AI Tools For Communication

Agent memory has quickly become one of the most discussed topics in AI. As more teams start building real agent systems, one limitation keeps showing up: agents don’t remember much. Most agents today are essentially stateless. They can reason through tasks, call tools, and generate impressive responses, but once the session ends, the system forgets everything. And the conversation often gets simplified into two layers: 𝟏) 𝐒𝐡𝐨𝐫𝐭-𝐭𝐞𝐫𝐦 𝐦𝐞𝐦𝐨𝐫𝐲 = 𝐭𝐡𝐞 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐰𝐢𝐧𝐝𝐨𝐰 This is where agents keep conversation history, reasoning steps, and recent tool outputs.  But context windows are temporary. 𝟐) 𝐓𝐡𝐞𝐧 𝐭𝐡𝐞𝐫𝐞’𝐬 𝐥𝐨𝐧𝐠-𝐭𝐞𝐫𝐦 𝐦𝐞𝐦𝐨𝐫𝐲 This is where agents remember things across sessions: - user preferences - past interactions - knowledge collected over time - intermediate results from previous tasks And once you start thinking about long-term memory, the problem quickly shifts. This is really a data infrastructure problem. In many cases, long-term agent memory ends up living in the data layer. Which is why databases are starting to play a bigger role in modern AI systems. For example, 𝐌𝐨𝐧𝐠𝐨𝐃𝐁 has been building more capabilities around this idea. By integrating vector search directly into the database, application data and embeddings can live in the same system instead of being split across multiple tools. That makes it easier to store agent memory, retrieve relevant context with vector search, and keep embeddings synchronized with the underlying data. For teams building AI systems, this kind of architecture reduces a lot of the complexity around memory. If you're exploring this space, MongoDB’s Learning Hub has some useful courses and hands-on labs worth checking out https://lnkd.in/gazxytWP As agents start running longer workflows, memory quickly becomes part of the system architecture. Designing how that memory is stored, retrieved, and updated may turn out to be one of the most important pieces of agent design. #aiagents #agenticai #machinelearning #data #database

The anatomy of a sales call has changed dramatically. Last week, I shadowed some of HubSpot’s top reps and what struck me was how differently the best sellers work today. They’re using AI at every stage: before, during, and after the call. And the results are real. The brain: before the call. AI does the heavy research — scanning 10Ks, news, emails, and past calls to surface the insights that matter most. Tools like Breeze Assistant can prep a full company overview in seconds. According to our State of Sales Report, 74% of sellers say buyers are showing up to calls more informed than ever before. Salespeople need to be just as ready. The heart: during the call. AI notetakers capture everything: next steps, budget mentions, open questions, so reps can focus on listening, not typing or scribbling notes on the side.  Also, AI assistants surface the right case study or testimonial in real time, making every answer sharper and every example more relevant. That means as a sales rep you are more engaged and relevant. The muscle: after the call. AI follows through fast. It drafts personalized follow-up emails in your own voice, outlines next steps, and flags what needs attention. More time with customers and less time writing emails. The result: sellers who prepare better, connect deeper, and close faster. The anatomy of a great sales call used to be manual effort and hustle. Now, it’s human connection powered by intelligence.

“Stop calling everything an agent” Folks are slapping 'agent' on anything that touches AI. It’s confusing. I jumped on Peter Yang’s podcast to unpack why that’s misguided, and why the middle ground (agentic workflows) is where real ROI lives. Workflows = determinism and reliability Agents = judgment and flexibility Stitch them together and you get the safest, most powerful form of AI orchestration. Give your agent just enough tools and context to do one job exceptionally well, and orchestrate the rest with workflows. Two examples of this I’m using personally: 𝗘𝘅𝗲𝗰𝗖𝗼𝗻𝗻𝗲𝗰𝘁 (Workflow / Determinism)  👉 A teammate submits an Interfaces form to request exec engagement, the AI drafts an on-brand message, posts to Slack, and tracks it in Tables. This one runs hundreds of times a month. Zero chaos, total clarity 𝗜𝗻𝗯𝗼𝘅 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁 (Agent / Inference) 👉 When a new email arrives, the agent reads it, checks HubSpot, uses reasoning to categorize it, and sorts it in Slack. It flags customers, intelligently routes the right things to my EA Cortney, and clears all of the noise. It reasons like a human assistant, saving us hours each week with full transparency logs Cortney’s Inbox Management agent is actually available as a template, you can steal it here: https://lnkd.in/gR8UjTCN Full episode coming soon. Thanks for having me, Peter.

AI is rapidly moving from passive text generators to active decision-makers. To understand where things are headed, it’s important to trace the stages of this evolution. 1. 𝗟𝗟𝗠𝘀: 𝗧𝗵𝗲 𝗘𝗿𝗮 𝗼𝗳 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗙𝗹𝘂𝗲𝗻𝗰𝘆 Large Language Models (LLMs) like GPT-3 and GPT-4 excel at generating human-like text by predicting the next word in a sequence. They can produce coherent and contextually appropriate responses—but their capabilities end there. They don’t retain memory, they don’t take actions, and they don’t understand goals. They are reactive, not proactive. 2. 𝗥𝗔𝗚: 𝗧𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗖𝗼𝗻𝘁𝗲𝘅𝘁-𝗔𝘄𝗮𝗿𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Retrieval-Augmented Generation (RAG) brought a major upgrade by integrating LLMs with external knowledge sources like vector databases or document stores. Now the model could retrieve relevant context and generate more accurate and personalized responses based on that information. This stage introduced the idea of 𝗱𝘆𝗻𝗮𝗺𝗶𝗰 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗮𝗰𝗰𝗲𝘀𝘀, but still required orchestration. The system didn’t plan or act—it responded with more relevance. 3. 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜: 𝗧𝗼𝘄𝗮𝗿𝗱 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 Agentic AI is a fundamentally different paradigm. Here, systems are built to perceive, reason, and act toward goals—often without constant human prompting. An Agentic system includes: • 𝗠𝗲𝗺𝗼𝗿𝘆: to retain and recall information over time. • 𝗣𝗹𝗮𝗻𝗻𝗶𝗻𝗴: to decide what actions to take and in what order. • 𝗧𝗼𝗼𝗹 𝗨𝘀𝗲: to interact with APIs, databases, code, or software systems. • 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝘆: to loop through perception, decision, and action—iteratively improving performance.    Instead of a single model generating content, we now orchestrate 𝗺𝘂𝗹𝘁𝗶𝗽𝗹𝗲 𝗮𝗴𝗲𝗻𝘁𝘀, each responsible for specific tasks, coordinated by a central controller or planner. This is the architecture behind emerging use cases like autonomous coding assistants, intelligent workflow bots, and AI co-pilots that can operate entire systems. 𝗧𝗵𝗲 𝗦𝗵𝗶𝗳𝘁 𝗶𝗻 𝗧𝗵𝗶𝗻𝗸𝗶𝗻𝗴 We’re no longer designing prompts. We’re designing 𝗺𝗼𝗱𝘂𝗹𝗮𝗿, 𝗴𝗼𝗮𝗹-𝗱𝗿𝗶𝘃𝗲𝗻 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 capable of interacting with the real world. This evolution—LLM → RAG → Agentic AI—marks the transition from 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 to 𝗴𝗼𝗮𝗹-𝗱𝗿𝗶𝘃𝗲𝗻 𝗶𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲.

🔮 Design Patterns For AI Interfaces (https://lnkd.in/dyyMKuU9), a practical overview with emerging AI UI patterns, layout considerations and real-life examples — along with interaction patterns and limitations. Neatly put together by Sharang Sharma. One of the major shifts is the move away from traditional “chat-alike” AI interfaces. As Luke Wroblewski wrote, when agents can use multiple tools, call other agents and run in the background, users orchestrate AI work — there’s a lot less chatting back and forth. In fact, chatbot widgets are rarely an experience paradigm that people truly enjoy and can fall in love with. Mostly because the burden of articulating intent efficiently lies on the user. It can be done (and we’ve learned to do that), but it takes an incredible amount of time and articulation to give AI enough meaningful context for it to produce meaningful insights. As it turned out, AI is much better at generating prompt based on user’s context to then feed it into itself. So we see more task-oriented UIs, semantic spreadsheets and infinite canvases — with AI proactively asking questions with predefined options, or where AI suggests presets and templates to get started. Or where AI agents collect context autonomously, and emphasize the work, the plan, the tasks — the outcome, instead of the chat input. All of it are examples of great User-First, AI-Second experiences. Not experiences circling around AI features, but experiences that truly amplify value for users by sprinkling a bit of AI in places where it delivers real value to real users. And that’s what makes truly great products — with AI or without. ✤ Useful Design Patterns Catalogs: Shape of AI: Design Patterns, by Emily Campbell 👍 https://shapeof.ai/ AI UX Patterns, by Luke Bennis 👍 https://lnkd.in/dF9AZeKZ Design Patterns For Trust With AI, via Sarah Gold 👍 https://lnkd.in/etZ7mm2Y AI Guidebook Design Patterns, by Google https://lnkd.in/dTAHuZxh ✤ Useful resources: Usable Chat Interfaces to AI Models, by Luke Wroblewski https://lnkd.in/d-Ssb5G7 The Receding Role of AI Chat, by Luke Wroblewski https://lnkd.in/d8xcujMC Agent Management Interface Patterns, by Luke Wroblewski https://lnkd.in/dp2H9-HQ Designing for AI Engineers, by Eve Weinberg https://lnkd.in/dWHstucP #ux #ai #design

What uses more energy: brewing a cup of Keurig coffee, or running 100 ChatGPT prompts? According to ChatGPT (with its deep research tools), the answer might surprise you. It estimates that: One GPT-4o prompt (1K tokens in, 1K out) uses about 0.75 watt-hours Brewing one Keurig coffee uses roughly 75 watt-hours So… one cup of coffee ≈ 100 prompts. As someone who writes software, this hit close to home. I drink A LOT more coffee when I code. And between my computer, cooling, lighting, and caffeine—the AI may actually be the most energy-efficient part of the whole setup. Yes — I’m excluding model training here. But the more we use these models, the more that cost gets amortized. And here's the kicker: the value of a good prompt isn’t just high — it’s unbounded. Unlike a cup of coffee, the value of a prompt varies wildly depending on what you’re asking it to do. The more meaningful or complex the task, the more disproportionate the payoff. Think of it as Value-per-Watt: how much useful insight, action, or outcome you get per unit of energy. For simple tasks, it's high — but for complex or high-stakes ones, a single prompt can deliver exponential returns on a tiny energy footprint. This isn’t just about convenience — it’s about replacing high-energy, high-cost workflows with low-energy, high-leverage reasoning. For example: I asked ChatGPT to estimate the energy cost of AI inference vs. brewing coffee. In under 5 minutes, it pulled watt-hour data, inference benchmarks, and third-party sources to make the comparison clear. Hiring someone to do that? That’s hours of research, more money, and far more electricity. I’ve used it to write and debug production-ready Python code faster than it takes to brew a cup. A task that might’ve taken hours now runs on under a watt-hour of inference. When I needed to make sense of blood test results, I used it to understand different lab values and generate thoughtful, specific questions to ask my doctor. That clarity helped me use my time — and my doctor’s — far more effectively, with almost no energy cost beyond the prompt itself. I used it recently to evaluate whether I should replace my HVAC system. What could’ve taken hours of reading and multiple in-home consults turned into a clear decision path from a few prompts. The new HVAC system is far more efficient. These aren’t just time-savers — they’re energy shifters. So before someone says, “AI is expensive,” the better question is: Compared to what? Compared to doing nothing? To not asking your doctor the right question? To hiring a team of specialists every time you hit a wall? To spending hours writing the code by hand? I’m not claiming this is the final answer — this post is a prompt in itself. Fact-check it. Disagree. Add nuance. How should we be thinking about AI and energy use? Is its analysis wrong?

I tried EVERY major AI Coding tool so you don’t have to. Here’s what I learned about each one - and which one’s the best for your particular use case 👇 After an entire weekend of hands-on testing 15+ AI coding assistants, building the same real-life application (tax comparison calculator), and documenting every step - here's the comprehensive breakdown to separate the signal from the noise: 🏆 Best Overall: Cline - 100% open source and free version of Cursor + Windsurf that’s a simple VS Code extension - Truly thoughtful agentic coding with extensive tool use (terminal, computer use, websites, etc) - Wrote the best code with fewer mistakes, better self-healing, but no inline chat 🎨 Best for Non-Technical Users: Vercel V0 - Fast, Easy, intuitive UX - Strong community and templates - Component-specific editing via AI is magical ⚡Best for Quick Prototypes: Anthropic Claude 3.5 Sonnet - Fast & clean responses - Great reasoning & logic clarity - Artifact is great for prototyping, with ability to publish and share Replit: Good for full-stack cloud development, but sits in an awkward spot—too complex for beginners, too constrained for advanced users. StackBlitz Bolt.new: A standard cloud IDE with AI codegen, but nothing special. Lovable: Similar to Bolt, but unreliable AI-generated code, hard to toggle/see code. Cursor: Great Copilot alternative, but lacks extensive agentic capabilities like Cline. Codeium Windsurf: Strong agent mode but agent was sometimes lazy and incomplete. GitHub Copilot: Good for simple inline edits, but lacks full agentic workflow (though an agent mode was recently released). Aider: Terminal & keyboard only. Feels like Vim/Emacs on steroids. Too hardcore. OpenHands: Open-source and free Cognition Devin with strong agentic coding, but SaaS version is unstable. OpenAI (o3-mini-high): Good logic depth but lacks a coding canvas. Anthropic (Claude 3.5 Sonnet): Fast + clean. Artifact is great for prototypes, but can’t edit code directly inside it. Google Gemini 2: Poor experience—lazy, incomplete code. Generated separate files that I had to manually combine. DeepSeek AI R1: Strong long reasoning chains, but gets a lot of logic wrong. Tempo (YC S23): Promising PRD → Design → Code → Deploy workflow, but still in early stages. Onlook: Strong for design-first workflows but inconvenient for direct code editing. Reweb: Generates only UI components, not code with logic. My Final Recommendations: - For non-technical users: Vercel V0 is the best no-code/low-code option. - For cloud-based development: Try Bolt. - For local AI-powered coding: Cline is free and outperforms Cursor/Codeium. - For rapid prototyping: Claude 3.5 Sonnet is fast and effective. - For designers: Tempo or Onlook provide a strong UI-first workflow. Do you want to see a full write up of my AI coding experiences? Let me know if I should make a full post comparing AI Coding tools in detail by sharing this post and commenting below.

There’s a secret trap MANY people fall into when using AI to create their presentations. After years of studying what makes presentations succeed or fail, I'm noticing a concerning pattern as leaders rush to adopt AI for their high-stakes communications. In 1964, media theorist Marshall McLuhan said, "The medium is the message." His framework helps us understand what happens when a new technology enters our lives. When I applied his Tetrad of Media Effects to AI in presentations, the pattern became clear . Here's what AI is doing to your presentation process: AI gives you a 24/7 thinking partner. Need headline variations for your product launch? Want to test different story angles for your board presentation? AI accelerates all of that exploration. You're no longer building in isolation. Like the ancient oral traditions, you can shape ideas through dialogue before they're polished. It's collaborative, iterative, and fast. This transforms your role from slide creator to story architect. Your job isn't to fill slides, but to shape the logical and emotional journey your audience experiences. But there's a dangerous trade-off emerging. I've watched brilliant leaders deliver AI-generated presentations that looked perfect on paper, yet completely failed to move their audiences to action. Their messages were efficient... but empty. Here's the trap: When your presentation arrives instantly through AI, you skip the mental friction that creates genuine breakthrough thinking. The quiet walk. The reflective pause. The deep consideration of your audience's specific needs. Without realizing it, you become reactive rather than purposeful. Your thinking is outsourced rather than enhanced. The most devastating consequence? Your audience feels it immediately. They detect the generic thinking. They sense the lack of true empathy for their situation. And they don't take action. The very tool that makes you faster can undermine what makes you persuasive. The solution isn't avoiding AI. It's using it while preserving four essential human capabilities: 1. Empathy: Deeply understanding your audience's context 2. Message: Testing for clarity and resonance 3. Visuals: Creating memorable images that guide understanding 4. Delivery: Bringing it to life through authentic presence Because every presentation that moves people to action still starts with human empathy, not algorithmic efficiency.

Every fast-moving company pays a silent tax: duplicative work. The faster you move, the easier it is for teams to lose visibility. We’ve felt it at Glean too: two teams unknowingly solving the same problem. The costly part isn’t the obvious overlap (“two people made the same slide”). It’s the hidden duplication that surfaces later and quietly pulls execution apart. Two strategy docs steering the company in different directions. Two analyses reaching opposite conclusions because the teams never saw each other’s work. Two models built on different assumptions that can’t be compared. That’s why I ask Glean Assistant: “What duplicative work is happening right now that nobody has pointed out?” When I asked it today, it didn’t just flag duplication, it proposed fixes (it called it a “remediation plan”). For example, it caught conflicting messaging narratives and suggested converting certain docs to view-only, with a header linking to the source of truth to prevent future duplication. Every organization should be using AI to continuously surface, reconcile, and eliminate duplicative work. In the future, AI shouldn’t wait for a prompt. It should detect duplication before its ripple effects spread—and eventually prevent it by revealing the structural gaps in process, ownership, and communication that let it form in the first place.

You can become 10x more efficient by using AI agents. What are AI agents? Just like a mutual fund agent manages your investments, AI agents manage your workflows. You tell them what to do, and they get it done. Be it ordering a mouse on Amazon or posting a LI post on a Twitter thread. They don’t just give answers, they take action. They are like digital team members who help you automate repetitive tasks and free up your time. Some of them are even free to use. Here are five tools you can start exploring today: 1. ChatGPT (Agent Mode) - You can ask it to find a mouse under ₹2000 on Amazon and guide you through checkout. - Or tell it to sort emails and auto-draft replies. - It completes the task in real time, step by step, with your confirmation. Currently, only available to Pro/Plus/team users. 2. Lindy - Great for automating daily workflows. - Ask it to take notes in every meeting or email you every article where “ChatGPT” is mentioned. It can track web data for you and ensure you stay updated on all news in your domain. - Just describe the task, and Lindy builds the flow for you. 3. Gumloop - Similar to Lindy, but it gives you step-by-step guidance instead of building the workflow automatically. - Good for those who want more control while setting things up and have some technical knowledge. 4. Make - A powerful tool for building custom automations. - You can create flows like pulling funding announcements from Gmail into a Google Sheet and sending a Slack update. - It takes a little time to learn, but if you have used Zapier or enjoy visual builders, it’s worth trying. 5. Relevance AI - Useful for investors, analysts and research teams. - You can upload expert call transcripts and extract key insights, summarise news around portfolio companies, or compare pitch decks based on metrics. - With a bit of upfront setup, it saves hours of manual work in research and tracking. We all want to spend more time on meaningful work and less on admin. Until recently, that meant hiring help, but not anymore. AI agents can now take care of note-taking, summarising, follow-ups and tracking. They are fast, accurate, and always available. That said, we should always be conscious of what we allow access to. Start with one simple task this week. Let your AI agent handle the repetitive work, so you can focus on what really matters. What is one task you would delegate to an AI agent today? #ai