AI Chatbot Usage Insights

Last week, I shared how Gen AI is moving us from the age of information to the age of intelligence. Technology is changing rapidly and the way customers shop and buy is changing, too. We need to understand how the customer journey is evolving in order to drive customer connection today. That is our bread and butter at HubSpot - we’re deeply curious about customer behavior! So I want to share one important shift we’re seeing and what go-to-market teams can do to adapt. Traditionally, when a customer wants to learn more about your product or service, what have they done? They go to your website and explore. They click on different pages, filter for information that’s relevant to them, and sort through pages to find what they need. But today, even if your website is user-friendly and beautiful, all that clicking is becoming too much work. We now live in the era of ChatGPT, where customers can find exactly what they need without ever having to leave a simple chat box. Plus, they can use natural language to easily have a conversation. It's no surprise that 55% of businesses predict that by 2024, most people will turn to chatbots over search engines for answers (HubSpot Research). That’s why now, when customers land on your website, they don’t want to click, filter, and sort. They want to have an easy, 1:1, helpful conversation. That means as customers consider new products they are moving from clicks to conversations. So, what should you do? It's time to embrace bots. To get started, experiment with a marketing bot for your website. Train your bot on all of your website content and whitepapers so it can quickly answer questions about products, pricing, and case studies—specific to your customer's needs. At HubSpot, we introduced a Gen AI-powered chatbot to our website earlier this year and the results have been promising: 78% of chatters' questions have been fully answered by our bot, and these customers have higher satisfaction scores. Once you have your marketing bot in place, consider adding a support bot. The goal is to answer repetitive questions and connect customers with knowledge base content automatically. A bot will not only free up your support reps to focus on more complex problems, but it will delight your customers to get fast, personalized help. In the age of AI, customers don’t want to convert on your website, they want to converse with you. How has your GTM team experimented with chatbots? What are you learning? #ConversationalAI #HubSpot #HubSpotAI

If I were starting Data Analytics from scratch, here are 4 projects I wouldn't miss (beginner → AI-powered advanced) 1. 𝐒𝐚𝐥𝐞𝐬 𝐃𝐚𝐬𝐡𝐛𝐨𝐚𝐫𝐝 𝐰𝐢𝐭𝐡 𝐄𝐱𝐜𝐞𝐥 & 𝐏𝐨𝐰𝐞𝐫 𝐁𝐈 (𝐁𝐞𝐠𝐢𝐧𝐧𝐞𝐫) Build an interactive dashboard analyzing sales performance across regions and products. ↳ Tools: Excel, Power BI/Tableau, SQL basics ↳ Dataset: Sample Superstore or AdventureWorks ↳ 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥: https://lnkd.in/dXW4EsAq 2. 𝐂𝐮𝐬𝐭𝐨𝐦𝐞𝐫 𝐂𝐡𝐮𝐫𝐧 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬 𝐰𝐢𝐭𝐡 𝐏𝐲𝐭𝐡𝐨𝐧 (𝐈𝐧𝐭𝐞𝐫𝐦𝐞𝐝𝐢𝐚𝐭𝐞) Predict which customers are likely to leave using classification models and create actionable insights. ↳ Tools: Python (pandas, scikit-learn), Jupyter, SQL ↳ Skills: EDA, feature engineering, logistic regression ↳ 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥: https://lnkd.in/deb-cj5j 3. 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐏𝐢𝐩𝐞𝐥𝐢𝐧𝐞 (𝐀𝐝𝐯𝐚𝐧𝐜𝐞𝐝) Build an end-to-end pipeline that ingests streaming data and creates live dashboards. ↳ Tools: Apache Kafka/Airflow, PostgreSQL, dbt, Grafana ↳ Cloud: AWS/GCP for data warehousing ↳ 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥: https://lnkd.in/dVqQVphA 4. 𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐀𝐬𝐬𝐢𝐬𝐭𝐚𝐧𝐭 (𝐍𝐞𝐱𝐭-𝐆𝐞𝐧) Create a chatbot that answers business questions using natural language and generates insights automatically. ↳ Tools: LangChain, OpenAI API, Streamlit, SQL ↳ Skills: Prompt engineering, RAG implementation ↳ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dHN6TRnB With AI transforming analytics, we're no longer just creating static reports. 𝐖𝐞'𝐫𝐞 𝐬𝐞𝐞𝐢𝐧𝐠: • AutoML for automated insight discovery • Natural Language Analytics, where stakeholders ask questions in plain English • Predictive Analytics that proactively alerts before issues occur • AI-powered data quality that catches anomalies automatically 𝐌𝐲 2 𝐜𝐞𝐧𝐭𝐬: Focus on the business problems these projects solve. The future analyst isn't just someone who can query data; they're the bridge between AI capabilities and business strategy. Which project resonates with your current goals? Vishakha has the best formats for posts! 😉 ♻️ Save it for later or share it with someone who might find it helpful! 𝐏.𝐒. I share job search tips and insights on data analytics & data science in my free newsletter. Join 16,000+ readers here → https://lnkd.in/dUfe4Ac6

This Stanford study examined how six major AI companies (Anthropic, OpenAI, Google, Meta, Microsoft, and Amazon) handle user data from chatbot conversations.  Here are the main privacy concerns. 👀 All six companies use chat data for training by default, though some allow opt-out 👀 Data retention is often indefinite, with personal information stored long-term 👀 Cross-platform data merging occurs at multi-product companies (Google, Meta, Microsoft, Amazon) 👀 Children's data is handled inconsistently, with most companies not adequately protecting minors 👀 Limited transparency in privacy policies, which are complex and hard to understand and often lack crucial details about actual practices Practical Takeaways for Acceptable Use Policy and Training for nonprofits in using generative AI: ✅ Assume anything you share will be used for training - sensitive information, uploaded files, health details, biometric data, etc. ✅ Opt out when possible - proactively disable data collection for training (Meta is the one where you cannot) ✅ Information cascades through ecosystems - your inputs can lead to inferences that affect ads, recommendations, and potentially insurance or other third parties ✅ Special concern for children's data - age verification and consent protections are inconsistent Some questions to consider in acceptable use policies and to incorporate in any training. ❓ What types of sensitive information might your nonprofit staff  share with generative AI?  ❓ Does your nonprofit currently specifically identify what is considered “sensitive information” (beyond PID) and should not be shared with GenerativeAI ? Is this incorporated into training? ❓ Are you working with children, people with health conditions, or others whose data could be particularly harmful if leaked or misused? ❓ What would be the consequences if sensitive information or strategic organizational data ended up being used to train AI models? How might this affect trust, compliance, or your mission? How is this communicated in training and policy? Across the board, the Stanford research points that developers’ privacy policies lack essential information about their practices. They recommend policymakers and developers address data privacy challenges posed by LLM-powered chatbots through comprehensive federal privacy regulation, affirmative opt-in for model training, and filtering personal information from chat inputs by default. “We need to promote innovation in privacy-preserving AI, so that user privacy isn’t an afterthought." How are you advocating for privacy-preserving AI? How are you educating your staff to navigate this challenge? https://lnkd.in/g3RmbEwD

If you are building AI agents or learning about them, then you should keep these best practices in mind 👇 Building agentic systems isn’t just about chaining prompts anymore, it’s about designing robust, interpretable, and production-grade systems that interact with tools, humans, and other agents in complex environments. Here are 10 essential design principles you need to know: ➡️ Modular Architectures Separate planning, reasoning, perception, and actuation. This makes your agents more interpretable and easier to debug. Think planner-executor separation in LangGraph or CogAgent-style designs. ➡️ Tool-Use APIs via MCP or Open Function Calling Adopt the Model Context Protocol (MCP) or OpenAI’s Function Calling to interface safely with external tools. These standard interfaces provide strong typing, parameter validation, and consistent execution behavior. ➡️ Long-Term & Working Memory Memory is non-optional for non-trivial agents. Use hybrid memory stacks, vector search tools like MemGPT or Marqo for retrieval, combined with structured memory systems like LlamaIndex agents for factual consistency. ➡️ Reflection & Self-Critique Loops Implement agent self-evaluation using ReAct, Reflexion, or emerging techniques like Voyager-style curriculum refinement. Reflection improves reasoning and helps correct hallucinated chains of thought. ➡️ Planning with Hierarchies Use hierarchical planning: a high-level planner for task decomposition and a low-level executor to interact with tools. This improves reusability and modularity, especially in multi-step or multi-modal workflows. ➡️ Multi-Agent Collaboration Use protocols like AutoGen, A2A, or ChatDev to support agent-to-agent negotiation, subtask allocation, and cooperative planning. This is foundational for open-ended workflows and enterprise-scale orchestration. ➡️ Simulation + Eval Harnesses Always test in simulation. Use benchmarks like ToolBench, SWE-agent, or AgentBoard to validate agent performance before production. This minimizes surprises and surfaces regressions early. ➡️ Safety & Alignment Layers Don’t ship agents without guardrails. Use tools like Llama Guard v4, Prompt Shield, and role-based access controls. Add structured rate-limiting to prevent overuse or sensitive tool invocation. ➡️ Cost-Aware Agent Execution Implement token budgeting, step count tracking, and execution metrics. Especially in multi-agent settings, costs can grow exponentially if unbounded. ➡️ Human-in-the-Loop Orchestration Always have an escalation path. Add override triggers, fallback LLMs, or route to human-in-the-loop for edge cases and critical decision points. This protects quality and trust. PS: If you are interested to learn more about AI Agents and MCP, join the hands-on workshop, I am hosting on 31st May: https://lnkd.in/dWyiN89z If you found this insightful, share this with your network ♻️ Follow me (Aishwarya Srinivasan) for more AI insights and educational content.

Most coaches & consultants don’t have a time problem. They have a systems problem. AI doesn’t fix chaos. It scales whatever system you already have. Here are 5 AI tools that actually plug into your daily workflow (with real use-cases): 1. ChatGPT: Use it to think, not just write. Daily integration: Pre-call: Generate 5 sharp questions based on client background Post-call: Convert notes into insights and next steps Sales: Practice objection handling before discovery calls Example: “Here are my client notes → identify blind spots and suggest 3 tough questions for next session.” 2. Notion AI :Your second brain for client delivery. How to use: Create client dashboards with auto summaries Maintain SOPs for your programs Turn session transcripts into insights + next steps Example: Upload session notes → “Summarize key breakthroughs + assign action items” Your client gets clarity instantly. 3. Descript: Content creation without the headache. How to use: Edit podcasts/videos by editing text Remove filler words automatically Repurpose long-form content into shorts Example: Record a 20-min coaching insight → Cut it into 5 LinkedIn videos + 10 reels in under an hour. 4. Otter.ai.: Never miss what your client actually said. Daily integration: Record and transcribe coaching calls Highlight key patterns across sessions Build a repository of client insights over time Example: Spot recurring phrases like “I feel stuck” and use that language in your next session to go deeper. 5. Make: Where everything connects. Daily integration: Auto-send session summaries after calls Connect forms to CRM, email, and task managers Build end-to-end onboarding flows Example: Client fills a form, gets a calendar link, books a call, receives a prep doc, and you get a summary. All automated. Here’s the shift most people miss: Don’t ask, “Which AI tool should I use?” Ask, “Which part of my workflow is still manual?” That’s where AI fits. Because the goal isn’t to use more tools. It’s to free up more thinking time. What’s one task in your workflow you’d love to automate right now?

I just finished reading three recent papers that every Agentic AI builder should read. As we push toward truly autonomous, reasoning-capable agents, these papers offer essential insights, not just new techniques, but new assumptions about how agents should think, remember, and improve. 1. MEM1: Learning to Synergize Memory and Reasoning Link: https://bit.ly/4lo35qJ Trains agents to consolidate memory and reasoning into a single learned internal state, updated step-by-step via reinforcement learning. The context doesn’t grow, the model learns to retain only what matters. Constant memory use, faster inference, and superior long-horizon reasoning. MEM1-7B outperforms models twice its size by learning what to forget. 2. ToT-Critic: Not All Thoughts Are Worth Sharing Link: https://bit.ly/3TEgMWC A value function over thoughts. Instead of assuming all intermediate reasoning steps are useful, ToT-Critic scores and filters them, enabling agents to self-prune low-quality or misleading reasoning in real time. Higher accuracy, fewer steps, and compatibility with existing agents (Tree-of-Thoughts, scratchpad, CoT). A direct upgrade path for LLM agent pipelines. 3. PAM: Prompt-Centric Augmented Memory Link: https://bit.ly/3TAOZq3 Stores and retrieves full reasoning traces from past successful tasks. Injects them into new prompts via embedding-based retrieval. No fine-tuning, no growing context, just useful memories reused. Enables reasoning, reuse, and generalization with minimal engineering. Lightweight and compatible with closed models like GPT-4 and Claude. Together, these papers offer a blueprint for the next phase of agent development: - Don’t just chain thoughts; score them. - Don’t just store everything; learn what to remember. - Don’t always reason from scratch; reuse success. If you're building agents today, the shift is clear: move from linear pipelines to adaptive, memory-efficient loops. Introduce a thought-level value filter (like ToT-Critic) into your reasoning agents. Replace naive context accumulation with learned memory state (a la MEM1). Storing and retrieving good trajectories, prompt-first memory (PAM) is easier than it sounds. Agents shouldn’t just think, they should think better over time.

𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗶𝘀𝗻’𝘁 𝗷𝘂𝘀𝘁 𝗸𝗶𝗻𝗴, 𝗶𝘁’𝘀 𝘁𝗵𝗲 𝗲𝗻𝘁𝗶𝗿𝗲 𝗸𝗶𝗻𝗴𝗱𝗼𝗺. After diving deep into context engineering for agentic AI, one insight keeps hitting me:- we’ve been thinking about prompts all wrong. The real game isn’t crafting the perfect prompt anymore. It’s about curating the perfect 𝗮𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 𝗯𝘂𝗱𝗴𝗲𝘁. Think about it:- LLMs are like us, limited working memory, diminishing returns as information piles up. Every token you feed an agent depletes its ability to focus on what actually matters. 𝗧𝗵𝗲 𝗯𝗿𝗲𝗮𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵? Progressive disclosure. Instead of front-loading everything, let agents explore just-in-time. Give them lightweight identifiers, not full data dumps. Let them navigate their environment like humans do, with bookmarks, not encyclopedias. 𝗧𝗵𝗿𝗲𝗲 𝗮𝗽𝗽𝗿𝗼𝗮𝗰𝗵𝗲𝘀 𝗜’𝗺 𝗲𝘅𝗽𝗲𝗿𝗶𝗺𝗲𝗻𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵: → Compaction:- Summarize, compress, reinitiate. → Structured note-taking:- Persistent memory outside context windows. → Sub-agent architectures:- Specialists returning distilled insights. The pattern is clear:- 𝘁𝗿𝗲𝗮𝘁 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗮𝘀 𝗽𝗿𝗲𝗰𝗶𝗼𝘂𝘀 𝗮𝗻𝗱 𝗳𝗶𝗻𝗶𝘁𝗲, 𝗻𝗼𝘁 𝗶𝗻𝗳𝗶𝗻𝗶𝘁𝗲 𝗮𝗻𝗱 𝗳𝗿𝗲𝗲. What context engineering strategies are you seeing work in production? Would love to hear what’s actually moving the needle for your agents. Check out this one from Anthropic! #AI #AIAgents #LLM #ContextEngineering #PromptEngineering #MachineLearning #ArtificialIntelligence #AgenticAI #BuildingWithAI #TechInnovation #AIEngineering #DevTools #Claude #Anthropic

𝗘𝘃𝗲𝗿𝘆 𝗹𝗼𝗻𝗴-𝗿𝘂𝗻𝗻𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 𝗲𝘃𝗲𝗻𝘁𝘂𝗮𝗹𝗹𝘆 𝗿𝘂𝗻𝘀 𝗼𝘂𝘁 𝗼𝗳 𝗰𝗼𝗻𝘁𝗲𝘅𝘁. A bigger context window does not fix this, attention quality degradation almost always happens in the range of 100-200 thousand tokens. The longer a session runs, the more tool outputs, retries, and history is added. Context compressions is what we implement as AI Engineers to handle inefficiencies caused by too many tokens in the context window. There are mainly three larger groups of how we can implement this. Everything you have read about context engineering in a sense of context compression is one of these three, or a combination. 𝟭. 𝗗𝗿𝗼𝗽 𝗶𝘁 Remove low-value tokens. Some of the strategies: ▪️ Sliding window over message history: keep the most recent turns. ▪️ Hard truncation at a token limit, head or tail. ▪️ Pruning stale tool outputs once they have been acted on. ▪️ Deduplicating repeated content and re-retrieved chunks. ▪️ … ✅ Cheapest option with close to zero added latency since it is encoded in deterministic application code. ❗️ Risk of dropping high value information when it is not. 𝟮. 𝗦𝘂𝗺𝗺𝗮𝗿𝗶𝘇𝗲 𝗶𝘁 Replace a long span of context with a shorter representation that stays in the window. ▪️ Compaction: fold older turns into a running recap, on a trigger (recursively, when the history is itself too big for one pass). ▪️ Compressing a large tool result down to the few fields that matter. ▪️ Distilling a chain of reasoning into the decision it reached. ▪️ Rolling state: keep a compact running summary of facts and decisions, updated as you go. ▪️ … ✅ You keep the signal and reduce the token count. ❗️ The cost is an extra model call and the chance that the summary quietly loses a detail you will miss three steps later. 𝟯. 𝗢𝗳𝗳𝗹𝗼𝗮𝗱 𝗶𝘁 Move content out of the window into external storage, then pull it back only when it is needed. ▪️ Retrieval over a vector store or document store. ▪️ Long-term memory the agent queries on demand. ▪️ Sub-agent delegation: hand a subtask to a fresh context, keep only the result. ▪️ Reference by pointer: store the blob, pass an ID or path instead of the content. ▪️ … ✅ Nothing is lost and the window stays small. ❗️ Requires complex retrieval infrastructure and risks fetching the wrong thing back in. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝗱𝗼𝗻𝗲 𝗶𝗻 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻. Real systems rely on a mix of different strategies. E.g. 👉 Drop the obvious noise 👉 Summarize the middle history 👉 Offload anything that must survive the whole session. Pick per type of content, not once for the whole agent. The hard part? Each application benefits from different strategy combinations :) Which of the three is doing the heavy lifting in your agent today? 👇

We gave the same AI models the same 10 scenarios twice. The only thing we changed was whether they understood how our company works. The first time, they answered on their own. The second time, we connected them to our Teamwork Graph, the living record of everything AI needs to know about Atlassian to be effective: our knowledge, work, teams, communication, code, assets, and data. Same models, same questions. The only difference was connected context. With context, the models gave us 44% more accurate answers while using 48% fewer tokens, with no drop in speed. It’s a challenge we keep hearing. 69% of knowledge workers say their data and knowledge foundations aren’t optimised for AI yet. Making context accessible to AI came down to a few habits: ➡️ We connect all our tools to the Teamwork Graph and stay model-agnostic ➡️ We tag every page’s status - draft, in review, verified - so AI pulls from work we trust ➡️ We keep all our goals in one connected, centralised knowledge base so AI stays anchored to our business strategy and priorities instead of guessing based on chat volume⁠ Connected context is the difference between AI that guesses and AI that knows what to do. ⭐

One of my clients was losing deals because of his own memory. He does 90 minute discovery calls. In person. Face to face. No Zoom. No transcript. He's locked in. Taking notes. Asking great questions. Then he gets back to his desk and realizes he can't remember half of what they said. Worse. He'd write down his interpretation of their words instead of their actual words. "They're concerned about timeline" instead of "We have to be live by March 1st or we lose the budget." Those details matter. They're the difference between a generic follow-up and one that makes them think "this guy actually listened." So we built him a system. Step 1: Record everything. He wears an AI recorder. Asks permission at the start of every meeting. 99 out of 100 say yes. "Just to make sure I'm fully present and catch everything. I have a note taker that records our conversation. That cool?" Nobody cares. They appreciate it. (If you’re on Zoom, you’ve no excuse. Get Fathom or Otter to record your calls) Step 2: Dump the transcript into ChatGPT. He has a prompt that organizes everything into a framework: → Pain points (with their exact quotes) → Success criteria → Stakeholders mentioned → Timeline signals → Budget reality Step 3: Force it to prioritize. "Give me the top 3 deal risks and the exact actions to mitigate them." No 15-point lists. No fluff. Just the three things that will kill this deal if he ignores them. Step 4: Generate the follow-up email. Separate prompt. Uses their language. References their goals. Their timeline. Their words. Not his. Step 5: Copy the whole thing into the CRM. One paste. Deal notes done. Next steps clear. Total time: 10 minutes. Before this system, he'd spend an hour writing notes and still miss things. Now he catches stuff he didn't even process in the moment. Last week he reviewed a transcript and found a throwaway comment from the buyer about needing board approval over $50K. He didn't catch it live. Too focused on the demo. The transcript caught it. Now he knows exactly how to structure the deal. Here's the thing: Your brain is fast at pattern recognition. It's terrible at precision recall. In the moment, they say something. You translate it. Write down your own version. But the words they use are more specific than the words you remember. Record everything. Let AI do the heavy lifting. You just show up and sell. — BTW: I use 4 custom GPTs to help me save 10 hours of time in sales per week. Want to see them? Check them out here: https://lnkd.in/g6X-nWaG