** * **Full Agentic Coding Harnesses:** The entire loop: orchestrator → subagent → CI gate → merge loops. * **Isolation Layers:** Configured execution layers (such as E2B, Modal, or secure Docker runtimes) as isolated sandboxes for AI-generated code. * **Parallel Claude Code Sessions:** Managed multiple simultaneous subagents on scoped tasks via Git worktrees. * **Self-Hosted LiteLLM Gateways:** Routing to multiple models (Claude, GPT, Gemini, DeepSeek). * **MCP Server Infrastructure:** Connected file system, PostgreSQL, Atlassian, and Slack tool layers for active agents. * **Agent Framework Structures:** Used CLAUDE.md, COMMON\_MISTAKES.md, subagent role definitions, hook scripts, and settings.json. * **Human-in-the-Loop Orchestration:** Built Plan Mode or equivalent approval gates before agent execution. * **Multi-Agent Frameworks:** 7-agent feature factory patterns or frameworks like LangGraph, CrewAI, or Autogen. * **Durable Workflow Engines:** Applied Temporal, n8n, or similar tools for long-running agent workflow execution. * **Mechanical Quality Gates:** Treating CI green as the ultimate gate for agent output quality. \[[1](https://manveerc.substack.com/p/ai-agent-sandboxing-guide)\] **Our Current Stack (What you are reviewing)** * **Backend:** Python (FastAPI / Django) & Node.js (TypeScript) * **Frontend:** React (Next.js) * **Database & ORM:** PostgreSQL / Prisma / SQLAlchemy * **Infrastructure:** Docker Compose, AWS (ECS/EKS) * **CI/CD:** GitHub Actions / GitLab CI * **AI Layer:** Claude Code with shared `.claude/` directory, CLAUDE.md, and LiteLLM gateway in Docker * **MCP:** Atlassian (Jira/Confluence), custom PostgreSQL MCP server, Slack * **Workflow Automation:** Temporal / n8n * **QA Automation:** Playwright / Autonoma **Scope of Work (Review & Advisory Only)** 1. **Comprehensive Audit:** Audit our current agent harness and identify architectural gaps against a production-grade standard. 2. **Sandbox Strategy Consultation:** Review our environment strategy to ensure highly secure, isolated execution runtimes for agent code runs. 3. **Workflow Hardening Review:** Evaluate our parallel agent workflow setup (Git worktrees, subagent role configs, hook scripts, and settings lockdown). 4. **CI Pipeline Integration Strategy:** Advise on wiring our sandbox execution layer into the existing CI pipeline so agent-executed code runs in clean snapshots, not live infra. 5. **Architectural Runbook:** Deliver an optimization report / documented standard that our backend lead can easily own and execute going forward. **How to Apply** Skip the generic pitch. Show us something real to be considered: 1. A GitHub repo, architecture diagram, or Loom walkthrough of an agentic harness you have actually shipped. 2. Specific tools from our stack you have personally configured (E2B, LiteLLM, Claude Code, etc.). 3. One sentence explaining the hardest problem you solved to get full agent loops running reliably. 4. Your availability to conduct this high-impact architectural review session this week.

We’re hiring an extraordinary developer to own and grow our Base44 apps and sales products. around the future of AI discovery 1. Future of AI Discovery Core Demo – https://pull-discovery-core.base44.app/ You’ll evolve https://pull-discovery-core.base44.app/ into a beautiful, fluid, high‑performance, full-functional future of AI discovery demo following our advanced and sophisticated technical blueprint Integrate and orchestrate AI models incorporating LLM's, Search and World Models into a seamless experience with no visible seams between UX and intelligence. Own front‑end performance, responsiveness, and micro‑interactions—animations, transitions, and state changes should feel intentional and “alive,” not bolted on. Implement robust logging and analytics to understand how users explore, where they get stuck, and how the discovery engine can adapt dynamically. 2. Book Sales Engine – Six‑Channel Publishing System The second current Base44 project is a system that operationalizes our comprehensive sales plan across six channels. SEE THE COMPREHENSIVE BOOKSALES PLAN ATTACHMENT UNDERNEATH THIS POSTING You will: Translate a detailed multi‑channel publishing strategy (KDP optimization, physical bookstores via IngramSpark, other digital platforms, libraries, bulk institutional sales, and authority‑engine content marketing) into concrete workflows, tools, and dashboards. Build internal interfaces and automations to: Track metadata, pricing, and promotions across Amazon KDP and other platforms. Monitor campaigns across TikTok, Meta, LinkedIn, YouTube, newsletters, and partnerships. Surface KPIs like BSR, review velocity, ad spend, email growth, library adoptions, and bulk orders in a single, coherent view. Design light internal UIs that make it easy for non‑technical team members to update copy, add titles, trigger campaigns, and view performance without breaking anything. Implement robust, testable integrations between Base44, external APIs, and data sources to keep everything in sync as we scale from 8 to 22+ titles and beyond. Who You Are We’re not looking for a generic “full‑stack dev.” We’re looking for an unusual combination of visionary and doer: Creative technologist mindset – You think in systems and interfaces at the same time. You care deeply about how a product feels as well as how it works. Obsessed with execution – You’re disciplined, structured, and relentless about shipping. You break ambiguity into sprints, reduce complexity into tickets, and never let projects stall. Proactive owner – You don’t wait for instructions. You propose better ways to do things, flag risks early, and bring options—not problems—to every conversation. Strong product sense – You can balance ideal UX with realistic constraints and understand when to ship v1 vs. when to invest in polish. Comfortable with complexity – Multi‑channel distribution, layered data flows, and evolving requirements don’t scare you; they energize you. Ideal Skills & Experience You don’t need all of these, but you should recognize yourself in most: 5+ years building production web applications, ideally with a strong front‑end/UI focus. Deep experience with modern web stacks (React/Vue/Svelte or similar) and TypeScript, plus comfort with Node or comparable back‑end runtimes. Strong visual/UI instincts: experience collaborating with designers or owning design yourself for data‑rich interfaces and dashboards. Experience integrating AI/LLM APIs and retrieval systems into real products (RAG flows, multi‑step tool use, chat‑like interfaces, recommendation engines). Experience with analytics and experimentation: event tracking, funnel analysis, A/B testing. Familiarity with publishing, ecommerce, or multi‑channel marketing systems is a plus (KDP, IngramSpark, email platforms, ad platforms, analytics). Prior work in environments like Base44 or other low‑code/agentic platforms is a strong plus, but not required if you learn fast.

I'm looking for a skilled developer who can move fast, think creatively, and act more like a partner than a contractor. If you're someone who builds things quickly, brings ideas to the table without being asked, and genuinely cares about creating great experiences for end users, keep reading. -—————- **What You'll Be Working On:** This product sits at the intersection of AI, data, and customer experience. At its core, it needs to: - Monitor and process large volumes of data** in or near real time — surfacing insights, anomalies, and patterns that matter. - Send automated personalized outreach via SMS and email — based on the data signals and triggers, the system should be able to generate and send personalized messages to the right person at the right time, without manual intervention - Integrate with POS systems and CRMs** — pulling, syncing, and acting on data across platforms - Deliver a seamless, intuitive customer-facing experience** — this isn't just a backend tool, how users feel when they interact with it matters enormously - Be built on top of **Claude (Anthropic's AI)** using **Claude Code** as a core part of the development workflow We're in early stages, which means we're figuring things out as we go. That's not a warning — it's an opportunity for the right person. --- **What I'm Looking For:** - Hands-on Claude Code experience** — you've actually built with it, not just read about it. Experts only please - CRM and POS integration experience** — you've connected to platforms like Salesforce, HubSpot, Square, Toast, Lightspeed, or similar, and you know the quirks - Data monitoring and pipeline experience** — you've built systems that ingest, process, and surface meaningful signals from large datasets - Customer experience mindset** — you think about the end user constantly, and you've built tools that real customers interact with - Fast builder, fast thinker** — you're comfortable with ambiguity, can ship quickly, and know how to iterate without everything being perfectly defined upfront - Collaborative and opinionated** — I want someone who pushes back, brings ideas, and helps shape where this goes — not someone waiting for a spec I also want to **learn as we build** — so being able to explain what you're doing and why, in plain terms, is important to me. --- A Note Before You Apply: Please only submit a proposal if you have deep, hands-on experience with Claude Code — not surface-level familiarity, not currently learning it. We're looking for someone who has already put in the reps, knows the ins and outs, and can hit the ground running from day one. We respect your time and ask that you respect ours. If Claude Code isn't already a tool you've mastered, this isn't the right fit. **When You Apply, Please Include:** - Specific examples of tools you've built that involve **CRM or POS integrations** — name the platforms and describe what you built - Examples of **data monitoring or real-time data tools** you've worked on — what did it track, how did it work, what was the scale? - Any **AI-powered products** you've shipped, especially using Claude or other LLM APIs — links, screenshots, or descriptions - How you approach building something when the full picture isn't defined yet - A thought or two on what makes a truly great AI-powered customer experience — I want to see how you think --- **What This Could Become:** This is the beginning of something bigger. The right person won't just be a hire — they'll grow with the product. There's real potential for a long-term working relationship as this evolves.

Overview We run a high-volume B2B cold email program for a national background screening company. The infrastructure is built and live. We need an experienced operator to take full ownership — running the system, maintaining deliverability, managing lead pipelines, and continuously improving performance. This is not a setup job. This is an ongoing management role for someone who already knows these tools and can hit the ground running with minimal handholding. What You'll Own Lead Sourcing & Scraping — Build and manage Apify scraping workflows to pull targeted prospect lists from the right sources. You understand what makes a list clean versus garbage, and you enforce quality before anything touches an inbox. Email Infrastructure — Manage sending domains and inboxes in Scaledmail and Instantly. This means monitoring domain health, rotating inboxes appropriately, maintaining warmup, and keeping bounce rates low. You know what a burned domain looks like before it's actually burned. Automation & CRM Integration — Maintain and improve Make.com workflows that move verified leads from sourcing → enrichment → Instantly → HubSpot. Automations must be reliable and auditable. You're comfortable debugging broken scenarios and building new ones. Email Verification — Manage AnyMailFinder to verify contacts before they enter any sending sequence. You understand verification thresholds and make judgment calls on borderline lists. Campaign Management — Different sequences go to different audiences. You'll manage which contacts flow into which campaigns, monitor performance, and make copy or sequencing adjustments based on what the data shows. Reporting — Weekly summary of key metrics: open rates, reply rates, bounce rates, domain health, inbox placement, leads delivered to HubSpot. Flag issues before they become problems. This Role Is Right for You If: You've managed cold email programs at 30K–100K+ emails/month and know what breaks at scale You treat deliverability as non-negotiable — domain reputation is something you protect, not react to You're a systems thinker who builds processes that don't require babysitting You proactively flag when something looks off — you don't wait to be asked You can look at reply rate and bounce data and know what to adjust without being told You've personally managed Instantly, Apify, Make.com, Scaledmail, and AnyMailFinder — not just heard of them Hard Requirements Hands-on experience with Instantly (inbox management, campaign structure, sending limits, warmup) Hands-on experience with Apify (building or running scraping actors for lead generation) Hands-on experience with Make.com (multi-step automation scenarios, error handling, webhook flows) Experience with AnyMailFinder or comparable verification tools (not just "I've used email verification") HubSpot CRM experience — contacts, lifecycle stages, list management, basic workflow logic Demonstrated ability to keep bounce rates under 3% at volume English fluency — you'll be reading and interpreting campaign data and communicating findings clearly Nice to Have Experience with B2B lead generation for HR, workforce, or compliance-adjacent industries Copywriting or sequencing instincts — you can spot a weak subject line or a broken CTA Experience managing multiple client programs simultaneously (you know how to context-switch without dropping balls) To Apply Please include in your proposal: A brief description of the largest cold email program you've personally managed (volume, tools, outcomes) Your approach to maintaining deliverability at scale — specifically what you monitor and how often One example of an automation or workflow you built in Make.com for a lead gen or email program Your current availability (hours/week) and any other active commitments Proposals without these four items will not be reviewed. A note on fit: We're not looking for someone to check boxes. We want someone who treats this program like it's their own — who notices when something's underperforming and already has a fix in mind before we ask. If that's not how you work, this isn't the right role.

We're a growing service company looking for an experienced developer to build a Slack bot that answers employee questions about our HR policies, SOPs, and internal documentation. Team members will tag the bot in a channel, ask a question in plain language, and receive a conversational, accurate answer grounded in our documented materials. **This is a build + teach engagement.** I have no coding background, and a core requirement of this project is that you walk me through your decisions and architecture as you build, so I can understand, maintain, and eventually extend the system myself. If you're a strong developer but don't enjoy explaining your work, this isn't the right fit. ## What You'll Build A production-ready Slack bot with the following architecture: - **Slack integration** using Slack's Bolt framework (Python or Node.js — your recommendation welcome) - **Retrieval-Augmented Generation (RAG)** pipeline: questions are matched against our documentation via semantic search, and relevant context is passed to an LLM for a conversational answer - **Vector database** (Pinecone, Weaviate, or a comparable option you can justify) storing embeddings of our policies, SOPs, and transcripts - **OpenAI API** integration for embeddings and chat completions - **Document ingestion pipeline** that can handle multiple source formats: Word docs, PDFs, spreadsheets, and plain-text transcripts (e.g., exported Loom video transcripts) - **Source citations** in bot answers, so users can see which policy or document the answer came from - Deployment to a cloud environment (AWS, Heroku, Railway, or similar) with clear instructions for how it runs and how to restart or update it ## Technical Requirements You should have demonstrable experience with: - Slack app development (Bolt framework, event subscriptions, OAuth/permissions setup) - OpenAI's API (chat completions and embeddings) - RAG architecture and vector databases (Pinecone, Weaviate, Qdrant, pgvector, or similar) - Python or Node.js backend development - Cloud deployment and basic DevOps (environment variables, API key security, uptime) **In your proposal, please link to or describe at least one similar project you've built** — ideally a Slack bot, a RAG system, or an LLM-powered internal tool. ## Deliverables 1. A working Slack bot deployed to production and connected to our Slack workspace 2. Document ingestion process (with instructions or a simple tool for me to add new documents myself as our documentation grows) 3. Full source code in a repository I own, with clear comments 4. **Written documentation** covering: system architecture, how each component connects, how to add/update documents, how to update API keys, and common troubleshooting steps 5. **Teaching sessions**: recorded screen-share walkthroughs (or live calls) at each major milestone explaining what was built and why — I estimate 3–5 sessions of 30–60 minutes 6. A handoff session at the end where we test the bot together and review maintenance procedures ## Communication & Working Style - Regular progress updates (at minimum, 2x per week) - Willingness to explain decisions in plain English, not just technical jargon - Patience with beginner questions — teaching is part of the paid scope, not a favor - Fluent written and spoken English - Availability for scheduled video calls (please note your time zone in your proposal) ## Scope Notes - Initial document set is modest, but the system should be designed to scale as our documentation library grows significantly - Future phases may include: automatic transcript ingestion from Loom, additional Slack channels/workflows, and analytics on what questions get asked — mention if you have experience with any of these - I will provide: Slack workspace admin access, OpenAI API account, and all documentation to be ingested ## How to Apply In your proposal, please include: 1. A brief description of a similar project you've built (links or screenshots appreciated) 2. Your recommended tech stack for this project and a one-paragraph explanation of why 3. Your approach to the teaching/documentation component 4. Estimated timeline and total cost (fixed price preferred; open to milestone-based payment) 5. Your time zone and general availability Proposals that are clearly personalized and address the teaching component will be prioritized. Generic copy-paste proposals will be declined.

Create an A.i sales agent that automates tasks in real estate