AI in Coding and Development

Google published a free ~50 page whitepaper on the new SDLC with Vibe Coding & Agentic Engineering! Today I'm sharing a 50-page paper co-authored by me, Shubham Saboo and Dr. Sokratis Kartakis Kartakis, and part of Google's 5-day AI Agents course on Kaggle. It's free and we think you'll find it a useful read. AI compresses implementation from weeks to hours. But requirements, architecture, and verification stay stubbornly human-paced. That asymmetry changes everything. The bottleneck isn't typing anymore. It's spec quality. Vibe coding and agentic engineering aren't different tools. They're different disciplines. The difference isn't whether you use AI. It's how much structure, verification, and human judgment surrounds the output. Casual prompts and accepted-whatever-came-back is vibe coding. Formal specs, automated eval suites, CI gates, and human oversight of architecture is agentic engineering. Both use the same agent. What separates them is the harness. Agent = Model + Harness. There's a temptation to treat model quality as the explanation for everything good and bad about your agent. It's wrong, and it leads to the wrong investments. The model is the engine. The harness - the prompts, tools, rule files, sandboxes, guardrails, orchestration logic, observability - is the car, the road, and the traffic laws. When an agent does something wrong, the first instinct is to blame the model. More often the failure traces back to a missing tool, a vague rule, an absent guardrail, or a context window stuffed with noise. Most agent failures, examined honestly, are configuration failures. Three things I believe will stay true as the tools change: Structure scales, vibes don't. Vibe coding is valid for exploration and prototypes. For software organizations depend on, the discipline of agentic engineering is not optional. AI amplifies your engineering culture. Strong testing practices and clear architectural standards get dramatically more value from AI than teams without them. It's a force multiplier, and it multiplies both your strengths and your weaknesses. The human role is evolving, not diminishing. The builders who understand architecture, define precise specifications, and evaluate output critically are more valuable than ever. The skills that matter are shifting from implementation to judgment - from writing code to designing the systems that produce code. Generation is solved. Verification, judgment, and direction are the new craft. We hope you find the new whitepaper a helpful read! Download the PDF here: https://lnkd.in/gPsGzjPZ #ai #programming #softwareengineering

𝗥𝗔𝗚 𝗵𝗮𝘀 𝗰𝗼𝗺𝗲 𝗮 𝗹𝗼𝗻𝗴 𝘄𝗮𝘆 — 𝗮𝗻𝗱 𝗶𝘁’𝘀 𝗻𝗼 𝗹𝗼𝗻𝗴𝗲𝗿 𝗷𝘂𝘀𝘁 𝗼𝗻𝗲 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲. Today, Retrieval-Augmented Generation (RAG) is a design space. There are many emerging patterns, but in this post, I’m focusing on the 𝘁𝗼𝗽 𝟴 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲𝘀 you should know in 2025. Why? Because the way we retrieve context 𝘥𝘪𝘳𝘦𝘤𝘵𝘭𝘺 𝘴𝘩𝘢𝘱𝘦𝘴 how intelligent, useful, and safe our AI systems are. Here are 8 RAG variants changing how we build with LLMs: • 𝗦𝗶𝗺𝗽𝗹𝗲 𝗥𝗔𝗚 𝘄𝗶𝘁𝗵 𝗺𝗲𝗺𝗼𝗿𝘆 — add past interactions to make responses more grounded • 𝗕𝗿𝗮𝗻𝗰𝗵𝗲𝗱 𝗥𝗔𝗚 — pull from APIs, databases, and knowledge graphs at once • 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 — where an agent decides what to retrieve and when • 𝗛𝘆𝗗𝗲 — generate hypothetical documents to guide more targeted lookups • 𝗦𝗲𝗹𝗳-𝗥𝗔𝗚 — the system rephrases, self-grades, and reflects before generating • 𝗔𝗱𝗮𝗽𝘁𝗶𝘃𝗲 𝗥𝗔𝗚 — chooses the best data source dynamically • 𝗖𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝘃𝗲 𝗥𝗔𝗚 (𝗖𝗥𝗔𝗚) — filters out noisy context using thresholds • 𝗦𝗶𝗺𝗽𝗹𝗲 𝗥𝗔𝗚 — still a valid choice when your data is clean and static    I created this visual guide to help AI engineers, architects, and teams rethink what retrieval can (and should) do. Because retrieval is no longer just “fetch and feed.” It’s evolving into an intelligent layer that brings 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴, 𝗳𝗲𝗲𝗱𝗯𝗮𝗰𝗸, 𝗮𝗱𝗮𝗽𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆, and 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 into GenAI systems. Have I overlooked anything? Please share your thoughts—your insights are priceless to me.

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

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.

AI Product Management AI Product Management is evolving rapidly. The growth of generative AI and AI-based developer tools has created numerous opportunities to build AI applications. This is making it possible to build new kinds of things, which in turn is driving shifts in best practices in product management — the discipline of defining what to build to serve users — because what is possible to build has shifted. In this post, I’ll share some best practices I have noticed. Use concrete examples to specify AI products. Starting with a concrete idea helps teams gain speed. If a product manager (PM) proposes to build “a chatbot to answer banking inquiries that relate to user accounts,” this is a vague specification that leaves much to the imagination. For instance, should the chatbot answer questions only about account balances or also about interest rates, processes for initiating a wire transfer, and so on? But if the PM writes out a number (say, between 10 and 50) of concrete examples of conversations they’d like a chatbot to execute, the scope of their proposal becomes much clearer. Just as a machine learning algorithm needs training examples to learn from, an AI product development team needs concrete examples of what we want an AI system to do. In other words, the data is your PRD (product requirements document)! In a similar vein, if someone requests “a vision system to detect pedestrians outside our store,” it’s hard for a developer to understand the boundary conditions. Is the system expected to work at night? What is the range of permissible camera angles? Is it expected to detect pedestrians who appear in the image even though they’re 100m away? But if the PM collects a handful of pictures and annotates them with the desired output, the meaning of “detect pedestrians” becomes concrete. An engineer can assess if the specification is technically feasible and if so, build toward it. Initially, the data might be obtained via a one-off, scrappy process, such as the PM walking around taking pictures and annotating them. Eventually, the data mix will shift to real-word data collected by a system running in production. Using examples (such as inputs and desired outputs) to specify a product has been helpful for many years, but the explosion of possible AI applications is creating a need for more product managers to learn this practice. Assess technical feasibility of LLM-based applications by prompting. When a PM scopes out a potential AI application, whether the application can actually be built — that is, its technical feasibility — is a key criterion in deciding what to do next. For many ideas for LLM-based applications, it’s increasingly possible for a PM, who might not be a software engineer, to try prompting — or write just small amounts of code — to get an initial sense of feasibility. [Reached length limit. Full text: https://lnkd.in/gYY-hvHh ]

AI security/securing the use of AI is going to kill me. I use Claude Code almost daily. It's a problem.... Here's what I have to change AGAIN this week. Security researcher Ari Marzuk disclosed 30+ vulnerabilities across AI coding tools. Cursor. GitHub Copilot. Windsurf. Claude Code. All of them. He called it IDEsaster. The attack chain includes prompt injection, hijacking LLM context, and auto-approved tool calls executing without permission. Then, legitimate IDE features are weaponized for data exfiltration and RCE. Your .env files. Your API keys. Your source code. Accessible through features you thought were safe. Most studies I read claim that around 85% of developers now use AI coding tools daily. Most have no idea their IDE treats its own features as inherently trusted. 𝗦𝗼... 𝗮𝗳𝘁𝗲𝗿 𝗿𝗲𝘃𝗶𝗲𝘄𝗶𝗻𝗴 𝗔𝗿𝗶'𝘀 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵, 𝗵𝗲𝗿𝗲'𝘀 𝗜 𝘄𝗶𝗹𝗹 𝗯𝗲 𝗱𝗼𝗶𝗻𝗴... Be warned: All this is SO much easier said than done! Audit every MCP server connection. Checked for tool poisoning vectors where legitimate tools might parse attacker-controlled input from GitHub PRs or web content. Removed servers I couldn't verify. Disabled auto-approve for file writes. The attack chains weaponize configuration files and project instructions like .claude/settings.json and CLAUDE.md. One malicious write to these files can alter agent behavior or achieve code execution without additional user interaction. Move all credentials to a secrets manager. No .gitignored .env files in agent-accessible directories. API keys live in 1Password CLI. Environment variables inject at runtime through a wrapper script the LLM never sees. Start running Claude Code in isolated containers. Mounted volumes limited to specific project directories. No access to ~/.ssh, ~/.aws, or ~/.config. If the agent gets compromised, blast radius stays contained. Enable all security warnings. Claude Code added explicit warnings for JSON schema exfiltration and settings file modifications. These exist because Anthropic knows the attack surface. Add pre-commit hooks for hidden characters. Prompt injections hide in pasted URLs, READMEs, and file names using invisible Unicode. Flag non-ASCII characters in any file the agent might ingest. The fix isn't to stop using AI coding tools. The fix is to stop trusting them implicitly. What controls do you have for AI tools with write access to your codebase? 👉 Follow for more AI and cybersecurity insights with the occasional rant #AISecurity #DevSecOps

AI tools can make iteration much faster. But production still needs the boring layers: auth, storage, deployment, security, scaling, monitoring, and recovery. A short checklist to pressure-test an AI-built product before calling it production-ready: 1. Data access * Who can see what data? * Are permissions enforced at the data or query level, not just in the UI? 2. State and storage * Where does the data live? * What happens when users refresh, retry, upload, delete, or edit the same record? 3. Failure handling * What breaks when the API is slow, the model times out, or traffic spikes? * Is there fallback logic, retry logic, or graceful failure? 4. Observability * When something goes wrong, can the team see what happened? Logs, traces, errors, user actions, and model inputs / outputs where appropriate. 5. Recovery * Can you recover without guessing? Rollback, restore data, redeploy safely, and understand what changed. The demo milestone is: it works once. The production milestone is: it keeps working with real users, real data, and real failures. And if you are building with AI, this upcoming course may be worth checking out: Build an AI-powered content and monetization engine 🔗https://lnkd.in/gpRFwD3G

I taught myself machine learning > 10 years ago. If I had to start again today, I wouldn’t touch models, LLMs, or agents first, as many AI experts suggest. I'd start with the math and the code. Ugly truth: 90% of people skip the foundations, then wonder why everything feels like magic or falls apart in production. If you want to be different, actually understand ML, not just copy-paste, this is the roadmap I'd follow: Start with fundamentals: Because no matter how fast LLMs or GenAI evolve, your math, code, and logic will keep you relevant. Here's what you should focus on: 📐 1. Linear Algebra Learn these core ideas: Vectors, matrices, tensors Matrix multiplication (dot products, broadcasting) Transpose, inverse, rank, determinants Eigenvalues & eigenvectors (especially for PCA & embeddings) Projections and orthogonality ✅ Use NumPy to implement everything yourself → Practice matrix ops, dot products, and visualizing transformations with Matplotlib 🔁 2. Calculus Focus on: Derivatives & partial derivatives Chain rule (for backpropagation in neural nets) Gradient descent Convex functions, minima/maxima ✅ Use SymPy or JAX to visualize and compute derivatives → Plot functions and their gradients to develop deep intuition 🎲 3. Probability You need a solid grip on: Random variables (discrete & continuous) Conditional probability & Bayes' rule Joint & marginal probability The Chain rule Expectation, variance, entropy Common distributions: Bernoulli, Binomial, Gaussian, Poisson Central limit theorem The law of large numbers ✅ Simulate simple probability experiments in Python with NumPy → E.g. simulate sampling from distributions 📊 4. Statistics These are must-know topics: Descriptive stats: mean, median, mode, standard deviation Hypothesis testing: p-values, confidence intervals, t-tests Correlation vs. causation Sampling, bias, and variance Overfitting/underfitting A/B testing basics ✅ Use Pandas & SciPy to explore real datasets → Calculate descriptive stats, create histograms/box plots, run t-tests 🔧 Essential Python libraries to learn early NumPy – for vectorized math and fast array ops Pandas – for loading, cleaning, and analyzing tabular data Matplotlib / Seaborn – for plotting and visualizing distributions, relationships, and trends SymPy – for symbolic math and calculus SciPy – for stats, optimization, and numerical methods Use Jupyter Notebooks(to combine math, code, & visuals in one place) 📚 Best resources to nail the fundamentals: ✅ Machine Learning Foundations Math series (ML Foundations: Linear Algebra, Calculus, Probability, and Statistics)-series of 4 courses that I've created together with LinkedIn learning ✅ Hands-On ML with TensorFlow & Keras book by Aurélien Géron ✅ The Hundred-page Machine Learning Book by Andriy Burkov If you want to become an actual ML engineer, not just someone who watches and copies demos, start here. ♻️ Repost to help others💚

Developers want to create solutions. Not port Java 11 to Java 17. The real opportunity with AI isn't about chasing the latest trend. It's about removing the undifferentiated heavy lifting that keeps teams from doing their best work. The latest research on Amazon Science validates this approach. Using our cost-to-serve-software framework (CTS-SW), teams that identified specific challenges before adopting AI tools cut costs by 15.9% year-over-year. They deployed more frequently and reduced manual interventions by 30.4%. And here's what really matters. Team velocity became the strongest predictor of cost efficiency in software development. This isn't just about AI. It's about focusing on the right problems first. Read the research here: https://lnkd.in/eCdd3wxz Insights from Jim Haughwout here: https://lnkd.in/egMCX6qe Now, go build!

The Shift for Developers is More Radical Than We Think Over the next 24 months, the very identity of a software engineer won’t just be reshaped—it will be redefined from the ground up. We’re moving from a world where mastery meant syntax… …to a world where mastery means orchestration. The best engineers won’t just write code. They’ll reason across complex systems. They’ll prompt AI agents to build, test, and optimize code. They’ll architect workflows that combine human intent and machine autonomy. Code authorship becomes a small—but still meaningful—part of a broader system of intelligence. This isn’t just a step function improvement. It’s a whole new way of thinking. And here’s the counterintuitive part: AI won’t reduce the role of developers—it will expand it. So those that are eager to learn AI and push themselves. Developers who resist this change will be left behind. Those who embrace it will become 10x, 50x more impactful—not only in their output, but in the scope of the problems they will be able to solve. They won’t just build features. They’ll become architects of intelligence. At Cisco we believe this future will belong to companies that: • Reimagine what development looks like in an AI-native world • Treat agentic AI not as a tool, but as a collaborator • Attract and develop the world’s best builders—and give them an environment to do the most meaningful work of their careers That’s why we’ve partnered with OpenAI—not just as customers, but as co-designers of our future. Through initiatives like Codex and deep partnerships with leading AI companies, we’re going to completely up-level how technology gets built and the class of problems it ends up solving. But this isn’t just about Cisco evolving. It’s about expanding what’s possible: • When AI unlocks a developer’s full potential… • That developer unlocks Cisco’s full potential… • And Cisco, in turn, will power and secure AI to help unlock AI’s full potential… This isn’t augmentation of AI. This is a fundamental reinvention with AI. When we look back 10 years from now, I believe the decision to go all-in on AI—to fundamentally reimagine how our product teams work—will be seen as one of the most consequential moments in Cisco’s history. Our goal is to make Cisco THE destination where the world’s best developers want to assemble to build infrastructure and platforms that power and secure AI to solve some of the hardest and most important problems faced by humanity. See my blog of the partnership in the comments