Autonomous Scheduling Tools

10^30000 scheduling combinations. 50 hours per week in Excel. If you've lived inside traditional WFM tools, you know this headache. Assembled's new AI-powered Schedule Generation does it in minutes. Here's the breakdown: 1,000 agents. 5 shifts each. 8 hours per shift. That's 5,000 shifts to schedule. Each shift needs: One productive event (chat, email, or phone). Two breaks. One lunch. One meeting. Discretize 8 hours into 15-minute blocks and you get 32 options. For non-productive events alone: 32 × 31 × 30 × 29 / 2 = 431,520 combinations per shift. Multiply by 3 productive event options. 1,294,560 combinations per shift. Now do that for 5,000 shifts. (10^6)^5000 = 10^30000. That's a number with 30,000 digits. At 2,000 digits per page, it takes 15 pages just to write it out. The “nurse scheduling” problem is a classic NP-hard problem. This is what workforce managers are solving with spreadsheets. Assembled's AI-powered Schedule Generation feature handles this in minutes. Agent needs Thursday off for a doctor's appointment? Old way: Submit request. Wait for approval. Hope it doesn't conflict. Assembled's way: Integer linear programming for coverage optimization. Constraint programming for breaks, lunches, and labor law compliance. Decomposition to break 34,000 weekly shifts into 50 parallel subproblems. 2 hours becomes 10 minutes. Agents can also browse available swaps directly in the system. AI ensures swaps follow your rules: Matching skills Queue compatibility Channel requirements. Our schedule Layers prevent coverage gaps entirely. It has three intelligent layers: Productive work Meetings/breaks Time off. When a training cancels, productive work surfaces automatically underneath. One global payments company told us: "This replaces our hideous spreadsheet where we export schedules just to flag compliance issues. Programming rules directly in is chef's kiss." AI handles 10^30000 combinations. Managers can now handle strategy. Kudos to the team on this big, NP-hard launch. Antony Phillips, Claire D., Jack Gleeson, Malfy Das, Nicole Pan, Zach Clark, Chancie(Qianshi) Zheng, Charlie Rotholtz, David Patou, Devon Berger, Todd Bergman, Dan Hertz

Last night I hooked Claude Desktop up to my Outlook calendar using an MCP server, and I'm a little annoyed at myself for not doing this sooner. As everyone now knows, the MCP (Model Context Protocol) lets AI assistants like Claude interact directly with your tools. Calendar, email, git, databases, whatever. You configure a server, authenticate, and suddenly your AI assistant isn't just answering questions. It's operating inside your actual workflow. I used a community MCP server called "outlook-mcp" from Richard Laurence Yaker (ryaker) on GitHub. It connects Claude to Outlook using the Microsoft Graph API and took about 15-20 minutes to set up. It supports full calendar management and some email functionality. The process was simple: - Registered an app in the Azure Portal. - Cloned the repo, installed dependencies. - Dropped the config into Claude Desktop. - Authenticated via OAuth. I already created a study plan and workout routine with Claude, so I told it to create a schedule and send it to my calendar. In about 45 seconds, events were popping up on my calendar. No copying and pasting. No switching tabs. No manually entering times. One conversation, plan to calendar, done. I'm testing it out personally before I bring it into my work setup, but the implications are already obvious. As SRE folks, we spend our days automating tasks to eliminate toil. The whole playbook is about removing manual steps, but somehow I was still context switching between 6 different apps just to manage my day. MCP servers help eliminate that friction. The ecosystem is growing fast, too. Google Calendar, Slack, GitHub, databases, and cloud providers. There's an MCP server for almost everything now. And if there isn't one, you can build your own. If you're in DevOps, SRE, or any technical role and you haven't explored MCP integrations yet, you're leaving productivity on the table. I know because I was. Here's the repo: https://lnkd.in/eafJff97

I spend a huge part of my week just managing my calendar — finding free slots, rescheduling meetings, dealing with recurring events, and juggling multiple time zones. It’s tedious and eats into real work. That’s why I decided to build my own solution: a Google Calendar AI agent powered by Google’s Agent Development Kit. This agent can: 👉 Understand plain English commands like “Schedule a 1-hour call with Alex next Tuesday morning”. 👉 Suggest free time slots based on my existing calendar. 👉 Handle recurring events, cancellations, and attendees automatically. 👉 Work across time zones without any manual conversion. While building this, I learned something crucial: AI isn’t just about generating text — it can actually perform actions that solve real problems. Designing this agent taught me how to bridge natural language understanding with real-world API actions. I wrote a detailed step-by-step blog, including code snippets and logic, so anyone can replicate this setup or build their own AI productivity assistant: https://lnkd.in/dsDhtcMr #AIAgents #AgentDevelopmentKit Google Cloud #GoogleAI #GoogleCalendar #CalendarManagement #AgenticAI

I used Claude Cowork to build my own AI chief of staff. And you can too. I'm nicknamed it "The Jarvis Builder" Every morning at 5 AM, before my alarm goes off, Claude has already triaged my inbox, prepped me for every meeting on my calendar, flagged stale deals in my pipeline and color-coded them, scanned CMS and the Federal Register for policy changes that affect my practice, and pulled the latest literature in orthopedic trauma and clinical AI. By the time I pour coffee, I have an interactive dashboard with email drafts waiting in gmail, prioritized action items, and source links back to the original threads. I act from the dashboard and claude co-work. No switching between twelve tabs. No thirty-minute prep tax before clinic. Slack messages to my team are drafted. I have a personalized newsletter that pulled headlines I care about for me. And the longer arc of what I am trying to accomplish for the week, the month, and the year are sitting in a pleasant UI/UX that refreshes twice daily called "centering horizons". The architecture is pretty simple: Claude Cowork scheduled tasks run on a cadence (daily, weekly, monthly). MCP connectors give Claude access to your actual tools — Gmail, Calendar, Slack, Granola meeting transcripts, HubSpot, Brex. You write the prompt once, it can interview you to curate your tasks. It executes on schedule. I run about twenty tasks across my week, organized around the pillars of my life: clinical, company building, policy, academic, and personal. The personal ones are some of the most useful — a Friday grocery list based on next week's calendar, a travel-day counter that flags when I've been away from home too much, a monthly centering horizons page that maps my short-term, medium-term, and long-term goals into a single visual. Today I'm releasing the tool I built to make this accessible to anyone: The Jarvis Builder — an interactive configurator with dozens of scheduled tasks across 7 personas (Essential, CEO, Clinician, Knowledge Worker, Learner, Finance, Policy). Browse the library, preview every prompt, see your week at a glance, run a single Mega Interview that builds your entire personalized system, and export it ready to deploy. You don't need to be a clinician. You don't need to be technical. If your professional life runs on email, calendar, and cloud tools, you can build your own Jarvis this afternoon. My new Techy Surgeon article walks through the ssystem — how it works, how I use it, and step-by-step setup instructions so you can build yours. The prompt in my article will interview you and help you create your own system in Claude CoWork. "The Agentic Clinic" dives deeper, but the most important thing is to try to use these tools to leverage software to your benefit. And stay tuned for "Claude for Clinicians"! 🔗 Article below #AI #HealthcareAI #ClaudeAI #AgenticAI #HealthTech #ClinicalAI #Productivity #SurgeonLife #HealthPolicy #Anthropic

𝗖𝗮𝗻 𝗮 𝗦𝗰𝗵𝗲𝗱𝘂𝗹𝗶𝗻𝗴 𝗧𝗼𝗼𝗹 𝗥𝗲𝗱𝘂𝗰𝗲 𝗕𝘂𝗿𝗻𝗼𝘂𝘁 𝗮𝗻𝗱 𝗪𝗮𝗶𝘁 𝗧𝗶𝗺𝗲𝘀 𝗮𝘁 𝗢𝗻𝗰𝗲? Orlando Health thought their infusion clinics were running at full capacity. Turns out, they were just poorly scheduled. After implementing Epic’s infusion scheduling template generator, everything changed. 𝗧𝗵𝗲 𝗕𝗲𝗳𝗼𝗿𝗲 → Patients waited up to a week for an appointment → Nurses overwhelmed during midday peaks → 6-minute average scheduling calls → High turnover, overbooked chairs 𝗧𝗵𝗲 𝗔𝗳𝘁𝗲𝗿 → 32% drop in patient wait times → 50% increase in nurse satisfaction → 200 monthly care hours recovered → Appointments offered within 24 hours The difference? Smarter scheduling built around actual staffing, capacity, and patient needs not guesswork. 𝗪𝗵𝗮𝘁 𝗧𝗵𝗲𝘆 𝗗𝗶𝗱? → Used Epic’s system to auto-build templates based on data → Shifted scheduling conversations to system-recommended slots → Consolidated appointment info onto one screen → Automatically rebalanced unclaimed appointments overnight 𝗧𝗵𝗲 𝗥𝗲𝗮𝗹 𝗦𝗵𝗶𝗳𝘁? This wasn’t about more chairs or overtime. It was about reducing chaos through system logic and giving nurses and patients a better experience. 𝗬𝗢𝗨𝗥 𝗧𝗔𝗞𝗘? → Is your clinic really full or just misaligned? → Would automated scheduling free up care hours in your workflow? → Could smarter workflows reduce nurse turnover without increasing cost? #EpicSystems #DigitalHealth #InfusionCare #PatientExperience #ClinicalWorkflows #NurseRetention #SmartScheduling #OrlandoHealth #HealthTech #OncologyCare #EpicShare #TechlingHealthcare

It is time for another automation story. The Automated Interview Scheduler helps the Talent Acquisition teams to schedule interviews with candidates, based on information from our Applicant Tracking system and defined business mappings. The solution requests availability from the candidate via a designated UiPath app and aligns it to the one of the interviewers, prior to sending the actual invites. All interviews can be managed in a different UiPath app dedicated to Talent Acquisition team where they can edit candidates availability if requested, cancel interviews or monitor the invites responses for each interview. The business mappings are covering different types of interviews: (a) 1:1 Interviews, between the candidate and only one interviewer; (b) Panel Interviews, between the candidate and multiple interviewers at the same time and (c) Loop Interviews, a series of interviews one after another in the same day or in two consecutive days. How does it work? Requests candidate availability, follow-up on candidate response, checks interviewer(s)' availability in different systems (including Outlook), identifies suitable intervals for scheduling all types of interviews, sends meeting invite to candidate & interviewer/s via Outlook, generates Hacker Rank Link, sends Feedback Forms to interviewers and monitors invite’s responses. Busy automation. Removes a lot of mundane and repetitive activities of our colleagues. Automation built by our Center of Excellence using UiPath Business Automation Platform in collaboration with our People Operations Team. Florentina Rondin-Irimia, Ruxandra Radulescu, Elke Manjet, Elena Mega, Irina Căpățînă. #UiPath #ActionCenter #UiPathApps #AI+Automation

We tested 4 AI scheduling tools with network companies. The results surprised everyone. After weeks of real-world testing with Cal.com, Inc., Calendly, Reclaim.ai, and Clockwise, here's what we discovered: The fastest tool wasn't the highest-rated Speed matters, but user experience trumps everything. Teams consistently chose tools that felt intuitive over those that booked meetings 30% faster. Efficiency ≠ Effectiveness The most "efficient" AI often created the most friction. Simple automation beat complex algorithms every time. 🎯 Key findings: → Integration quality matters more than feature count → Teams preferred tools that learned their habits organically → Smart rescheduling saved more time than instant booking → Buffer time management was the hidden productivity killer This is exactly the kind of real-world tech discovery we dive into at PeopleAtom, our CXO community where we test, debate, and discover the best technology for people strategy and systems. Because the right tools can transform how your team operates. Which scheduling challenge frustrates your team most? Drop a comment below 👇 #AITools #Productivity #WorkflowOptimization #SchedulingTools #TechTesting

Every conference, I build a booth shift schedule. It’s one of those tasks that sounds simple - but quickly turns into calendar conflicts, last-minute swaps, and endless back-and-forth. So I automated it. I built a conference booth scheduling agent that pulls from reps’ Google Calendars (via WRITER's Google Calendar connector), accounts for travel, availability, and conflicting meetings, and outputs a ready-to-use booth schedule. Instead of manual coordination, I now just fill out a short playbook: 📌 Event name & time zone 📌 Conference expo hours 📌 Booth staff names & emails 📌 Scheduling constraints & preferences From there, the agent generates: 📌 A booth staffing grid I can drop straight into our Know Before You Go guide 📌 A confirmation message ready to paste into Slack 📌 A complete booth staffing schedule After running the playbook, all deliverables live in the agent’s deliverables tab. What was once reactive, manual, and chaotic is now structured and repeatable.  This results in fewer gaps, less back-and-forth, and a more seamless on-site experience!