Automating Repetitive Tasks in Consulting Workflows

I turned the most annoying 20 minute task of my job into 20 seconds. Here's the step-by-step breakdown: For years, I've been drowning in business card requests. Emails at all hours, random texts, people stopping by my office - all asking for the same thing but never giving me complete information. I'd spend 15-20 minutes per request just coordinating between employees, our designer, and placing orders. It was literally the least important but most time-consuming part of my week. Working with Claude (Anthropic's AI), I built my first AI agent that completely automates this workflow. Now when someone needs business cards, they fill out a simple form in Teams. The moment they hit submit: ✅ Data automatically saves to SharePoint ✅ A ClickUp task gets created for our designer with all the details ✅ Task gets assigned with a 3-day deadline ✅ I get notified when it's ready for ordering What used to take me 15-20 minutes of back-and-forth now happens in seconds. Zero manual work on my end. The crazy part? This entire system was built in a few hours using tools we already had - Power Apps, SharePoint, Teams, and Power Automate. No coding required. Here's my biggest takeaway: AI agents aren't just for tech companies. They're for anyone tired of repetitive tasks eating away at time that should be spent on strategic work. I'm a marketing leader at an oil and gas services company, not a programmer. If I can build this, anyone can. What repetitive task is driving you crazy? Maybe it's time to automate it. Next up: I'm eyeing our expense reporting process 👀

This week I wrapped up a small Power Apps and Power Automate solution for our team and it is already making our workflow feel lighter. We were juggling scheduling requests and calendar holds in a way that left a lot of room for missed steps. People were sending messages in different places and tracking follow up work manually. These requests impact timelines, client communication, and how we plan the rest of our work. Everyone needs clarity on what is coming, what is waiting for review, and what needs action. It was too easy for something to slip through the cracks. So I built a simple Power Apps screen and two lightweight automations to keep everything organized. The app lets you create a new calendar hold or update the status of an existing one all in one place. The automations handle everything that used to rely on memory. Here is what the solution does now: → When someone submits a new class request through the app, it is automatically labeled with a Status of Hold so nothing starts in a blank or unknown state. → A Power Automate flow creates a calendar event that blocks the time for our team with session details and the hold end date. If the status changes, the event is updated or removed automatically. → The team sees all pending items in one clean table inside the app and on the shared team calendar. → A second automation checks our list every day and looks for any hold that ends today. When it finds one, it notifies our admin and client services teams so they can follow up with the client at the right time. The result is exactly what we needed. ★ Items no longer get lost in chat threads or long email chains. ★ Everyone works from the same information, which removes a lot of guesswork. ★ The workflow is consistent, which makes collaboration smoother. No one has to track calendar blocks manually. No one has to chase down missing details. The workflow stays organized with minimal effort from the team. This is the kind of automation I love! Something that simplifies the day and removes repetitive work. And the pattern is useful in so many places. • Healthcare teams scheduling equipment or appointments • Facilities teams tracking room reservations or maintenance tasks • Higher education departments managing events or reviews • Nonprofits organizing volunteers and donation pickups • HR teams coordinating onboarding or training sessions Any team that handles requests and needs a simple way to see what is on Hold, what is approved, and what is overdue can adapt this approach. If you want a straightforward automation that makes work feel lighter, this is a great place to begin. Let’s start building!

Claude Skills turns AI into a teammate that already knows how you work. Here’s how to use it to save 30–40 minutes on recurring tasks. Most people still use AI like a search engine. Prompt → answer → context disappears → repeat. Which means every task starts from zero. You re-explain: ↳ your role ↳ your tone ↳ your formatting preferences ↳ your constraints ↳ your workflow Claude Skills removes that friction. Instead of re-briefing the model every time, you encode the instructions once  and Claude loads them automatically when the task appears again. That turns AI from a tool into something closer to operational infrastructure. Here’s the simple structure behind every Skill: Role Who Claude is in this context. Rules What to do, what to avoid, tone, formatting, standards. Trigger The phrase or task that automatically loads the Skill. Once written well, the model already understands the job before you even start prompting. A practical way to start: Build Skills for the tasks you repeat every week. Examples: Writing Skill Role: LinkedIn editor Rules: concise, structured, actionable, no fluff Trigger: “Write a LinkedIn post” Research Skill Role: industry analyst Rules: summarize trends, cite sources, highlight implications Trigger: “Research / analyze” Meeting Skill Role: chief of staff Rules: extract decisions, action items, owners, risks Trigger: “Summarize meeting” Each one eliminates repeated prompting. Setup takes about 10 minutes. But you can reuse the Skill hundreds of times. The important shift is this: The AI advantage does not come from better prompts. It comes from designing reusable thinking systems. ↳ writing frameworks ↳ research workflows ↳ analysis checklists Once encoded properly, they become persistent intelligence. That’s how individuals begin building what companies are trying to build at scale: an AI operating layer around their work. Prompting helps. But workflow design creates the real leverage. 🔁 Repost if this helped clarify how to turn AI into a system, not just a tool. ➕ Follow Gabriel Millien for practical insights on AI execution and building real leverage with AI. Image credit: Chris Donnelly

GRC Engineering Isn't Just a Cloud Native Thing Following a lot of questions from the community and people from "traditional" companies reaching out, I wanted to address something important. GRC Engineering principles work everywhere. Over 90% of the Fortune 500 is hybrid cloud. Outside of B2B SaaS and some B2C SaaS, no one's fully cloud-native for obvious reasons (being in business for more than 15 years) For cloud-native, the plumbing part of GRC Engineering (evidence collection, CCM, etc.) has been completely commoditised by tooling. GRC automation platforms are way cheaper than both dedicated engineering time and GRC pros vibe coding scripts. It's a no-brainer especially for smaller companies where compliance is a GTM play. For more established enterprises, it can be tougher to think through how GRC Engineering applies through very reductive lenses and might feel excluded from benefitting from the movement (I've heard it). Here are 10 real examples that prove you don't need to be cloud native to benefit: 🔧 PowerShell scripts that audit Windows server permissions weekly 📋 Excel macros that compare monthly configuration exports to baseline standards 📧 Email workflows that route security alerts based on asset criticality ⏰ Scheduled batch jobs that extract user access reports from legacy HR systems 🗂️ File-based automation that transforms mainframe reports into evidence packages 📊 Database triggers that log configuration changes for compliance tracking 🖥️ Desktop automation tools (like Power Automate) connecting COTS applications 📝 Template-driven processes that standardise evidence collection across teams 🔄 Robotic Process Automation for repetitive compliance tasks in legacy interfaces 📈 Custom reporting scripts that aggregate data from multiple on-premise sources All of this is ALSO GRC Engineering in my book. Whether you're working with: - 60-year-old COBOL systems - Bespoke applications with zero APIs - Physical infrastructure requiring manual checks - Mixed cloud and on-premise environments You can still apply GRC Engineering thinking: ✅ Systematise repetitive tasks ✅ Reduce manual evidence collection ✅ Create predictable, reliable processes ✅ Build transparency into compliance activities The goal isn't perfect automation. It's intentional improvement. Start where you are. Use what you have. Do what you can. That's GRC Engineering. Some resources for non cloud-native GRC leaders: 1️⃣ Podcast episode on GRC Engineering beyond the API with an ex-AWS exec https://lnkd.in/ewa3cmgf 2️⃣ How to orchestrate your controls in complex enterprise environments https://lnkd.in/eE7bWNjy 3️⃣ Building valuable automation in the enterprise GRC context https://lnkd.in/ev-x86Vu #GRCEngineering #COBOLove #LegacySystems

Ever feel like your team is stuck in an endless loop of manual data entry? (Automation Tip Tuesday 👇) That’s exactly where one of our clients — an education consulting firm — found themselves. They were juggling a whole tech stack of tools that didn’t “talk”  to each other, creating inefficiencies and double work. We started with a look into their sales workflow. 🔹 Sales data lived in HubSpot, but once a deal closed, someone had to manually update Asana to track project progress. 🔹 Internal teams worked from one Asana board, but clients needed visibility into their own project timelines — cue more manual updates. 🔹 With so much repetitive data entry, valuable time was being wasted on low-impact admin work. Here’s what we did: 🔗 HubSpot → Asana automation: We created an integration that auto-generates project tasks in Asana when a deal reaches a certain stage in HubSpot. No more copy-pasting! 📢 Internal and client boards sync: Internal progress updates in Asana now automatically reflect on client-facing Asana projects, reducing the back-and-forth. Less busywork, more productivity. By eliminating duplicate data entry, the team saved 10+ hours per week — time now spent on strategy and client success. When your tools work together, your team can focus on what really matters. Where is your team losing time? Drop a comment below! ⬇️ -- Hi, I’m Nathan Weill, a business process automation expert. ⚡️ These tips I share every Tuesday are drawn from real-world projects we've worked on with our clients at Flow Digital. We help businesses unlock the power of automation with customized solutions so they can run better, faster and smarter — and we can help you too! #automationtiptuesday  #automation #workflow #efficiency

If you’re an SAP consultant & you’re not sweating bullets after Sapphire 2024, you missed the memo. AI is coming for you. But Jonathan, you’re kidding, right? RIGHT? I wish I was: ‘Joule for Consultants’ will accelerate projects by +30% by automating many routine tasks. Whose routine tasks? Yours. Low-code/no-code development on BTP promises to make it easier for businesses to customize SAP themselves. Whose customization work? Yours. SAP’s “clean core” ERP strategy keeps S/4HANA free from excessive custom code, meaning fewer complex customizations. Whose complex customizations? Yours. But my friend, you are not going to freak out. You are going to pull yourself up by your bootstraps & prepare for the future. Here’s how you are going to turn these challenges into opportunities: 1. Embrace AI to Enhance Your Skills Joule is a game-changer, yes. But, instead of fearing it, leverage it. -Understand how Joule works & integrate it into your workflow to enhance productivity. -With Joule handling routine tasks, focus on higher-value activities like strategic planning.  -Take courses in AI & ML so you can stay ahead & offer new AI-driven services to your clients. 2. Master Low-Code/No-Code Platforms LCND development on BTP is revolutionizing customization. So you need to get ahead by mastering it. -Obtain certifications in SAP’s low-code/no-code platforms to help clients build & customize applications efficiently.  -Position yourself as an expert who can train client teams to use these platforms effectively.  -Create & market pre-built solutions that clients can easily customize, adding value to your consulting services. 3. Adapt to the Clean Core ERP Strategy With over 6k customers adopting RISE with SAP, the clean core ERP strategy is here to stay. Adapt & thrive. -Shift your focus from heavy customization to mastering configuration within the clean core framework.  -Advise clients on best practices for maintaining a clean core ERP system, ensuring they get the most out of their S/4HANA investment.  -Keep abreast of the latest updates & features in S/4HANA to provide the most current & relevant advice. 4. Evolve with the Industry The traditional SAP consulting model is evolving. So should you. -Commit to lifelong learning & stay updated with the latest SAP technologies & industry trends.  -Expand your expertise to include emerging technologies like blockchain, IoT, & advanced analytics. -Join SAP communities, attend conferences, & collaborate with other professionals to stay connected & informed. Sapphire 2024 was a wake-up call. The old way of doing SAP consulting is being profoundly reshaped. If you’re not adapting, you’re falling behind. The future is… LITERALLY  RIGHT  NOW It is time to pivot & find your new niche before it’s too late. If you don’t embrace these changes & you don’t take proactive steps, you may find yourself wishing that you had.

For PMs who want to use AI agents to be more productive but feel stuck coming up with ideas, I've been experimenting with a prompt: (this works best in a project that already has context on you/your team/product) ❝❝❝ Based on what you know about me and my organization, please brainstorm five ideas for an AI automation I can build using platforms such as Zapier Agents/Lindy AI/Relay app/Cassidy AI/Gumloop/ etc. These should help me as a product manager save time on draining-yet-essential tasks that take me away from more valuable, strategic, and creative use of my attention and energy. Ask yourself: What ongoing repetitive work requires some judgment and writing abilities, but not my full expertise and intuition? # IMPORTANT: these should be event-driven AI automations, not batch tasks Only suggest event-driven automations that process items one-at-a-time as they arrive. Do NOT suggest batch tasks that process multiple items on a schedule (e.g., "every morning scan all..." or "weekly compile..."). Why: AI automations shine in one-at-a-time, repetitive tasks. They do best when designed for immediate responses to individual triggers. ❌ WRONG (Batch Task): "Every morning, scan all new support tickets and summarize them" ✅ RIGHT (Event-Driven): "When a new support ticket arrives, analyze it and alert me if it's urgent" # Examples Below are examples of use cases where product managers have gotten a lot of value from AI agents. 1. Compile fragmented information that would require a lot of clicks “When a new message is posted in the #feature-requests Slack channel, distill the customer request into 2-5 keywords. Search those keywords in recent Slack threads, HubSpot conversations, and Gong snippets, and reply to the thread with what you find.” “Every morning scan my calendar for customer calls, and instead of searching the web, DM me with recent interactions from this customer in Salesforce, Gong, and Zendesk.” “Every Monday morning, prepare a competitor activity digest by scanning recent blog posts, App Store updates, and X announcements.” “When a customer churns, post a message in the #churn-lessons channel with recent support interactions, NPS rating and date, and churn survey response.” 2. Boring, Sisyphean tasks with high upside “Monitor the pricing pages of 5 competitors for changes.” “DM me a weekly report with bugs that are nearing their SLA deadline for the associated customer, and cc each respective CS representative.” 3. Scanning exhausting amounts of data “DM me with support cases where the resolution was around product confusion rather than tech.” “Monitor NPS responses being posted as messages in a Slack channel. If something is clearly a technical issue, create a support ticket in Zendesk.” 4. Drafting updates “Every Friday at 10 a.m., write a summary of progress made across all teams in our project board, across epics, changes made to scope, and highlight any timeline changes.” ❞❞❞

Most people are doing AI backwards. They pick a shiny tool, then try to jam it into their business. It doesn't stick. Here's what works instead: Start with the problem. Not the solution. I call this the Inside Out AI Framework. It's simple: 1. Identify the problem inside your business first 2. Map the entire process 3. Then find the AI tool that fits Not the other way around. Process mapping is your key skill here. By 2026, this will separate businesses that use AI well from those drowning in subscriptions they don't use. Here's how to do it: Step 1: Run a Time Audit Track everything you do for 3-5 days. • Look for tasks that are: • Repetitive • Draining Time-consuming These are your AI targets. Step 2: Map the Process Pick one workflow. Something manageable. Draw it out. Every step. Use a visual tool (Miro, Lucidchart, even pen and paper). Example: Email inbox management • Check inbox • Read email • Decide: respond, delegate, file, or delete • Draft response • Send • File or archive Make it detailed. Include context and decision points. Step 3: Color Code It Assign colors to: • Your tasks (blue) • Team tasks (green) • AI tasks (orange) This shows: → who owns what at a glance. → where AI can actually help versus where a human must decide. Step 4: Select the AI Tool Only NOW choose your tool. Match it to the specific steps AI can handle. In my email example, AI: • categorizes • drafts replies to common questions • flags urgent items Step 5: Build, Test, Iterate Implement it. Track the results. Refine. My email workflow went from 90 minutes a day to 10 minutes. That's 6.5 hours saved per week. AI doesn't fix broken workflows. It accelerates the ones that already make sense. Start small. One process. One quick win. Build confidence. Then scale. The businesses winning with AI in 2026 won't be the ones with the most tools. They'll be the ones who mapped their processes first. What's one repetitive task in your business you could map this week? ⬇️ Let me know in the comments Want to know if an AI use case is worth it? Use my ROI calculator. It’s free. ⬇️ Sign up here https://lnkd.in/dKNuKHza ♻️ Repost to help your network automate with AI.

Every finance team is trying to do more with less. In international development right now, that pressure is especially acute. AI hasn't closed the resource gap, and there's plenty of hype. I wanted to find out what it could actually do. So I started looking for places to test what was possible. Here's what I found: (1) Automating monthly check reconciliation for a school PTA I volunteer with. Every month when the bank statement drops, someone (read, me) has to manually find each check transaction in QuickBooks and attach a scanned image — dozens of checks, every month, without fail. Working with Claude Cowork, I built a tool that pulls each check image out of the PDF statement, crops each check, converts each image to a compressed PDF, and injects it directly into QBO through the browser — working inside the page's own JavaScript context to comply with QBO's content restrictions. Now I run it at month close. What used to be an hour of clicking (and clicking and clicking) is one command. I click run when I go to bed, and it's done by morning. (2) Building a Planful knowledge system that works like having a senior consultant on call. At Evidence Action, we recently adopted Planful for FP&A. It's a powerful platform, but the learning curve is steep — and we don't have a deep bench of technologists. So I loaded Claude with all relevant articles from Planful's knowledge base and hundreds of emails and tickets with guidance and instructions. Now I can get precise answers to highly specific questions, troubleshoot end-to-end, and design and build reports as if an expert were sitting next to me. What used to require a support ticket or an expensive consultant call now takes minutes. And the outputs are a lot prettier than what I could build on my own. I've started treating Claude like a tech-savvy analyst who's read everything and forgets nothing. When you give it the right context and ask precise questions, it extends what your team can actually produce — sometimes while you sleep. Finance is full of repetitive, rule-bound workflows. We've all heard that AI will automate the repeatable work so we can focus on the hard stuff. I'm beginning to see it happen. If Cowork can do that for a PTA's check reconciliation, I'm genuinely excited about what it opens up for finance teams operating at scale — in development and beyond.

I just solved a workflow problem that was eating hours of my time every week - and I want to share how I did it. Like many content creators, I was manually converting my Beehive newsletter drafts into markdown for my website. Copy, paste, reformat, fix images, adjust embeds... you know the drill. It was tedious and error-prone. So I built a custom MCP (Model Context Protocol) server in Java that: • Connects directly to Beehive's API • Pulls draft content automatically • Converts HTML to my specific markdown format • Handles images, YouTube embeds, and Twitter posts • Creates files in the right directory structure The best part? I can just tell Claude: "Grab the latest draft and create the markdown file for my website" - and it handles everything. This isn't just another toy tutorial. It's a real solution to a real problem that saves me hours every week. The MCP server gives Claude the exact tools it needs to automate complex workflows that would be painful to script manually. I've even set up GitHub Actions to build native images for Mac, Windows, and Linux - so you don't need Java installed to use it. The source code is available on GitHub if you want to see how it works or build something similar for your own workflow. What manual tasks in your workflow could benefit from this kind of automation? Sometimes the best solutions come from scratching your own itch. Watch the full demo: https://lnkd.in/e-M2fMZy ##MCP #Java