Claude's Contribution to Streamlining Workflows

Claude Code can now build HubSpot workflows. Not describe them. Build them. HubSpot quietly shipped a Workflows API in beta. That means AI agents can now create workflows, not just trigger them. This is another big addition to the Claude <> HubSpot stack. And this one is big for admins, RevOps, and solution partners. Before: Claude could read your data, update records, and start workflows. But building the automation was still your Tuesday afternoon. Now: Claude Code can read your portal, spot the gap, and create the workflow through the API. You QA it in the UI. You flip the toggle. The flow: - Agent analyzes patterns and process gaps in the portal - Proposes an automation - Builds the workflow via the API - Admin QAs and turns it on - Agent tests and refines based on performance Nothing here replaces the human. The admin still decides what "good" looks like. The solution partner still owns the architecture. But the "sit down and build 14 workflows this sprint" part? That just got compressed. For HubSpot Solution Partners, this also shifts delivery economics. Clicking through the workflow builder is no longer the main cost. The value moves to strategy, QA, and ongoing governance. HubSpot keeps calling its vision the "agentic customer platform." Every release like this is another piece of that scaffolding. Claude Code can talk to HubSpot via MCP and API. Now it can build inside it too. Start working with Claude <> HubSpot today. You won't just be early. You'll be ready when HubSpot gives you more power in the future. P.S. Would you let Claude build a workflow in your production portal today, or sandbox only? #HubSpot #Claude #RevOps #API

Here’s 2-weeks of a Head of People Ops’ Claude use cases from simple to sophisticated. Level 1: Internal communication with Claude Chat (Sonnet 4.6) I launched a company-wide product training initiative and needed a Slack announcement for our #all-headlines channel. The program, Creator Quest-ions, is adventure-themed, informal, and energetic. I gave Claude the context and tone I wanted as well as the Notion doc with content for the first session. Claude drafted the announcement, made decisions about what to include vs. save for the channel itself, and linked to the project-specific Slack channel by ID so it’d render as clickable. I edited maybe two sentences. Level 2: Document redaction with Claude Cowork (Opus 4.6, extended thinking enabled) In HR, we have a lot of documents that have details with varying levels of sensitivity. If you have a PDF document and you need to remove one section (e.g., compensation expectations) before sharing it more broadly, you can have Claude Cowork redact the document with a Python script. No, you don’t need to know Python. Just describe what you want removed in plain text. No more using Preview to put black or white shape boxes over things. Level 3: Compensation analysis with Claude Cowork (Opus 4.6, extended thinking, HR plug-in) This is where Cowork gets interesting. Anthropic launched an HR plugin that’s designed for people operations — recruiting, onboarding, performance reviews, compensation analysis. It comes pre-loaded with slash commands like /offer-letter, /onboarding-plan, and /comp-analysis. You can configure it with your company’s actual benefits, equity structure, and comp philosophy so the outputs aren’t generic. I’ve been using the compensation analysis workflows alongside our existing job architecture, salary tier system, etc. to do things like calculate formulas for new sub-tiers faster (Claude can derive the quartile spread formula we use and apply it in new rows from a sheet with values only) and sanity check the data pulled from our compensation tool. Level 4: Manager updates with Claude Cowork and connected tools (Slack, GoogleDrive, Notion) We recently confirmed our outstanding performance grant awardees and I needed to individually inform managers and give them all the details along with a script and deadline to tell their direct reports. By giving Claude Cowork the GoogleSheet with the confirmed awardees and grants, the Notion SOP, and an example from last cycle, Claude could draft and send all the necessary DMs via Slack. It’s like a new version of a mail merge. Now since this is sensitive info, I did do additional double checking to confirm Claude had the right Slack IDs, manager matches, etc. I also sent a test first. Hopefully this helps make some applications of AI more concrete and exciting.

Claude is quietly changing how analysts work - from manual steps to intelligent workflows. Data analysis is no longer just about writing queries. It’s about building systems that think, plan, and execute with you. This breakdown shows what that actually looks like in practice. Instead of jumping straight into queries: → Claude plans the entire analysis before execution Instead of struggling with messy data: → It auto-loads CSV, Excel, JSON, and understands schema instantly Instead of switching tools constantly: → It connects directly to databases, sheets, and warehouses Instead of writing everything from scratch: → It runs Python, SQL, and bash in real time and iterates with you Instead of static reports: → It generates charts, dashboards, and full reports automatically And where it gets really powerful: → Tracks your transformations and lets you rewind anytime → Saves workflows so you can rerun full analyses in one command → Uses specialized sub-agents for SQL, stats, and visualization → Converts one prompt into complete outputs (Excel, PPT, PDF, docs) This is the shift happening: From analyst → to AI-powered decision engine The people who adapt to this workflow will move faster, test more ideas, and deliver better insights.

I attend 30+ data and AI conferences every year, and for the longest time, outreach was complete chaos. Spreadsheets everywhere, notes scattered across tools, follow-ups slipping through, and the worst part was sending generic emails that got ignored. It did not matter how many events I attended, the system just did not scale. So I rebuilt everything inside Airtable. I created a simple but structured system with conferences, sponsors, and contacts all connected in one place. Now I could actually see who I met, where, and what needed to happen next. That alone made things cleaner, but it still required a lot of manual work. The real shift happened when I connected it with Claude. Now I start my workflow in Claude. It pulls context directly from my Airtable base, understands the sponsors I am targeting, the events I am attending, and the history of interactions. Then it goes out, does research on each company, looks at what they have recently announced, and brings back insights that actually matter. From there, it writes everything back into Airtable. New sponsor ideas get added. Outreach emails are drafted with real context. Follow-ups are created automatically based on status. Everything stays structured, tracked, and easy to act on. The biggest change for me is I am no longer jumping between tools or starting from scratch every time. I think in Claude, execute in Airtable, and then go back to Claude to refine messaging or strategy. That back and forth is what makes this powerful. This is how I now manage conference partnerships at scale. Not by adding more tools, but by connecting the right ones in a way that actually works. Learn more about it here – https://lnkd.in/gFCDbR7T #airtablepartner #data #ai #claude #theravitshow

I just taught Claude to directly query my CRM. Complex workflows became single prompts: A month ago my network kept talking about something called Model Context Protocol (MCP). Initially abstract, I understood it simply as: MCP lets AI models directly access your existing tools and databases. Think of it like the invention of USB: → Before USB: Multiple incompatible ports → After USB: One universal connection → Before MCP: Custom data integrations → After MCP: Universal plug-and-play AI connectivity Then a week ago I got an email from my personal CRM provider Clay that they had support for MCP. Historically, CRMs have acted as passive databases, requiring manual interactions to deliver insights. Here is what I used to do when I wanted to know who within my network had changed roles recently: OLD PROCESS: → Log into Clay CRM, export contacts as CSV → Clean and format data in a spreadsheet → Copy-paste formatted data into Claude → Manually instruct Claude to analyze job changes → Copy Claude’s insights back to Clay → Update contact records individually → Manually set follow-up tasks for each contact NEW PROCESS: → Simply instruct Claude: “Identify contacts in my network who recently changed jobs, showing their old and new positions and when I last interacted with them.” → Claude directly accesses Clay via MCP → Finds contacts who’ve recently changed jobs → Instantly provides a detailed, actionable list The results aren't perfect, but they turned a previously tedious process into an effortless query. The technical setup took 5 minutes: → Generated a Clay API key → Connected through Clay’s Smithery page → Installed Node.js locally → Ran one terminal command → Restarted Claude, confirming integration MCP's power comes from three shifts: → From isolated silos to interconnected intelligence → From sequential tasks to seamless orchestration → From human middleware to direct and automated interactions While it is early days, I believe we are scratching the surface with what is possible. I'm now working with several of our portfolio companies to explore how we can do deeper AI integrations. In an age where everyone has access to similar AI tools, the real competitive advantage isn't the tool itself. It's how deeply you embed it into your workflows.

Last week I asked PMs whether they use Claude Code. A third of them didn't know where to start. And when I read the comments, even PMs who do use it are overwhelmed by how fast everything moves and unsure which workflows are worth investing in. Every week there's a new list of "must-use" agents and skill packs, and the pressure to overhaul your setup is real. But most PMs are still trying to figure out what fits their actual work and what's just noise. Pulling signals from bugs, feature requests, competitor moves, VP asks, user research. Stitching it together. Formatting it. Making it presentable. The actual product thinking gets whatever time is left. These are the kind of problems that skills in Claude Code are ideal to solve. A skill in Claude Code is a workflow you describe once and run with one command. You don't need a hundred. You need three or four that solve your specific week. Three of my favorite that anyone can use to learn about /skills: /research Pull a weekly AI research brief every Monday. Three developments, one quote, one action item. Used to take 45 minutes of tab-switching. Now it runs while you make coffee. /meeting-prep (name) If you connect searches Gmail for shared docs, open action items, and recent threads. Returns the three things to cover in your next meeting. Run it 10 minutes before every 1:1. /prd-review This one is fun. Run a PRD through three parallel agents, each reading from a different stakeholder persona (eng manager, director, PM peer). Three independent gap lists before the doc goes to anyone. Pro tip: ask your boss and your eng manager to help you build a persona that resembles them, then your PRD reviews can be much more effective. Building skills in Claude Code is very easy. Each one started as a conversation where I described the problem, refined the output until it matched what I wanted, and saved it. And the best part is that they can build on each other. You can have, for example, the research skill feed into meeting prep. One workflow becomes the input to the next. The data gathering, sorting, wrangling and eternal scrolling work still happens. It just doesn't have to eat your calendar anymore. I wrote a step-by-step guide on building /skills from scratch this week on Product SideQuest and I believe everyone, especially Product Managers, should be building skills and delegate the 'busy' work to agents. #ProductManagement #AI

You are using one Claude mode There are actually THREE. Most people use Claude like a chatbot. That's leaving 80% of its power on the table. Claude has three distinct modes: Chat, Cowork, and Code. Each is built for a different type of work. Using the wrong one is like using a screwdriver to hammer a nail. It works. But poorly. Here's how they differ, and how I use each one daily: CLAUDE CHAT → Think ↳ The conversational interface. ↳ Best for brainstorming, exploring frameworks, drafting content, researching a topic from scratch, processing half-formed thoughts into something structured. ↳ Not for: Tasks that need to work with your actual files or produce finished deliverables directly. ↳ How I use it: Every new idea starts here. When I'm building a framework or exploring a content angle, Chat is where I go. My thinking partner. CLAUDE COWORK → Execute ↳ You point it at a folder on your computer, describe the outcome, and it plans and executes. ↳ Best for: Working directly with your local files. Organizing documents, synthesizing research across multiple sources, creating formatted reports. ↳ Not for: Quick one-off questions (Cowork consumes usage allocation much faster than Chat). Not for software development. Still in research preview, so expect rough edges. ↳ How I use it: I point Cowork at my content folder: "analyze this transcript for actionable" or "create this deck using this research." It reads everything, builds a plan, delivers. No copy-pasting between apps. CLAUDE CODE → Build ↳ Originally built for developers. Its agentic architecture makes it capable of far more. ↳ Best for: Software development (writing, debugging, git workflows). Also: advanced agentic workflows. Running sub-agents, orchestrating multi-step research, automating content pipelines through MCP integrations. ↳ Not for: If you've never opened a terminal, this isn't your starting point. Start with Chat. Graduate to Cowork. Come to Code when you're ready for full agent-mode. ↳ How I use it: I run Claude Code in my IDE and desktop app to orchestrate agent-driven workflows. Automated research for LinkedIn posts, newsletter production, course material development. This is what I teach in my agentic AI workshops. One thing most people don't know: All three modes live inside the Claude Desktop app. One app, three modes. Download at claude.com/download. Chat is on free plans. Cowork and Code require paid plans. The mental model: ↳ Chat = Think ↳ Cowork = Execute ↳ Code = Build Start with Chat. Move to Cowork when you need real file-level work done. Graduate to Code when you're ready to build systems that work for you while you sleep. --------- I am Priyadeep Sinha and I help you go from AI Anxiety to AI Expertise one strategy at a time Every week, I share one complete AI workflow system for leaders, consultants and knowledge workers in my newsletter Work in Beta: https://lnkd.in/gPqYEzaJ

Tested new Claude for Excel - here’s my honest opinion as a CFO. So Anthropic just released Claude directly inside Excel. Which basically means financial analysis in natural language, inside the tool finance teams already live in. After Claude Code and Claude Cowork, this feels like a big step toward AI becoming infrastructure - not another app, but something embedded into daily workflows. I tested it immediately. Here’s what works (and what doesn’t). How it works: 1/ You need a Claude Pro, Max, Team, or Enterprise plan 2/ Install it from the official website 3/ Open with Control + Option + C (Mac) or Control + Alt + C (Windows) 4/ Prompt it directly inside Excel What I tested: 1/ Data cleanup I intentionally left errors in a dataset - extra spaces, misspelled transaction names, inconsistent formatting. Claude caught everything. Fast, accurate, honestly impressive for cleanup and structuring messy data. This alone can save hours every week. 2/ Basic financial modeling It built a reasonable model structure with correct formulas. Good starting point. But not very flexible yet - harder to adjust scenarios or evolve the model after it’s generated. 3/ Advanced modeling & forecasting I gave it last year’s financials and asked for a 3-statement model with a 5-year forecast. It produced separate tabs for: – Income Statement – Balance Sheet – Cash Flow At first glance, it looked solid. But when you go deeper: – missing data assumptions – some hard-coded values – logical inconsistencies that break the model And in finance, 99% correct is still wrong. My takeaway: This is incredibly powerful - and also risky. If you understand finance, this makes you faster. If you don’t, it can give you false confidence. AI in Excel is amazing for: ✅ cleanup ✅ first drafts ✅ speeding up analysis But not for blind trust. AI can build the model. You still need to understand whether the model makes sense. Curious if anyone else tested it already - where did it help you most?

If you use Claude for sales, you’ve hit this wall: it suddenly forgets key details mid-project. This isn't you. It’s “context compaction.” As chats near Claude’s memory limit, it auto-summarizes and loses the crucial details from your meeting transcripts and early decisions. You need a system. Here’s the 4-layer architecture that works: LAYER 1: CLAUDE PROJECTS Your permanent base. Store your proposal templates, product specs, and methodology here. Every new chat starts with this context pre-loaded. Stop pasting the same docs repeatedly. LAYER 2: THE HANDOFF DOCUMENT Your session bridge. Before the chat gets too long, command Claude to create a structured summary of the strategic state: key client insights, decisions made, and exact next steps. Copy this into a fresh chat to continue seamlessly. This preserves ~95% of your progress. LAYER 3: NOTION MCP (The Game-Changer) Your external brain. Connect Claude to Notion in 20 mins. Now, Claude can read/write directly to your Notion databases. After a call: Claude saves extracted insights straight to a structured Notion page. Days later in a new chat: “Pull all notes for Acme Corp from Notion and draft the exec summary.” This creates persistent memory outside Claude’s limit. LAYER 4: CONVERSATION DESIGN Work in focused, single-task chats (“analyze transcript” then “draft proposal section”). Build incrementally and save parts to Notion. This prevents huge, slow sessions. THE 4-WEEK PATH: Week 1: Master Projects & Handoffs. Week 2: Integrate Notion MCP. Week 3: Redesign workflow into task-scoped chats. Week 4: Automate. Use Notion as your single source of truth. This shifts Claude from a forgetful chat tool into a proactive sales intelligence system. Insights from every call compound. The edge in sales is now conversation quality powered by managed context. Link to full article laying down step by step approach is in the comments. #SalesTech #AI #Claude #Notion #Productivity #B2BSales #ArtificialIntelligence

This just changed how we create presentations forever. 🤯 Claude and Gamma just integrated, and it's the first time AI thinking actually flows directly into finished decks without breaking your workflow. Before: brainstorm in Claude, copy notes to another tool, rebuild or regenerate a deck, go back to Claude to refine thinking, repeat. Now: Claude's Gamma Connector generates and updates Gamma presentations inside Claude. Your thinking evolves with your deck in real-time. This removes the biggest friction in AI workflows today: losing momentum between thinking and creating. Here's what actually changed: You can now turn Claude brainstorming into a live Gamma presentation without context switching. Keep refining both thinking and the deck in the same flow. Your deck evolves with your ideas, not after them. But the deeper unlock is connector flexibility. Gamma doesn't just connect to Claude. It connects to what Claude already knows through your other connectors. - Gmail + Gamma: presentations directly from emails - HubSpot + Gamma: pipeline summaries generated automatically - GitHub + Gamma: turn docs, strategies, or notes into structured presentations - Notion + Gamma: client pitches automatically Claude pulls the data. Gamma turns it into something you can share. No manual exporting, copy-pasting, or reformatting. Three workflow changes that matter: 1. No context switching – Your deck stays aligned with your thinking because they happen in the same place. 2. No rebuilding decks – Iterate without restarting from scratch each time you refine an idea. 3. No manual reporting – Pull real data from Gmail, Slack, or Notion and let Gamma structure it automatically. This is what "agentic era" actually looks like. Not AI that generates static outputs. AI that keeps structure, visuals, and narrative aligned as ideas evolve. The system that keeps up with your thinking wins. Claude handles reasoning. Gamma handles presentation. You stay in flow. Try it here: https://lnkd.in/gC2XA9YK