GenAI Implementation and Impact

"Despite $30–40 billion in enterprise investment into GenAI, this report uncovers a surprising result in that 95% of organizations are getting zero return. The outcomes are so starkly divided across both buyers (enterprises, mid-market, SMBs) and builders (startups, vendors, consultancies) that we call it the GenAI Divide. Just 5% of integrated AI pilots are extracting millions in value, while the vast majority remain stuck with no measurable P&L impact. This divide does not seem to be driven by model quality or regulation, but seems to be determined by approach. Tools like ChatGPT and Copilot are widely adopted. Over 80 percent of organizations have explored or piloted them, and nearly 40 percent report deployment. But these tools primarily enhance individual productivity, not P&L performance. Meanwhile, enterprise grade systems, custom or vendor-sold, are being quietly rejected. Sixty percent of organizations evaluated such tools, but only 20 percent reached pilot stage and just 5 percent reached production. Most fail due to brittle workflows, lack of contextual learning, and misalignment with day-to-day operations. From our interviews, surveys, and analysis of 300 public implementations, four patterns emerged that define the GenAI Divide: • Limited disruption: Only 2 of 8 major sectors show meaningful structural change • Enterprise paradox: Big firms lead in pilot volume but lag in scale-up • Investment bias: Budgets favor visible, top-line functions over high-ROI back office • Implementation advantage: External partnerships see twice the success rate of internal builds The core barrier to scaling is not infrastructure, regulation, or talent. It is learning. Most GenAI systems do not retain feedback, adapt to context, or improve over time."

The Alan Turing Institute 𝗮𝗻𝗱 the LEGO Group 𝗱𝗿𝗼𝗽𝗽𝗲𝗱 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝗰𝗵𝗶𝗹𝗱-𝗰𝗲𝗻𝘁𝗿𝗶𝗰 𝗔𝗜 𝘀𝘁𝘂𝗱𝘆! ⬇️ (𝘈 𝘮𝘶𝘴𝘵-𝘳𝘦𝘢𝘥 — 𝘦𝘴𝘱𝘦𝘤𝘪𝘢𝘭𝘭𝘺 𝘪𝘧 𝘺𝘰𝘶 𝘩𝘢𝘷𝘦 𝘤𝘩𝘪𝘭𝘥𝘳𝘦𝘯.) While most AI debates and studies focus on models, chips, and jobs — this one zooms in on something far more personal: 𝗪𝗵𝗮𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝘀 𝘄𝗵𝗲𝗻 𝗰𝗵𝗶𝗹𝗱𝗿𝗲𝗻 𝗴𝗿𝗼𝘄 𝘂𝗽 𝘄𝗶𝘁𝗵 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜? They surveyed 1,700+ kids, parents, and teachers across the UK — and what they found is both powerful and concerning. 𝗛𝗲𝗿𝗲 𝗮𝗿𝗲 9 𝘁𝗵𝗶𝗻𝗴𝘀 𝘁𝗵𝗮𝘁 𝘀𝘁𝗼𝗼𝗱 𝗼𝘂𝘁 𝘁𝗼 𝗺𝗲 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝗿𝗲𝗽𝗼𝗿𝘁: ⬇️ 1. 1 𝗶𝗻 4 𝗸𝗶𝗱𝘀 (8–12 𝘆𝗿𝘀) 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝘂𝘀𝗲 𝗚𝗲𝗻𝗔𝗜 — 𝗺𝗼𝘀𝘁 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝘀𝗮𝗳𝗲𝗴𝘂𝗮𝗿𝗱𝘀 → ChatGPT, Gemini, and even MyAI on Snapchat are now part of daily digital play. 2. 𝗔𝗜 𝗶𝘀 𝗵𝗲𝗹𝗽𝗶𝗻𝗴 𝗸𝗶𝗱𝘀 𝗲𝘅𝗽𝗿𝗲𝘀𝘀 𝘁𝗵𝗲𝗺𝘀𝗲𝗹𝘃𝗲𝘀 — 𝗲𝘀𝗽𝗲𝗰𝗶𝗮𝗹𝗹𝘆 𝘁𝗵𝗼𝘀𝗲 𝘄𝗶𝘁𝗵 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗻𝗲𝗲𝗱𝘀 → 78% of neurodiverse kids use ChatGPT to communicate ideas they struggle to express otherwise. 3. 𝗖𝗿𝗲𝗮𝘁𝗶𝘃𝗶𝘁𝘆 𝗶𝘀 𝘀𝗵𝗶𝗳𝘁𝗶𝗻𝗴 — 𝗯𝘂𝘁 𝗻𝗼𝘁 𝗿𝗲𝗽𝗹𝗮𝗰𝗶𝗻𝗴 → Kids still prefer offline tools (arts, crafts, games), even when they enjoy AI-assisted play. Digital is not (yet) the default. 4. 𝗔𝗜 𝗮𝗰𝗰𝗲𝘀𝘀 𝗶𝘀 𝗵𝗶𝗴𝗵𝗹𝘆 𝘂𝗻𝗲𝗾𝘂𝗮𝗹 → 52% of private school students use GenAI, compared to only 18% in public schools. The next digital divide is already here. 5. 𝗖𝗵𝗶𝗹𝗱𝗿𝗲𝗻 𝗮𝗿𝗲 𝘄𝗼𝗿𝗿𝗶𝗲𝗱 𝗮𝗯𝗼𝘂𝘁 𝗔𝗜’𝘀 𝗲𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁𝗮𝗹 𝗶𝗺𝗽𝗮𝗰𝘁 → Some kids refused to use GenAI after learning about water and energy costs. Let that sink in. 6. 𝗣𝗮𝗿𝗲𝗻𝘁𝘀 𝗮𝗿𝗲 𝗼𝗽𝘁𝗶𝗺𝗶𝘀𝘁𝗶𝗰 — 𝗯𝘂𝘁 𝗱𝗲𝗲𝗽𝗹𝘆 𝘄𝗼𝗿𝗿𝗶𝗲𝗱 → 76% support AI use, but 82% are scared of inappropriate content and misinformation. Only 41% fear cheating. 7. 𝗧𝗲𝗮𝗰𝗵𝗲𝗿𝘀 𝗮𝗿𝗲 𝘂𝘀𝗶𝗻𝗴 𝗔𝗜 — 𝗮𝗻𝗱 𝗹𝗼𝘃𝗶𝗻𝗴 𝗶𝘁 → 85% say GenAI boosts their productivity, 88% feel confident using it. They’re ahead of the curve. 8. 𝗖𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗶𝘀 𝘂𝗻𝗱𝗲𝗿 𝘁𝗵𝗿𝗲𝗮𝘁 → 76% of parents and 72% of teachers fear kids are becoming too trusting of GenAI outputs. 9. 𝗕𝗶𝗮𝘀 𝗮𝗻𝗱 𝗶𝗱𝗲𝗻𝘁𝗶𝘁𝘆 𝗿𝗲𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗶𝘀 𝘀𝘁𝗶𝗹𝗹 𝗮 𝗯𝗹𝗶𝗻𝗱𝘀𝗽𝗼𝘁 → Children of color felt less seen and less motivated to use tools that didn’t reflect them. Representation matters. The next generation isn’t just using AI. They’re being shaped by it. That’s why we need a more focused, intentional approach: Teaching them not just how to use these tools — but how to question them. To navigate the benefits, the risks, and the blindspots. 𝗪𝗮𝗻𝘁 𝗺𝗼𝗿𝗲 𝗯𝗿𝗲𝗮𝗸𝗱𝗼𝘄𝗻𝘀 𝗹𝗶𝗸𝗲 𝘁𝗵𝗶𝘀? Subscribe to Human in the Loop — my new weekly deep dive on AI agents, real-world tools, and strategic insights: https://lnkd.in/dbf74Y9E

Hey Salespeople: Here is a collection of current use cases for AI in sales & CS: ** GenAI in Sales ** --> Draft messaging for personalized email outreach --> Generate post-call summaries with action items; draft call follow ups --> Provide real-time, in-call guidance (case studies; objection handling; technical answers; competitive response) --> Auto-populate and clean up CRM --> Generate & update competitive battlecards --> Draft RFP responses --> Draft proposals & contracts --> Accelerate legal review & red-lining (incl. risk identification) --> Research accounts --> Research market trends --> Generate engagement triggers (press releases; job postings; industry news; social listening; etc.) --> Conduct role-play --> Enable continuous, customized learning --> Generate customized sales collateral --> Conduct win-loss analysis --> Automate outbound prospecting -->Automate inbound response --> Run product demos --> Coordinate & schedule meetings --> Handle initial customer inquiries (chatbot; voice-bot / avatar) --> Generate questions for deal reviews --> Draft account plans ** Predictive AI in Sales ** --> Score leads & contacts --> Score /segment accounts (new logo) --> Automate cross-sell & upsell recommendations --> Optimize pricing & discounting --> Surface deal gaps / identify at-risk prospects --> Optimize sales engagement cadences (touch type; frequency) --> Optimize territory building (account assignment) --> Streamline forecasting (incl. opportunity probabilities; stage; close date) --> Analyze AE performance --> Optimize sales process --> Optimize resource allocation (incl. capacity planning) --> Automate lead assignment --> A/B test sales messaging --> Priortize sales activities ** GenAI in CS ** --> Analyze customer sentiment --> Provide customer support (chatbot; voice-bot / avatar; email-bot) --> Draft proactive success messaging --> Update & expand knowledge base (incl. tutorials, guides, FAQs, etc.) --> Provide multilingual support --> Analyze customer feedback to inform product development, support, and success strategies --> Summarize customer meetings; draft follow-ups --> Develop customer training content and orchestrate customized training --> Provide real-time, in-call guidance to CSMs and support agents --> Create, distribute, and analyze customer surveys --> Update CRM with customer insights --> Generate personalized onboarding --> Automate customer success touch-points --> Generate customer QBR presentations --> Summarize lengthy or complex support tickets --> Create customer success plans --> Generate interactive troubleshooting guides --> Automate renewal reminders --> Analyze and action CSAT & NPS ** Predictive AI in CS ** --> Predict churn; score customer health; detect usage anomalies, decision maker turnover, etc. --> Analyze CSM and support agent performance --> Optimize CS and support resource allocation --> Prioritize support tickets --> Automate & optimize support ticket routing --> Monitor SLA compliance

RL isn't always the right answer! (Berkeley beat GRPO without a GPU) Same task, same base model, 10 points higher on the benchmark. The technique is called 𝗚𝗘𝗣𝗔. It came out of Berkeley in mid-2025, got accepted at ICLR 2026, and is now a first-class optimizer in DSPy. The reason it works points at something most teams get wrong about reinforcement learning on language models. Every team running agents in production is sitting on a pile of rollouts. A rollout is just one full run of your agent on a task, from the user query down to the final answer, with everything that happened in between. Most teams have thousands of these traces and no real idea what to do with them beyond eyeballing a few when something breaks. This is the part worth paying attention to. Each rollout is roughly a 5,000-token document containing reasoning steps, tool calls, compiler errors, and judge rationales. Rich, structured, and full of signal. 𝗚𝗥𝗣𝗢 compresses all of that to +1 or -1. That single bit gets back-propagated across every token in the policy. The information that told you what went wrong and where gets thrown away on the way to the gradient. This is why RL needs tens of thousands of rollouts to converge. The signal was never sparse, the optimizer made it sparse. 𝗚𝗘𝗣𝗔 reads the trace instead. A reflection LLM ingests the full rollout, diagnoses the failure, localizes it to one module in the pipeline, and rewrites that module's prompt. Same rollout, vastly more signal extracted. Weights become prompts, and opaque becomes readable. This is also why GEPA shines on multi-module workflows. Most real agents are pipelines of several modules glued together, and GEPA lets you target the exact module you want to improve instead of nudging the whole system at once. The honest framing is this. RL changes what the model knows, while GEPA changes how you ask. If your base model genuinely can't do the task, no prompt evolution will save you and you should fine-tune. But most of what teams currently route to GRPO is the second case, not the first. The model can already do it, and the prompt is the bottleneck. Reading a rollout costs less than running ten thousand more. If you want to go deeper, I've shared the paper and the DSPy implementation in the first comment. _____ Share this with your network if you found this insightful ♻️ Follow me (Akshay Pachaar) for more insights and tutorials on AI and Machine Learning!

Today Common Sense Media released their new white paper on "Generative AI in K–12 Education: Challenges and Opportunities." It takes a deep dive into the complexities of AI adoption in education and I was fortunate to share some of our experiences from AI for Education's work in schools and districts with one of the authors, Bene Cipolla . The white paper is definitely worth a read and we love the emphasis on responsible implementation, the importance of building AI literacy, and the need for clear guidelines to ensure AI enhances rather than undermines learning experiences. Key Highlights: Current State of AI in Education: • Though familiarity is increasing, there is still a lack of fundamental AI literacy • Only 5% of districts have specific generative AI policies, which reflects what we have seen in the field • Students are using AI tools, often without clear guidelines Opportunities for AI adoption: •  Student-focused: Adaptive learning, creativity enhancement, project-based learning, and collaborative support •  Teacher-focused: Lesson planning assistance, feedback on teaching, and productivity gains •  System-focused: Data interoperability, parent engagement, and communication Risks and Challenges: •  Inaccuracies and misinformation in GenAI outputs •  Bias and lack of representation in AI systems •  Privacy and data security concerns •  Potential for cheating and plagiarism •  Risk of overreliance on technology and loss of critical thinking skills What Students Want: •  Clear guidelines on AI use, not outright bans •  Recognition of both potential benefits and ethical concerns of the technology •  More education on AI's capabilities and limitations Recommendations: •  Invest in AI literacy for educators, students, and families •  Develop standardized guidelines for AI use in schools •  Adopt procurement standards for AI tools in education •  Use participatory design to include diverse voices in AI development •  Center equity in AI development and implementation •  Proceed cautiously given the experimental nature of the technology Make sure to check out the full report and let us know what you think - link in the comments! And shoutout to all of our EDSAFE AI Alliance and TeachAI steering committee members featured in the white paper. #aieducation #GenAI #ailiteracy #responsibleAI

One of the most important applications of GenAI is in foresight. A new report from Paulo Carvalho at IF Insight & Foresight on "How Generative AI Will Transform Strategic Foresight" provides wide-ranging perspectives on the possibilities. Here are some of the most interesting action-oriented frames I found in the report. 🔍 Real-Time Environmental Scanning: Use GenAI to conduct continuous scanning of emerging trends, weak signals, and disruptions across diverse sources. This real-time, dynamic approach allows organizations to stay agile, proactively adjusting strategies as new insights unfold. 🌐 Immersive Scenario Simulations: Utilize GenAI to create interactive VR/AR scenarios that bring potential futures to life. These simulations engage stakeholders deeply, helping them visualize and emotionally connect with complex strategic choices, fostering stronger alignment with future goals. 🔄 Adaptive Scenario Planning: Move from static to adaptive planning by integrating live data into foresight models. Continuous updates based on geopolitical, economic, and technological shifts ensure that scenarios remain relevant and actionable over time. 💬 Enhanced Strategic Conversations: Use GenAI-powered virtual agents to facilitate dynamic "what-if" conversations, helping stakeholders explore a range of possible outcomes. This deepens strategic insights and encourages a proactive approach to complex decision-making. ⚙️ Modeling Complexity and Emergent Behaviors: Use GenAI to simulate complex systems and emergent behaviors, enabling organizations to anticipate interconnected, cascading effects. This prepares them for resilience in the face of unpredictable challenges and non-linear changes. 📊 Multimodal Data Integration for Richer Insights: Leverage GenAI’s capacity to analyze diverse data types (e.g., text, images, audio, video) to gain a nuanced, comprehensive view of trends and risks. This multimodal approach captures intricate patterns that single-source analysis might miss. 🌍 Embrace Multiple Perspectives and Plurality: Design foresight processes that incorporate a wide array of perspectives, blending cross-disciplinary and cultural insights. This inclusive approach creates more robust, innovative scenarios that account for diverse worldviews and challenges assumptions. 🤝 Facilitate Participatory and Co-Creative Approaches: Use GenAI to build interactive platforms that invite diverse stakeholders to co-create and refine scenarios. Real-time collaboration enhances the relevance and inclusivity of strategic models, making them more reflective of shared goals and values. I'll be sharing some of my thoughts on this very important topic in the next little while.

Why 95% of GenAI pilots are failing and what leaders must do differently... A recent MIT study highlights a striking reality: 95% of enterprise GenAI pilots fail to create measurable business impact. The paradox is clear...while nearly every leadership team is experimenting with AI, very few are scaling it successfully. Across industries, three recurring themes explain why many pilots stall: >> Integration gaps, not model gaps. Most pilots are built on generic tools that don’t connect deeply into enterprise workflows, leaving business value unrealized. >> No learning loop. Pilots often lack feedback systems that allow GenAI to adapt and improve over time. >> Scattered focus. Organizations spread efforts too thin across marketing or customer-facing use cases, while overlooking operational domains where ROI is clearer and adoption easier. But failure is not inevitable. Successful organizations treat GenAI less as a “lab experiment” and more as a strategic capability build. Three shifts stand out: << Anchor pilots in business priorities. Start with a high-value, well-bounded use case tied directly to P&L impact. << Design for scale from day one. Ensure data pipelines, governance, and workflow integration are in place before pilots expand. << Blend build and buy. Leading firms use external vendors for speed while selectively building internal capabilities in sensitive or strategic domains. The early wave of GenAI adoption is producing plenty of activity, but limited impact. The next wave will be defined not by experimentation, but by disciplined execution, scale, and measurable business outcomes. The question for leaders is no longer “Should we pilot GenAI?” It is “What will it take to scale GenAI responsibly and profitably across the enterprise?”

The use-cases for AI and GenAI are truly limitless.    One of the new ways Deloitte is leveraging #GenAI is by supporting internal audit teams in their development of #AI strategies and applied capabilities. Not only are these tools supporting teams in the day-to-day audit process, but they are allowing them to build toward future-state operating models.    Here are a few of the ways Deloitte is offering AI-powered tools for the audit process:    Dynamic Risk Assessments – We utilize AI to develop end-to-end assessment capabilities to create more proactive models, resulting in a dynamic and iterative #risk assessment lifecycle that evolves with the org’s needs.    AI-on-Demand PODs – Our AI-on-Demand Product Oriented Delivery (POD) service delivery model consists of a team of engineers and designers to help clients develop customizable AI solutions that follow our Trustworthy AI Framework ™ (https://deloi.tt/3ywy7K8).    Automated SOX Scoping – We work with our clients to utilize AI to increase efficiency and save time during the Sarbanes-Oxley (SOX) scoping process. The statistical algorithms we put into place help clients develop a more accurate and risk-aligned scope for their SOX programs.    You can read more about how AI is changing the #audit landscape, here: https://deloi.tt/4d4xRBa Chris Griffin, Trevear Thomas, Dipti Gulati, Lynne Sterrett

🚨 Is your finance team using GenAI for journal entries, reconciliations, or board reports? My latest Substack article, GenAI Meets SOX: Audit-Proofing Your Finance Workflows, dives into why unchecked AI use is a compliance risk—and how to fix it. Regulators like the PCAOB and SEC are clear: AI outputs need traceable controls. From prompt logging to updated SOX narratives, learn five practical steps to keep your workflows audit-ready. 📥 Pro subscribers can download templates to streamline compliance. https://lnkd.in/eAThkJCh

Lately, I’ve been thinking about where GenAI systems actually break in practice. It’s rarely the model. Once you move past demos and start building real systems, the challenges show up elsewhere — integrations, coordination between components, reasoning paths, latency, reliability, and control. That’s what this diagram tries to capture. Things like protocol layers (MCP) that decouple models from tools, agents that can hand work to each other instead of relying on brittle chains, and GraphRAG where relationships matter more than keyword matches. You also start seeing why flow engineering and state management matter more than clever prompts, why reasoning at inference time changes how systems behave, and why small models running locally are often the right choice instead of defaulting to the biggest model available. The shift is subtle but important. GenAI is moving from model-centric thinking to system-centric thinking. If you’re building in this space, which layer has been the hardest for you recently: connectors, orchestration, evaluation, or cost/latency?