Overview We’re a software company that resells Microsoft licenses as part of our SaaS product and deploys workloads in Microsoft Azure. We need a specialist who can accurately model our per-user and per-deployment costs across both Azure infrastructure and Microsoft licensing so we understand exactly what each customer deployment costs us. What you’ll do • Build a clear, reusable cost model for a product deployment that combines Microsoft 365 licensing (e.g. E3/G3) with Azure Virtual Desktop (AVD) • Use the Azure Pricing Calculator to estimate infrastructure costs across different VM sizes and configurations (e.g. 8 GB vs 16 GB RAM, session host counts, storage, bandwidth) • Break down Microsoft licensing costs per user, including how E3/G3 and any add-ons stack up • Model how costs scale as we add users/seats, and identify the main cost drivers • Deliver the model in a spreadsheet we can adjust ourselves (change RAM, seat count, VM size, etc. and see the cost update) Required expertise • Hands-on experience with the Azure Pricing Calculator and real-world Azure cost estimation • Strong knowledge of Microsoft 365 / Azure licensing, including CSP/reseller licensing models • Experience with Azure Virtual Desktop sizing and cost (session hosts, VM SKUs, storage, FSLogix, etc.) • Ability to translate technical configs into a clean cost breakdown a non-engineer can follow Nice to have

AI Workflow & Automation Consultant for Executive Search Firm We are an executive search firm looking for an experienced AI technology consultant to help us evaluate, improve, and automate our internal workflows. We are not looking for someone to simply introduce generic AI tools. We want someone who can take a hands-on look at how our business currently operates, understand our recruiting/search process, and help us create practical, efficient AI-enabled workflows that our team will actually use. About Our Current Tech Stack We currently use: RecruitCRM as our applicant tracking/search CRM Microsoft 365 across the business Microsoft Copilot as our enterprise AI tool Claude, which integrates with RecruitCRM Microsoft Teams, Outlook, OneDrive, SharePoint, Word, Excel, and PowerPoint Additional recruiting tools, interview notes, candidate documents, and internal templates We want to better connect and leverage these systems so we can reduce manual work, improve consistency, and make our team more efficient. What We Need Help With We are looking for someone to review our full process and help identify where AI, automation, integrations, or better workflows can improve the way we work. This may include: Reviewing our current recruiting/search workflow from intake through candidate presentation Evaluating how we use RecruitCRM, Copilot, Claude, Microsoft 365, Teams, Outlook, OneDrive, and SharePoint Identifying repetitive manual tasks that can be automated or streamlined Helping us create better workflows for candidate presentations, interview notes, client updates, reporting, and document management Recommending practical AI tools, prompts, templates, automations, or integrations Helping us organize files, notes, candidate materials, and client deliverables more efficiently Training or documenting best practices so our team can adopt the new workflows Ideal Background The ideal consultant will have experience with: AI workflow design for small or mid-sized businesses Microsoft 365, Microsoft Copilot, Teams, Outlook, OneDrive, and SharePoint Recruiting, staffing, executive search, or professional services workflows CRM or ATS systems, ideally RecruitCRM or similar platforms Claude, ChatGPT, Copilot, or other AI tools used in business operations Automation tools such as Power Automate, Zapier, Make, or similar Process mapping, workflow optimization, and implementation Project Goal Our goal is to have someone come in, understand how we work today, and help us build a more efficient AI-enabled operating system for the business. We want practical improvements, not theoretical recommendations. The right person should be able to assess our current state, recommend what should change, help implement improvements, and provide clear documentation or training for our team. Deliverables May Include Current workflow assessment AI and automation opportunity map Recommended tools and integrations Updated workflows for key business processes Reusable prompts, templates, or SOPs Microsoft 365 / Copilot / RecruitCRM optimization recommendations Implementation support Training documentation for our team To Apply Please include: A brief overview of your experience with AI workflow consulting Examples of similar projects you have completed Your experience with Microsoft 365, Copilot, Claude, RecruitCRM, or recruiting workflows How you would approach reviewing and improving our current process Your suggested project structure and estimated timeline We are open to either an initial audit/strategy project or a longer-term implementation engagement depending on fit.

I'm a retired entrepreneur and active investor looking for a skilled Claude AI practitioner to serve as a private tutor and advisor. I use Claude regularly and have a working Microsoft 365 integration in place, but I want an experienced guide to help me unlock advanced capabilities and build efficient, reusable workflows tailored to my work. This is not a beginner engagement. I learn quickly, prefer direct feedback over hand-holding, and want sessions focused on my actual use cases — not generic training. Topics to Cover - Claude Projects — structure and strategy for ongoing, organized work - Investment and general research — synthesizing company, market, and topic information efficiently - Correspondence — drafting polished emails in Outlook that match my voice with minimal editing - Document analysis — extracting key information from legal, financial, and fund documents - Microsoft 365 add-ins — what's available and genuinely useful for Word, Excel, and PowerPoint - Voice input and dictation — getting started and optimizing as a primary input method - Workflow building — creating persistent, reusable tools rather than starting from scratch each session - Agents, skills, and connected tools — connecting external tools, leveraging agentic capabilities, and building autonomous workflows - Prompt craft — advanced techniques applicable across all of the above Ideal Candidate - Hands-on experience with Claude (not just ChatGPT or general AI) - Background working with business operators, investors, or executives — not primarily developers or academics - Can demonstrate real-world applications, not just theoretical knowledge - Comfortable moving at a fast pace and adapting sessions to my priorities Format Virtual sessions via video call, 60–90 minutes each. Frequency to be determined based on fit and progress. Looking to begin with 4–6 sessions and reassess. To Apply Please include: 1. A brief description of your hands-on experience with Claude specifically 2. One or two examples of business or executive use cases you've worked on 3. Your availability and hourly rate A short introductory call before committing to paid sessions is expected.

We have an existing application that includes several AI-powered features and integrations. Some features are currently not functioning as expected, and we are looking for an experienced developer to review the codebase, identify the root causes, and implement reliable fixes. The ideal candidate should be comfortable working with AI/LLM integrations, debugging complex systems, and improving existing functionality without disrupting the overall application.

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 are looking for an entry-level Software Engineer who is strong in computer science fundamentals and algorithms. You will work on real-world software problems. This role suits someone who enjoys bridging theory and practice: thinking carefully about problem formulation, writing clean and efficient code, and taking ownership of results end-to-end. ROLE OVERVIEW You will work within a small, cross-functional team to build software. You will be expected to think algorithmically, write quality code, and communicate your findings clearly to non-technical stakeholders. KEY RESPONSIBILITIES Analyse product and business requirements provided by the team. Select appropriate algorithms and architectures based on data characteristics, constraints, and performance requirements. Design and implement efficient data structures and algorithms. TOOLS & STACK Knowledge in these areas are preferred. Postgres and Mongo DB Machine learning and LLM frameworks Middleware and mobile concepts especially React-Native and Javascript/NodeJS Infrastructure: Basic familiarity with GCP or AWS Version control: Git QUALIFICATIONS Bachelor's degree in Computer Science is preferred Strong foundations in algorithms and data structures — able to reason about complexity and write efficient code. Good understanding of machine learning and LLM concepts Clear written and verbal communication; able to explain model behaviour and trade-offs to non-specialists.

Description We are a US-based software company that already runs AI coding agents in daily engineering work. We are looking for a senior agentic development expert to help us push further. This is a specialist engagement, not an entry-level or generalist AI role. We want someone who has done this for real teams shipping production code and can go deep quickly. The engagement starts with a focused review of how we use agents today and where they can safely take on more, followed by a practical plan we can act on. Specifics are shared under NDA once we shortlist. You are a strong fit if you: - Have designed and rolled out agentic development workflows for a production engineering team, with results you can point to - Know Claude Code at an expert level: harness setup, context management, custom skills and slash commands, subagents, hooks, and MCP - Have integrated agents into an existing codebase and CI, including automated review and guardrails - Can advise on running agents securely around proprietary code and secrets - Can assess a team's current setup and turn it into concrete, sequenced steps This is probably not the right fit if: - Your experience is mostly personal projects, tutorials, or casual use of AI chat tools - You have used AI coding tools but have not set up team-level workflows or guardrails - You are a generalist looking to branch into AI Nice to have: - Python backend and web application experience - Experience with automated, agent-driven code review and test workflows Engagement: - Remote, expert-level rate - Short initial engagement with potential to extend - Some availability for scheduled, recorded calls - NDA required before we share specifics To apply (proposals without these will not be considered): - A specific example of an agentic development setup you built for a team, what you designed, and the outcome - The AI coding agents you have worked with and the depth of that work - Links to anything that shows your work (skills or agent configs, writeups, repos, demos), if you can share them

We are an investment firm with a portfolio of healthcare companies. We are seeking to begin building our data capture systems across our business and layer AI to surface summarize and store insights. This is a process that is in parallel to our operations team SOP'ing our process in anticipation of expansion. It is our opinion that we have a relatively simple business process from end to end and lots of potential to capture useful data signals across each department/function. We have drafted a rough business process / data ontology diagram showing our preferred approach. We are seeking an expert to: 1 ) Create lightweight data systems to capture data signals from end to end across our business (Recruiting to Onboarding to Scheduling to Payroll to Finance to Legal to). This also includes organizing and categorizing our past / existing data in addition to capturing signals for future data. 2 ) Layer AI / agentic AI automations that can surface insights, categorize and aggregate info, populate knowledge databases, etc. Example Data Signals / Use Cases: Fireflies recorded meetings Tagging emails in inbox as Legal/Finance/Scheduling/Onboarding etc Job Board Postings Airtable (For building a lightweight scheduling/employee management system) (For storing a knowledge database and rolodex) To Apply: Please briefly present an instance of implementing a similar lightweight solution to capture data signals and convert the data into meaningful and actionable insight via AI

I need a advanced agentic system built with persistent memory and up to 6 agents that work together. I am building a franchised coffee shop business. there is so much data that can be pulled together and harvested from customer spending habits and also what is the highest grossing items that sell , vs the most profitable hours of the day. All that data needs to be meshed with the actual Quickbooks data and financials. All that then needs to be balanced with real world site selection for new coffee shop locations. Here is what I need: Agent 1. Pulls information Directly from clover POS automatically. Agent 2. takes Agent's 1 information and cross references with Margin Data from Quickbooks. Recommends New drinks that are both on trend AND High Margin. Agent 3 is the financial Agent. It works directly with Quickbooks. It monitors cash flow and alerts when labor percentage exceeds parameters. It also stress tests expansion and " what if" scenarios. Agent 4. the site selection agent. agent 4 monitors LoopNet, Costar, and parcel data for commercial land available. It cross references traffic count and demographics, it checks competitor coffee presence etc. Agent 5 is the capital strategist. when agent 4 finds a location, it consults with agent 3 which is connected to Quickbooks , it models out loan scenarios, cash flow impact. and helps run " what if " scenarios that it gets asked. Agent 6 is the main Orchestrator that runs everything that I would communicate soley with through Whatsapp. It connects all the agents and pulls data collectively and makes them all work together and stress tests ideas that one agent might find.