Training & Development

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build. Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention. The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention! Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on. The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience. When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful. [Truncated for length. Full text: https://lnkd.in/gKDQ6H9s]

We keep being told that more screens improve learning. The evidence is far less convincing. What stands out to me in this debate is the gap between what parents are told and what the research actually suggests. During a recent Senate hearing, brain expert Jared Cooney Horvath made a simple point: Children do not learn better just because a screen is involved. That matters. Because “digital” has too often been treated as if it automatically means “effective.” More devices. More platforms. More screen-based instruction. But children still learn the way they always have: through movement, conversation, hands-on experience, curiosity, and real engagement with the world around them. That is why many families are stepping back and rethinking education. They are choosing: → hands-on learning → real books → open conversation → curiosity-led exploration → the freedom to learn at a natural pace To me, this is the real issue. The question is not whether technology belongs in education. It does. The question is whether we are confusing constant digital exposure with meaningful learning. Because more screen time is not the same as deeper understanding. Are we improving education, or just making it more digital and calling that progress? #Education #Learning #Parenting #Homeschooling #EdTech #FutureOfLearning #ChildDevelopment #Teaching #Schools

Most people are taught how to be high performers. But too few are taught how to perform in a team. And that’s a problem, because in most roles, you’re not an individual contributor. You’re part of a larger entity, working with others to build something. Yet, I see founders spend hours refining their product or systems,  But don't devote time to team development. At HomeServe, I approached team performance with purpose,  And it was one of the best decisions I made. Here are 7 tools I’ve used (and still use) to build high-performing teams,  Based on real lessons from building a £4.1bn business: 1️⃣ Start With Why (Simon Sinek) ↳ Before you focus on what or how...get clear on why. WHAT – The product you sell or the service you provide HOW – What makes you different WHY – Your deeper purpose or belief Every great team needs a reason to get out of bed in the morning. 2️⃣ The 70-20-10 Rule (McCall, Lombardo & Eichinger) ↳ How people actually learn on the job: 70% from challenging experiences 20% from coaching and mentoring 10% from formal training Most teams over-invest in training, and under-invest in real development. I'm amazed at how few founders or CEOs have a coach or mentor. 3️⃣ The Trust Triangle (Frances Frei, Harvard) ↳ Trust isn’t built with perks. It’s earned in three ways: Authenticity – Are you real? Logic – Do your decisions make sense? Empathy – Do you care? Without trust, you can’t build speed or loyalty. 4️⃣ The 5 Stages of Team Development (Tuckman Model) 1. Forming – Team gets together 2. Storming – Conflicts surface 3. Norming – Ground rules form 4. Performing – Results roll in 5. Adjourning – Project ends or evolves Don't panic during ‘storming’. It’s necessary friction. 5️⃣ The Johari Window (Luft & Ingham) ↳ Self-awareness is a team sport. Open – You know, they know Hidden – You know, they don’t Blind Spot – They know, you don’t Unknown – No one knows (yet) This helps surface feedback, build confidence, and avoid surprises. 6️⃣ The Energy/Impact Matrix (Inspired by McKinsey) ↳ Map every team member’s impact vs. energy. Use it to: Make smart hiring/firing decisions Spot burnout early Retain high performers High-performing teams don’t tolerate drift. 7️⃣ The RAPID Decision-Making Model (Bain & Company) ↳ High-performing teams make fast, clear decisions. Recommend – Suggest the course of action Agree – Those who must sign off Perform – Executes the decision Input – Provides relevant facts or opinions Decide – Final decision-maker This clears up delays, dropped balls, and blame. Building a great team is about building an environment where talent can actually thrive. I go deeper into team-building in my new book. Order it today: https://lnkd.in/eRYDKXdT ♻️ Repost if you believe team performance should be built, not assumed. And for more on how I scaled teams to build a £4.1bn business, Follow me Richard Harpin.

Avoiding discomfort isn’t leadership—it’s abdication. Too many leaders see smoke in their organization and convince themselves it will take care of itself. Maybe it’s a performance issue, a personnel conflict, or a cultural drift. The temptation is to hope it fizzles out on its own. But here’s the truth: sparks almost always become fires. And when the leader turns away, everyone else does too. The ripple effect is costly: Problems grow instead of shrink. Teams assume someone else will deal with it. Trust in leadership quietly erodes. Real leadership means doing the opposite. It means running toward the smoke. Addressing issues early. Taking on a little bit of preemptive suffering so your people don’t have to experience a lot of suffering later. That’s what builds trust, credibility, and a healthier culture.

Humans are unique in that we can learn information throughout our entire lifespan through a process called neuroplasticity. Learning is a multistage process that requires focus and attention on the information we’re trying to learn, and then we must let our brain enter states of deep rest, in particular deep sleep and REM sleep (rapid eye movement), because that’s when the actual rewiring and plasticity of neural circuits occur. One of the most interesting research findings in the last decade is that mental rehearsal and self-testing of material we’re trying to learn, done later and away from exposure to the material, is one of the best ways to accelerate and deepen learning. This is NOT the same as saying that mental rehearsal is all that’s needed. We need real-world repetitions and exposure to information and skills that we’re trying to learn. But that’s just the initial stimulus. Self-testing and thinking about what we did correctly and incorrectly cause our neural circuits to change faster and more accurately. We forget less, too. This has been shown to apply to cognitive and skill learning, music, math, languages, sports, dance and on and on… Very few people incorporate the mental self-testing step of the learning process, but those who do can benefit tremendously. I did a solo episode of the Huberman Lab podcast called “Optimal Protocols for Studying & Learning,” where I go deep into the research on this and specific protocols you can use. But the slide summarizes the key overall takeaway. And as always, thank you for your interest in science!

Google just released LangExtract - an open-source Python library that turns the chaos of unstructured text into perfectly structured data with surgical precision. Think bank statements for transaction data, extracting medication dosages from clinical notes, pulling contract terms from legal documents - LangExtract handles it all. The new framework addresses a critical gap in production AI: while LLMs excel at understanding text, reliably extracting structured information without hallucinations or lost context has remained frustratingly elusive. LangExtract solves this with a refreshingly practical approach that maps every extraction back to its exact character position in the source. Package highlights: (1) Precise source grounding - every extracted entity includes exact character offsets, providing bulletproof traceability and enabling interactive visualizations that highlight extractions directly in the original text (2) Controlled generation with few-shot learning - define your schema with just a few examples and LangExtract enforces structured outputs, leveraging Gemini's controlled generation to eliminate the randomness that plagues naive LLM extraction (3) Long-context optimization - handles massive documents through intelligent chunking, parallel processing, and multiple extraction passes (4) Domain flexibility - from clinical notes extracting medication dosages to legal documents identifying contract terms, LangExtract adapts to any domain without fine-tuning Define your extraction task with a prompt and one good example, point it at your text, and get back structured JSON with every field traceable to its source. It works with Gemini models out of the box and supports local LLMs through Ollama for privacy-sensitive applications. GitHub repo https://lnkd.in/gktf3D3S — Join thousands of world-class researchers and engineers from Google, Stanford, OpenAI, and Meta staying ahead on AI http://aitidbits.ai

By 2030, these 11 abilities will decide who gets hired Most don’t show up on resumes yet. The World Economic Forum just revealed the top skills for 2030 in the Future of Jobs Report 2025. And it’s a wake-up call. Today's celebrated tech skills? AI will do those better by 2026. Those certifications? Outdated in 18 months. But here's the good news: The skills that matter most in 2030? Technology can't replace them. Start mastering these skills to stay relevant and be recognized: 1. AI and Big Data 🤖 ❌ Passively watch AI replace jobs ✅ Make AI your competitive edge → Use AI to automate weekly reports → Build self-updating dashboards and summaries 2. Analytical Thinking 🧠 ❌ Drown in opinions and noise ✅ Let data drive key decisions → Identify root causes before reacting → Monitor metrics that reveal blind spots 3. Resilience, Flexibility and Agility 🐆 ❌ Break down under shifting priorities ✅ Adapt fast and lead through change → Stay steady during messy execution → Pause, breathe, ask: “What’s the next best move now?” 4. Motivation and Self-Awareness 👤 ❌ Burn out chasing urgency ✅ Work in sync with your energy → Track your energy every 3 hours for a week → Schedule focus work when your mind feels sharp 5. Curiosity and Lifelong Learning 🔍 ❌ Stick to your job description ✅ Learn a complementary skill to your role → If you're in marketing, study basic product design → If you're in finance, explore storytelling with data 6. Leadership and Social Influence 🌟 ❌ Rely on your title for respect ✅ Build trust by how you think, speak and act → Explain why you made a tough call, not just what you decided → Share a client insight that helped your team level up 7. Technological Literacy 💻 ❌ Run to the IT helpdesk for every issue ✅ Build and adapt your own stack → Automate one repetitive workflow today using AI → Use familiar tools more efficiently (Excel, Slack) 8. Systems Thinking 🔧 ❌ React to broken processes ✅ Design workflows that scale → Improve one repeated but inefficient process this week → Ask: “Can this run without me?” 9. Empathy and Active Listening 🎧 ❌ Talk to be heard ✅ Listen to support, inspire and lead → Listen without needing to speak more in 1:1s → Decode what’s really being said 10. Creative Thinking 🎨 ❌ Wait for inspiration ✅ Build innovation into routine → Ask: “What’s another way to solve this?” → Try a small change to test a new idea 11. Talent Management 👥 ❌ Try to do it all ✅ Delegate and develop future leaders → List 3 tasks to delegate now → Improve hiring processes to onboard the right talent 💡 It’s not about doing more. It’s about evolving how you think, lead, and grow. Because the future expects you to. Which one are you focusing on this month? -- ♻ Share this with someone you’d want on your 2030 team. ➕ Follow me (Meera Remani) for future-ready leadership strategies. 🔔 My best insights for transforming your leadership career? Join my exclusive email list. Link below.

𝗢𝗻𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗠𝗢𝗦𝗧 𝗱𝗶𝘀𝗰𝘂𝘀𝘀𝗲𝗱 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻: 𝗛𝗼𝘄 𝘁𝗼 𝗽𝗶𝗰𝗸 𝘁𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝗟𝗟𝗠 𝗳𝗼𝗿 𝘆𝗼𝘂𝗿 𝘂𝘀𝗲 𝗰𝗮𝘀𝗲? The LLM landscape is booming and choosing the right LLM is now a business decision, not just a tech choice. One-size-fits-all? Forget it. Nearly all enterprises today rely on different models for different use cases and/or industry-specific fine-tuned models. There’s no universal “best” model — only the best fit for a given task. The latest LLM landscape (see below) shows how models stack up in capability (MMLU score), parameter size and accessibility — and the differences REALLY matter.  𝗟𝗲𝘁'𝘀 𝗯𝗿𝗲𝗮𝗸 𝗶𝘁 𝗱𝗼𝘄𝗻: ⬇️ 1️⃣ 𝗚𝗲𝗻𝗲𝗿𝗮𝗹𝗶𝘀𝘁 𝘃𝘀. 𝗦𝗽𝗲𝗰𝗶𝗮𝗹𝗶𝘀𝘁: - Need a broad, powerful AI? GPT-4, Claude Opus, Gemini 1.5 Pro — great for general reasoning and diverse applications.   - Need domain expertise? E.g. IBM Granite or Mistral models (Lightweight & Fast) can be an excellent choice — tailored for specific industries.  2️⃣ 𝗕𝗶𝗴 𝘃𝘀. 𝗦𝗹𝗶𝗺:  - Powerful, large models (GPT-4, Claude Opus, Gemini 1.5 Pro) = great reasoning, but expensive and slow. - Slim, efficient models (Mistral 7B, LLaMA 3, RWWK models) = faster, cheaper, easier to fine-tune. Perfect for on-device, edge AI, or latency-sensitive applications.  3️⃣ 𝗢𝗽𝗲𝗻 𝘃𝘀. 𝗖𝗹𝗼𝘀𝗲𝗱   - Need full control? Open-source models (LLaMA 3, Mistral, Llama) give you transparency and customization.   - Want cutting-edge performance? Closed models (GPT-4, Gemini, Claude) still lead in general intelligence.  𝗧𝗵𝗲 𝗞𝗲𝘆 𝗧𝗮𝗸𝗲𝗮𝘄𝗮𝘆? There is no "best" model — only the best one for your use case, but it's key to understand the differences to make an informed decision: - Running AI in production? Go slim, go fast. - Need state-of-the-art reasoning? Go big, go deep. - Building industry-specific AI? Go specialized and save some money with SLMs.  I love seeing how the AI and LLM stack is evolving, offering multiple directions depending on your specific use case. Source of the picture: informationisbeautiful.net

It takes one minute to damage a career you spent 30 years building. Because success isn’t about skill or intelligence. It’s about emotional regulation. Exercising restraint instead of: → Engaging in a heated debate with a client. → Exchanging a sharp word with a colleague. → Sending an angry email in the heat of the moment. The second you lose control, you’ve lost. Emotional regulation is the biggest marker of career success. The good news is it’s a muscle you can build. Here's how: 1. Know Your Triggers → Identify what sets you off. → Do you feel threatened when criticised? → Awareness is the first step to control. 2. Hit Pause → Before reacting, ask yourself: What are the consequences of my move? → Regret minimisation is critical. 3. Reframe the Experience → What else could this mean? → Maybe the person was having a bad day. → Chose an interpretation that serves you. 4. Create a Delay on Emails Sent → Set a 10-minute delay on all outgoing emails. → This in and of itself could save your career. 5. Breathe → When emotions rise, take three slow breaths. → It signals your nervous system to reset. → Simple, but powerful. 6. Speak With Emotional Intelligence → Once you’re ready to respond, choose your words carefully. → Ask: How can I create the right outcome in a calm way? Remember: → If you choose restraint, you win. → If you reframe, you grow. And every time you stay in control, you keep your power. How important do you think emotional regulation is for career success? ---- ☀️Follow Deena Priest for career, leadership and personal development insights.

"Feedback is a gift. It's an opportunity to learn and grow" At Google, we believe in the power of feedback to drive improvement. Sometimes feedback can be tough to hear. But taking the time to unpack it, understand the perspective, and reflect on it is crucial. Why feedback matters: - It reveals blind spots we cannot see ourselves - It accelerates learning by shortcutting trial and error - It demonstrates that others are invested in your success - It creates alignment between perception and reality How to receive feedback effectively: 1. Approach with curiosity, not defensiveness When receiving feedback, your first reaction might be to justify or explain. Instead, listen deeply and ask clarifying questions: "Can you give me a specific example?" or "What would success look like to you?" 2. Separate intention from impact Remember that well-intentioned actions can still have unintended consequences. Focus on understanding the impact rather than defending your intentions. 3. Look for patterns across multiple sources Individual feedback may reflect personal preferences, but patterns across multiple sources often reveal genuine opportunities for growth. 4. Prioritize actionable insights Not all feedback requires action. Evaluate which points will have the greatest impact on your effectiveness and focus your energy there. 5. Follow up and close the loop Demonstrate your commitment by acknowledging the feedback, sharing your action plan, and following up on your progress. Creating a feedback-rich environment: - Model vulnerability by asking for feedback yourself - Recognize and celebrate when people implement feedback successfully - Make it routine through structured check-ins rather than waiting for formal reviews At Google, we've learned that organizations with robust feedback cultures innovate faster, adapt more quickly to market changes, and build more inclusive workplaces. Let's commit to seeing feedback not as criticism but as a valuable investment in our collective future. The discomfort is temporary, but the growth is lasting. #motivation #productivity #mindset