How to Automate Cross-Team Workflow Integration

3 Workflows I've Automated for in-house teams. ① Ask Legal ② Procurement ③ Contract Review (not just the review!) 1. Ask Legal [or any department for that matter 🤷🏼♀️] You've heard me talk about legal teams and knowledge management. Long story short, your legal team is answering the same 20 questions over and over 😵💫 A simple way to save a CHUNK of time answering questions from the business (enabling them to go faster) ALL while having complete control & keeping a human in the loop? ↪️ Set up an 'Ask Legal' bot in your comms platform. ↪️ Sync it with your knowledge base (e.g GDrive/Notion/Sharepoint). ↪️ Set up your custom instructions (Want it to tag Bob on privacy questions only, specifically on a Tuesday? No problem).  ↪️ Don't want the answer to go straight out to the business without reviewing it first? Cool, turn on co-pilot mode. The result? 60-80% fewer repetitive queries. Your team focuses on the high value things that need a human lawyer. 2. Procurement Businesses have 100's of tools, but when departments don't speak to each other you end up with duplicate tools & subscriptions 😭 💵 🚽.  What if there was a way for the business to find out in <1 minute if there was a tool available that covered their needs, before needing to spend some hard secured department budget? Moreover, what if I told you, they could kick off the internal procurement process from the comfort of your comms platform? Team member : “Do we already have a tool for X?” in Slack/Teams ✅ Bot checks knowledge base (policies, procurement tool). ✅ If a match is found, it shares the approved tool & owner to contact. ✅ If not, the bot can ask the user for more info and direct them with next steps to kick off the procurement process from inside Slack/Teams. Ensuring your users ACTUALLY follow the process, without adding friction. Did I just see your CFO cry tears of joy? 3. Third Party Vendor Contract Review & Project Management Getting AI to redline a contract (as a first pass) is a huge win, but there's still the other pieces of the process missing, like: 🤷🏼♀️ The business figuring out IF legal review is even needed (according to company policy). 📨 The business actually submitting the contract to legal. 😩 Managing review capacity within the legal team. 🖥️ Getting the legal team to log & update the PM tool. The list never ends. Legal reviews only what actually needs their eyes, turnaround times improve, and the business stops pinging the team for “update pls?” in Slack : ) TLDR; Most legal teams are drowning in admin work that could be automated. I've built all of these using simple processes and tools (that I've found most businesses have). You also know I love a good Figma flow. So I’ve built them for all three of the above (see a sneak peak below). Want the entire thing? Comment "FLOWS" and I'll send them over. Also, tell me what you want to see - more of the above or step-by-step how-to build videos?

𝗜 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗠𝘆 𝗣𝗠 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝗶𝗻 10 𝗠𝗶𝗻𝘂𝘁𝗲𝘀—𝗛𝗲𝗿𝗲’𝘀 𝗘𝘅𝗮𝗰𝘁𝗹𝘆 𝗛𝗼𝘄 👇 Product teams waste 17% of their time on documentation and comms (McKinsey). And I automated the most tedious part for me using Lovable - with zero code.  👉 Turning detailed PRDs into internal launch comms, Notion posts, stakeholder briefs, and checklists. It was eating up hours every week — across product and growth team. So I thought, what if we just automated it? 🤔 𝗜 𝗯𝘂𝗶𝗹𝘁 𝗮 𝘀𝗶𝗺𝗽𝗹𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁: ✅ Reads our PRDs ✅ Extracts the key details ✅ Generates a Notion-ready launch post ✅ And even creates a structured PM checklist No code. Just a few smart prompt blocks. Now this agent saves our team 4–6 hours per launch, and keeps everyone aligned without the usual back-and-forth. In this post, I’m breaking down exactly how I built it step by step: - My exact 10-step framework   - Battle-tested prompts you can copy   - Common pitfalls (and how to avoid them)  👉 Swipe through to see how you can build your own AI teammate too. P.S. Should product teams have an "AI Agent Manager" role by 2025?

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

Day 2 learnings at the WCC event in Berlin. If you go “digital” in contractmanagement, the biggest risk is treating it as a tooling project. In practice, digital only works when you build a shared foundation first, then standardise, then automate, and only then scale adoption through behaviour and culture. Here’s a pragmatic step-by-step sequence that works. 1) Start with a uniform language (before you touch systems) If different teams use different words for the same thing, your data model will be inconsistent from day one. Align on a shared vocabulary and definitions, for example: contract types, obligations, milestones, change requests, claims, variations, approvals, risk categories, and ownership. This is not “nice to have”. It is the basis for clean reporting, reliable workflows, and meaningful automation later. 2) Do a cross-functional painpoint analysis (end-to-end) Digital contract management is cross-functional by nature: procurement, legal, contract management, finance, operations, and sometimes sales. Map the full lifecycle and identify painpoints together. Focus on where value leaks today, such as: handovers, unclear accountability, missing data, late approvals, uncontrolled changes, poor visibility of obligations, and recurring exceptions that are “handled in email”. 3) Implement a best-practice process framework (make it stable first) Before automating anything, implement a process framework that is clear, repeatable, and measurable. Define: - roles and decision rights - minimum required data per phase - standard workflows and gates - templates and playbooks - KPIs that reflect performance and compliance The goal is stability: a process that people can execute consistently, even without automation. 4) Once stable: automate the hell out of it (but only what you understand) Now you can digitise and automate with confidence: workflow routing, reminders, obligation tracking, dashboards, audit trails, integrations, and exception triggers. Automation should reduce friction and increase control. Not hide process weaknesses. If you automate a broken process, you simply get broken outcomes faster. 5) Then the real work starts: culture and behaviour (adoption is the multiplier) Processes and tools can look perfect on paper, but without adoption they will not fly. This is where many “digital transformations” stall. Plan explicitly for: - coaching and guidance in daily work - process support (someone must own questions and improvements) - error and exception handling (because reality never fits the happy flow) - feedback loops and continuous improvement - leadership behaviour that reinforces the new way of working Digital contract management is not a one-off implementation. It is a capability you build. If you follow this sequence: language → painpoints → framework → automation → behaviour. You create a foundation that scales, instead of a toolset that disappoints. #contractmanagement

There’s something frustrating about building integrations manually. You know what needs to happen, but you still spend hours writing glue code, chasing docs, tweaking edge cases. Even with AI, the first question is always the same: “Where do I even start?” That’s where Pathfinder came from - hybrid intelligence for building integration use cases. We needed a way to move faster without handing everything over to a black box. So we built a workflow that works like we do: Break the problem down. Add structure. Iterate. Review. Adjust. Each request moves through short, focused iterations, usually a couple of hours with updates at every step so you're never out of the loop. A human translates your request. AI builds. Another human reviews. You stay involved and can redirect anytime. You’ll see every request and result in a dashboard, along with credit usage. No guessing. No blind spots. Teams use Pathfinder to: - Build full integration prototypes - Create or extend connectors - Scale one use case across multiple APIs - Troubleshoot and improve broken flows We’ve used it ourselves to turn weeks of work into structured progress, without drowning in edge cases or technical guesswork. It’s not just magic. It’s just a better process. Want to see how it works? We documented the full flow here: https://lnkd.in/ehnW47bM

BPMN for Business Analysts: What, How, Why + a Simple Step-by-Step If you’ve seen “BPNM” floating around, the intended term is BPMN Business Process Model & Notation. It’s the global standard to visualize how work flows across people, systems, and teams. What is BPMN? A visual language with a small set of symbols to map processes end-to-end: • Events (circles): something starts/ends/happens (start, timer, error). • Activities (rounded rectangles): work done (task, subprocess). • Gateways (diamonds): decisions/splits/merges (XOR/OR/AND). • Flows & Messages (arrows): sequence vs. cross-team communication. • Pools/Lanes: who does what (orgs, teams, roles). • Artifacts: data objects, annotations, groups. How does it work? You place these symbols on a canvas to tell the story of a process from trigger to outcome capturing paths, exceptions, data handoffs, and responsibilities. Because the notation is standard, business, tech, QA, and automation platforms can all read the same picture. Why should a Business Analyst learn BPMN? • Clarity: turns messy narratives into one shared truth. • Alignment: reduces ambiguity between business & dev teams. • Traceability: links process steps to requirements, rules, and KPIs. • Automation-ready: many workflow engines (Camunda, Appian, etc.) use BPMN. • Improvement: surfaces bottlenecks, rework, and compliance gaps. • Scalability: easy to maintain, review, and version as processes evolve. A Simple Step-by-Step to Model with BPMN: 1. Define the goal & scope: What’s the business outcome? Where does the process start/stop? 2. Identify actors & boundaries List teams/systems → map them as pools/lanes. 3. Gather the “happy path” Capture the default flow first, from start event → end event. 4. Add tasks & sequence flows One task = one clear action. Keep verbs precise (“Validate KYC”, “Generate Invoice”). 5. Model decisions with gateways Use exclusive (XOR) for either/or, parallel (AND) for simultaneous work. 6. Place messages & data Cross-team handoffs = message flows; attach data objects where inputs/outputs matter. 7. Capture exceptions & timers Timeouts, cancellations, escalations → boundary events on the affected tasks. 8. Refine with subprocesses Hide detail that’s too deep; link to a child diagram when needed. 9. Validate with stakeholders Walk through scenarios, edge cases, and SLAs. Fix naming, remove noise. 10. Measure & improve Tag steps with KPIs (cycle time, wait time, error rate). Note pain points. 11. Version & publish Store the diagram, decisions, and assumptions; keep an As-Is and To-Be.

𝗪𝗵𝗲𝗻 𝗦𝗵𝗼𝘂𝗹𝗱 𝗬𝗼𝘂 𝗖𝗮𝗹𝗹 𝗶𝗻 𝗮𝗻 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁? Not every process needs a full-blown AI agent. Sometimes a simple macro or integration does the trick. But there are clear signs that your workflow is begging for an autonomous assistant. Here’s how to spot them—and why agents succeed where traditional automation stalls: 🔍 𝟭. 𝗖𝗿𝗼𝘀𝘀-𝗦𝘆𝘀𝘁𝗲𝗺 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: You’re juggling data from ERP, CRM, email, and a custom database—and every handoff is a manual export-import. 𝗔𝗴𝗲𝗻𝘁 𝗪𝗶𝗻: An AI agent can ingest records from your ERP API, enrich contacts in your CRM, send templated emails, and log responses. 𝘢𝘭𝘭 in one continuous flow. No more copy-paste handovers. 📚 𝟮. 𝗨𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱-𝗗𝗮𝘁𝗮 𝗢𝘃𝗲𝗿𝗹𝗼𝗮𝗱 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: Your team spends hours reading PDFs, extracting key specs, and summarizing them in slides or Jira tickets. 𝗔𝗴𝗲𝗻𝘁 𝗪𝗶𝗻: An agent reads documents, highlights critical passages, generates bullet-point summaries, and files them where you need. slashing review time from hours to minutes. 🔄 𝟯. 𝗕𝗿𝗶𝘁𝘁𝗹𝗲 𝗥𝘂𝗹𝗲 𝗘𝗻𝗴𝗶𝗻𝗲𝘀 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: Your decision tree works until a rare edge case pops up, then everything crashes and you scramble for ad-hoc fixes. 𝗔𝗴𝗲𝗻𝘁 𝗪𝗶𝗻: Agents pair a flexible language model with hard constraints (“never quote over X without approval”) so they adapt to new inputs without breaking your guardrails. 📈 𝟰. 𝗦𝗶𝗴𝗻𝗮𝗹-𝗗𝗿𝗶𝘃𝗲𝗻 𝗧𝗿𝗶𝗴𝗴𝗲𝗿𝘀 𝗣𝗿𝗼𝗯𝗹𝗲𝗺: You know that building-permit filings or job postings signal capital-investment opportunities. if only you could catch them in real time. 𝗔𝗴𝗲𝗻𝘁 𝗪𝗶𝗻: An agent monitors permit APIs, scrapes relevant job boards, scores leads by fit, and pings reps the moment a trigger appears. 🎯 𝗣𝘂𝘁𝘁𝗶𝗻𝗴 𝗜𝘁 𝗜𝗻𝘁𝗼 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗲 1. 𝗠𝗮𝗽 𝗬𝗼𝘂𝗿 𝗦𝘁𝗲𝗽𝘀: Document each tool and data source in your current workflow. 2. 𝗜𝗱𝗲𝗻𝘁𝗶𝗳𝘆 𝗣𝗮𝗶𝗻 𝗣𝗼𝗶𝗻𝘁𝘀: Where do handovers break down? Which tasks feel painful or error-prone? 3. 𝗣𝗶𝗹𝗼𝘁 𝗮 𝗠𝗶𝗻𝗶-𝗔𝗴𝗲𝗻𝘁: Start with a single “signal-to-action” flow, say, permit-to-email and measure time saved. 4. 𝗜𝘁𝗲𝗿𝗮𝘁𝗲 & 𝗘𝘅𝗽𝗮𝗻𝗱: Add complexity. Multi-tool flows, conditional logic, and human-in-the-loop checks as you gain confidence. Agents aren’t black boxes. They shine where processes span multiple systems, rely on unstructured inputs, or need continuous vigilance. If your team still wrestles with exports, manual reviews, or brittle scripts, an AI agent could help. 𝗖𝘂𝗿𝗶𝗼𝘂𝘀 𝘄𝗵𝗲𝘁𝗵𝗲𝗿 𝗮𝗻 𝗮𝗴𝗲𝗻𝘁 𝗳𝗶𝘁𝘀 𝘆𝗼𝘂𝗿 𝘁𝗼𝘂𝗴𝗵𝗲𝘀𝘁 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄?

All 20 members of Workflows.io use Claude Code daily. But it wasn’t straightforward to get to this point. It isn’t as simple as just purchasing a sub. You have to build the: - Context layer (company wiki) - Integration layer (MCPs, APIs, CLIs) - Execution layer (skills, internal apps, automations) And you can’t expect everyone to create their own versions of these. These layers should be built and maintained by the organization (usually a small team of dedicated builders). Here’s how I’d approach it if I had to start over: 1️⃣ Map Processes Feed Claude raw context on your current processes, with info on who does what. Every SOP, internal doc, or spreadsheet should be centralized. 2️⃣ Folder Structure Ask Claude to create a defined folder structure to house this data. My preferred structure: - 𝗖𝗟𝗔𝗨𝗗𝗘 .𝗺𝗱 - .𝗺𝗰𝗽 .𝗷𝘀𝗼𝗻 / .𝗰𝗹𝗮𝘂𝗱𝗲/ : 𝘀𝗸𝗶𝗹𝗹𝘀/, 𝗮𝗴𝗲𝗻𝘁𝘀/, 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/, 𝗵𝗼𝗼𝗸𝘀/, 𝗿𝘂𝗹𝗲𝘀/ / 𝗰𝗼𝗺𝗽𝗮𝗻𝘆-𝘄𝗶𝗸𝗶/ / 𝗿𝗮𝘄-𝗰𝗼𝗻𝘁𝗲𝘅𝘁/ / 𝗮𝗿𝗰𝗵𝗶𝘃𝗲/ 3️⃣ Connect MCPs & CLIs Hook up every relevant tool in your stack via MCP, CLI, or API. These are some of our favorites: HubSpot, Supabase, Pinecone, GitHub, Notion, Google Workspace, Apollo.io, Nooks, Instantly.ai, HeyReach, Ergo 4️⃣ Codify Knowledge into Wikis Guide Claude through digesting all the inputs and codifying them into AI-ready .md files. The goal: context on every business process maintained in GitHub. 5️⃣ Create Skills Use the process map to identify areas where the entire SOP could be automated. These are your skills. Some of our favorites: /content-ideator, /tam-mapping, & /campaign-builder 6️⃣ Data Sync & Automations Setup automations to consistently pipe in fresh business data. (e.g. transcripts, Slack convos, campaign data, CRM changes) 7️⃣ Build Agentic Workflows Use managed agents, scheduled runs or the Agents SDK to run your skills for you. (e.g. when an onboarding form is submitted → fill out internal documentation) 8️⃣ Deploy to the Team Give access to all the above via GitHub, a Claude plugin, or in some cases an internal app. 9️⃣ Educate the Team 3 things that worked for us: - Internal Claude workshops - Notion docs for every key component - A dedicated #claude-code Slack channel for troubleshooting 🔟 Feedback Loop Encourage your team to consistently suggest improvements via PRs. For agents where you have an objective readout for success (e.g. marketing agents), you can program them to self-improve. ━━━━━ This is the process we followed to fully integrate AI into our internal operations. I can't understate how big of an unlock this was. 100% worth the hassle. P.S. Save this post or send to a colleague if it was useful.

Anthropic shipped Claude Managed Agents last week and most people missed what actually changed. So here's a simple way to think about it. Every workflow your team runs falls into one of two buckets: tasks that require a human to initiate them every time, and tasks that just need to happen. Most teams have the second bucket full of things still sitting in the first one. That's the gap agents close. Here's how we're applying this at Understory: Outbound: Lists get pulled, enriched, sequenced, and pushed into HubSpot automatically. Someone still sets the strategy. Nobody has to fire the gun every morning. Client onboarding: There are 15 steps between a signed contract and a live campaign. Most of them are execution. An agent with persistent memory runs those steps overnight. A human manages the relationship. CRM hygiene: Nobody cleans data because nobody has time to clean data. An agent does it every week, logs every change, flags what needs a human eye. It just runs. Content research: The agent monitors client industries, finds angles, drafts in their voice, and queues posts for review. The team edits. Nobody starts from a blank page. Campaign reporting: Daily performance summaries, CPL alerts, client-ready reports delivered before anyone asks. The work happens whether or not someone remembers to pull it. The pattern across all five: the agent owns the execution loop, the human owns the judgment. That's where the real leverage is. Not in replacing your team - in clearing the work off their plate that was never a good use of their time to begin with. The teams that figure out which five workflows should just happen automatically, and actually build that, will be running circles around everyone still doing it manually by the end of the year.

If you’ve ever wished the browser could just do the repetitive work for you, Composite is here to make that a reality. What is Composite? + Composite is an AI agent that lives inside your existing browser and automates tedious web tasks — from clicks, form fills, navigation, to chaining workflows — all through natural language. + You simply tell it what you want done (“Send the weekly sales recap to the team”, “Update LinkedIn prospects into CRM”, etc.), and it executes the steps behind the scenes. ✅ Key Features & Differentiators + Feature Why It Matters Natural-language tasking You don’t need to script or wire APIs — just describe the task in plain English. + Real-time browser actions The agent works in your live browser session — you can see it scroll, click, type — and step in if needed. + Local-first / privacy-friendly Everything runs on-device — your credentials, DOM data, or private content are not sent to remote servers. + Low latency Since actions are local, there’s minimal lag. You can reliably automate even while screen-sharing. + Workflow chaining Because it drives the real UI of websites, you can combine steps across platforms (e.g. LinkedIn → CRM → Slack) seamlessly. + Minimal setup friction No API keys, no reauthentication hoops — it piggybacks on your existing browser session. 🎯 Benefits You’ll Feel Immediately + Save time: Offload repetitive tasks (data entry, updates, moves between systems) so you can focus on high-value work. + Reduce errors & drift: Automations follow exact steps consistently, reducing human mistakes from manual copy-pasting. + Faster onboarding & scaling: Because it needs little setup, teams can adopt it quickly without heavy IT or integration overhead. + Privacy & security comfort: The local-first design alleviates many concerns around sending sensitive data into cloud agents. + Flexibility & control: You retain visibility and the ability to override what the agent does in real time. 💡 Use Cases That Shine + CRM / sales teams: Auto-log LinkedIn leads into pipelines, send follow-ups, pull metrics + Recruiting / HR: Move candidate data between job boards, ATS systems, emails + Operations & admin: Sync dashboards, generate status reports, coordinate between tools + Marketing: Automate content updates, campaign dashboards, cross-platform publishing 🔗 Check it out at https://lnkd.in/eG-qCMwT #Productivity #AI #Automation #BrowserAgent #Composite #Tech