Gregory Lind

Innovation often hides behind wrappers. MCPs promise scale and speed, but let’s be honest: they’re just orchestrated prompts and APIs. Valuable? Yes. Foundational? No. The deeper question: are we funding primitives—or just better packaging? The history of technology is littered with companies that confused distribution hacks for paradigm shifts. Efficiency matters. But leaders must know the difference between an infrastructure play and a true leap in capability. So—what deserves our capital: elegant wrappers or new primitives? https://lnkd.in/g8yUQzDb #AI #InnovationStrategy #Technology

14

2 Comments

🦜Deep Agents <> MCP Added a section to the Deep Agent docs on how to use them MCPs This lets you set up an agent that can plan and act over longer time horizons and can also connect to arbitrary services Docs: https://lnkd.in/g2EaYy6r

462

15 Comments

Interoperability isn’t just a technical problem, it’s a human one. When we talk about interoperability in verifiable digital credential systems, too many conversations stop at technical standards, APIs, and data formats. Yes, these matter, but they’re only one layer of the stack. Real interoperability lives in the social and cultural systems that surround the technology: ✨The data models that determine what gets recognized and what gets left out. ✨The governance frameworks that shape who gets a seat at the table and who doesn’t. ✨The trust we build not just in the tools, but in the communities maintaining them. ✨The transparency to say when something isn’t interoperable, and the humility to fix it. Too often, vendors talk about interoperability as if it’s something you can solve with a spec sheet. Yet, if we’re serious about credentials that can move across systems, sectors, and societies we have to care as much about people, process, and power as we do about protocols. Interoperability isn’t just about systems talking to each other. It’s about humans agreeing on what’s worth saying. #DigitalCredentials #Interoperability #Trust #OpenStandards #Governance #DigitalIdentity #EthicalTech #PeopleFirst

31

2 Comments

The tech industry's "good times" are over—so now what? Sean Goedecke delivers a candid, insightful breakdown of how the software engineering landscape has changed. The days of lavish perks and unquestioned autonomy are fading. As rising interest rates reshape company priorities, engineers must realign their expectations and understand the new value equation: deliver outcomes that matter to leadership, or risk being left behind. https://lnkd.in/gyCr5rd2 #TechCareers #SoftwareEngineering #EconomicShift

14

1 Comment

So which models produce HTML that has the least accessibility errors, and at what cost? Mapped it out here (bottom left is the best). This is helpful for understanding which models are most compliant for those with disabilities and do it efficiently. Qwen and Gemini 2.5 Flash lead the pack. Hat tip to Ben Ogilvie for pointing me to this: aimac.ai

55

2 Comments

Remember when embedded development meant poring over register definitions and writing every line of code from scratch? Those days are fading fast. RTOSes, HALs, and auto-generated code now handle much of the heavy lifting, making development faster and more accessible. But there's a trade-off—as fewer engineers touch low-level code, we risk trading efficiency for convenience. Many engineers never touch the metal. They don’t need to. They grab a vendor library, visit GitHub, or ask AI. But what happens when performance bottlenecks creep in? When debugging goes beyond the abstraction layers? When an RTOS just isn’t precise enough? Bare-metal isn’t dead; it’s evolving. It’s becoming a specialized skill rather than a daily necessity. But when SDKs are too slow, power budgets are tight, or real-time constraints demand control, bare-metal expertise separates great engineers from good ones. So, where do you stand? Do you still have the skills to program at the register level, or are you riding the abstraction wave? Let’s discuss: has bare-metal programming truly disappeared, or has it just changed its role in modern embedded systems? Let me know what you think below. #EmbeddedSystems #RTOS #BareMetal #Firmware #SoftwareEngineering

167

51 Comments

Two weeks ago, Steve Yegge released GasTown: a multi-agent orchestrator he describes as "an industrialized coding factory manned by superintelligent chimpanzees." A few days later, Dan Lorenc, inspired by GasTown, pushed multiclaude, built on what he calls the "Brownian Ratchet" principle: chaos is fine, as long as we ratchet forward. They landed on almost identical architecture: - tmux for observability - git worktrees for isolation - External state persistence - CI as the final arbiter While they have very different approaches (i like both! for different reasons!), when two experienced engineers solve the same problem and arrive at the same primitives, that's not coincidence. That's the problem space telling you what it actually requires. The "19-agent trap" - simulating an org chart with Analyst → PM → Architect → Dev → QA handoffs - is giving way to something more operational. Bounded roles. Infrastructure primitives. CI as coordination mechanism instead of real-time sync. The chimpanzee factory and the Brownian ratchet asked different questions but got the same answer. If you're building agent systems, these are probably your primitives too.

251

26 Comments

The fundamental coding agent abstraction is the CLI. It’s not a UI or form factor preference, it’s rooted in the fact that agents need access to the OS layer. Coding agents are, at their core, computer-use agents. They run programs, create new ones, install missing ones, scan the filesystem, read logs. More than text editors, they’re *automating your computer* at a low level. It’s more accurate to think of Claude Code as “AI for your operating system” than a continuation of the copilot autocompletion → IDE AI assistance paradigm. Another consequence is that it works for any computer. Your desktop computer, but crucially, also the ones running in the cloud. 𝚗𝚟𝚒𝚖 nerds like yours truly always liked that it’s an editor that runs on your Mac but also any machine you 𝚜𝚜𝚑 into. Imagine if you could launch a million Claude Codes concurrently to tackle a bug, find cybersecurity threats, process your issue backlog, build features based on user feedback, run QA… That’s why we’re building vercel.com/sandbox as the infinite compute layer for agents.

499

29 Comments

When it comes to selecting the right DXP, things can go off the rails. But don’t lose your caboose. Dan Drapeau has a two-track evaluation model that can keep you rolling – full steam ahead. In today's Guest Critic article, Dan proves why he’s a masterful conductor on the digital experience train. As he explains, the DXP competitive landscape has converged across architectural models, and evaluation approaches haven’t evolved at the same pace. Dan’s observation is that single-track processes are still chugging along – focusing on feature breadth and demo cohesion and favoring pre-composed suites. In his experience, what we really need is a more balanced approach that separates platform evaluation from ecosystem architecture. How do you leave the station? By running two structured tracks, which he outlines in detail. This helps vet not only current capabilities but also long-term durability relative to core considerations like vendor lock-in, CDP and DAM strategies, and the ever-evolving target of AI. In his post, Dan details the operational requirements, where the complexities exist, and how to synthesize results. He even digs into the critical topics of validation and stress testing, and distills it all into a handy checklist to help guide your DXP evaluation. As he says, composable and pre-composed DXPs represent architectural strategies along a spectrum, and these pointers can help keep you on track. “A structured two-track evaluation approach ensures that whichever model is selected, it is chosen for structural alignment and long-term outcomes rather than surface cohesion.” If you’re currently evaluating DXPs – or considering it in the future – this is a fantastic read from a sharp practitioner. Check it out on CMS Critic: 🔶 https://lnkd.in/e-XB3Pig #dxp #digitalexperience #digitalexperienceplatform #softwareevaluation #dam #digitalassetmanagement #cdp #customerdata #customerdataplatform #cmp #contentmarketingplatform #ai #artificialintelligence

15

1 Comment

Coding bootcamps as a product largely collapsed in 2024–2025. The job market was the trigger, but the deeper issue was structural: many bootcamps optimized for enrollment instead of building defensible IP. I’ve been saying this for years. When I pushed bootcamps to focus less on volume and more on the engineering value they were creating, I caught plenty of heat for it. What felt obvious to me eventually became reality, and some still won’t acknowledge it. In tech, IP matters. It's the novel way of doing things captured in real code. It creates value even when customers slow down. It can make you an acquisition target when things go sideways. It also builds credibility with strong technical people, and that credibility compounds. Community and raw user counts can help, but they’re fragile. If the community fades, the value often goes with it. Too many bootcamps had little to no IP. They relied on generic or free curriculum, stitched together third-party tools, and called the glue a product. That works in a boom. It fails when conditions tighten. The silver lining is simple: admit it, learn, and build something real. Instead, I’m seeing defensiveness and deflection, and it’s making the industry’s decline sad to watch.

53

13 Comments

Agentic code development is improving fast. Models are more capable, agents more autonomous. But the systems they interact with are only getting more complex. Code alone isn’t enough context for this future (and present). At Hud, we believe coding agents need access to real system behavior - at runtime - to reason effectively, detect failure patterns, and generate code that holds up in the real world. That’s what our Runtime Code Sensor does. After installing it in minutes, it captures function-level behavior automatically, and streams it through Hud’s MCP server into the agent’s workflow. ▶ See it in action: hud.io

174

9 Comments

Claude Code and Opus 4.5 have recently made meaningful strides in raising the bar on agentic development. However, I’ve discovered that when you treat the agents more as teammates and less as automatons they really excel. Let me explain. Claude Code’s GitHub integration finally lets me manage agents the way a great CTO manages developers: with clear objectives, structured workflows, nuanced guardrails, and most importantly, stable context. I start every project in Claude Code's planning mode now. The agents and I work together to draft comprehensive plans. I review. We iterate. Then, and this is the key, we instantiate those plans as GitHub epics. Each epic becomes a container for related issues. Each issue becomes a discrete task with clear objectives, architectural guidelines, and acceptance criteria. The agents work methodically through the issues and submit PRs when done. They even check each other’s work, just like a human team would. Because Claude Code maintains context through these epics, we’re no longer fighting context window exhaustion. A three-week project stays coherent from day one to deployment. The agents can see the overall arc of the project at any time, track progress, and recall the architectural decisions from week one as they implement features in week three. The results have been striking. Code quality has improved markedly. The agents are producing more consistent, better-structured code that actually follows our established patterns. Error rates have dropped to levels I’d expect from more senior developers, not the interns agents sometimes seem to channel. And if they stray, I just ask them to revisit the epic and validate whether they’ve delivered against the requirements. They usually course-correct. With a growing level of comfort, I’m now starting to let the agents monitor GitHub on their own and select their own epics to work on, updating the underlying GitHub issues as they make progress. They’re not just executing rote tasks anymore—they’re participating in overall project management. Great tech leaders don’t micromanage. They set clear objectives, establish workflows, remove blockers, and trust their teams to deliver. That’s precisely what I’m doing with my agent teammates now. I’m just applying decades of engineering management wisdom to a new kind of hybrid team. And it’s working. Carpe Agentem. 🎯 #AgenticDevelopment #GitHubIntegration #ClaudeCode #EngineeringManagement #AI #FutureOfWork

168

15 Comments

Great read from Matt Brown last week on the context graph. He nails the vertical software structural advantage we’re pursuing at Canvas Medical. ”A context graph is a queryable record of business logic: the reasoning, precedents, and decision traces that explain why things happened, not just what happened.” Vertical software companies with the right tools and architecture can expose that record to AI and allow agents to take autonomous action with full context. This leads to compounding advantages in agent coordination, evaluation and reliability. In a vertical software business, the data model is “opinionated, purpose-built, and mapped to that industry’s reality.” The article uses the example of Toast, for restaurants. In an EMR platform these concepts span clinical, financial and operational data (e.g. demographics, diagnoses, encounter notes, claim codes, vitals, etc). Canvas takes this one step further, enabling our customer to both define and access custom elements in the data structure that are specific to their care model. So what is the advantage? Quoting again: “The reasoning gets recorded because the system is built around actual business decisions.”   “The context isn’t siloed because vertical platforms consolidate functions into one system.”   “The full decision trace is reconstructible because the ontology supports it.” As we start chaining AI agents together, and coordinating them to do work for businesses (generally) and healthcare (specifically for Canvas) those advantages become essential to system effectiveness. Or to use Matt’s words but adapt them to Canvas: 𝘌𝘢𝘤𝘩 𝘯𝘦𝘸 𝘧𝘶𝘯𝘤𝘵𝘪𝘰𝘯 𝘢𝘥𝘥𝘴 𝘪𝘯𝘧𝘦𝘳𝘦𝘯𝘵𝘪𝘢𝘭 𝘱𝘰𝘸𝘦𝘳 𝘵𝘰 𝘦𝘷𝘦𝘳𝘺𝘵𝘩𝘪𝘯𝘨 𝘢𝘭𝘳𝘦𝘢𝘥𝘺 𝘪𝘯 𝘵𝘩𝘦 𝘨𝘳𝘢𝘱𝘩. 𝘊𝘰𝘯𝘥𝘪𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘢𝘤𝘵𝘪𝘷𝘦 𝘮𝘦𝘥𝘪𝘤𝘢𝘵𝘪𝘰𝘯 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘮𝘢𝘬𝘦𝘴 𝘱𝘳𝘦𝘴𝘤𝘳𝘪𝘣𝘪𝘯𝘨 𝘥𝘦𝘤𝘪𝘴𝘪𝘰𝘯𝘴 𝘮𝘰𝘳𝘦 𝘢𝘤𝘤𝘶𝘳𝘢𝘵𝘦. 𝘌𝘭𝘪𝘨𝘪𝘣𝘪𝘭𝘪𝘵𝘺 𝘢𝘯𝘥 𝘪𝘯𝘴𝘶𝘳𝘢𝘯𝘤𝘦 𝘤𝘰𝘷𝘦𝘳𝘢𝘨𝘦 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘮𝘢𝘬𝘦 𝘤𝘭𝘢𝘪𝘮𝘴 𝘤𝘭𝘦𝘢𝘯𝘦𝘳. 𝘊𝘰𝘮𝘮𝘶𝘯��𝘤𝘢𝘵𝘪𝘰𝘯 𝘱𝘳𝘦𝘧𝘦𝘳𝘦𝘯𝘤𝘦 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘮𝘦𝘢𝘯𝘴 𝘱𝘢𝘵𝘪𝘦𝘯𝘵 𝘮𝘦𝘴𝘴𝘢𝘨𝘦𝘴 𝘢𝘳𝘦 𝘳𝘦𝘤𝘦𝘪𝘷𝘦𝘥 𝘢𝘯𝘥 𝘢𝘤𝘵𝘦𝘥 𝘶𝘱𝘰𝘯 𝘧𝘢𝘴𝘵𝘦𝘳. 𝘛𝘩𝘦 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘨𝘳𝘢𝘱𝘩 𝘥𝘰𝘦𝘴𝘯’𝘵 𝘫𝘶𝘴𝘵 𝘨𝘦𝘵 𝘸𝘪𝘥𝘦𝘳; 𝘪𝘵 𝘨𝘦𝘵𝘴 𝙙𝙚𝙣𝙨𝙚𝙧. 𝘋𝘦𝘯𝘴𝘪𝘵𝘺 𝘮𝘢𝘬𝘦𝘴 𝘵𝘩𝘦 “𝘸𝘩𝘺” 𝘳𝘦𝘤𝘰𝘯𝘴𝘵𝘳𝘶𝘤𝘵𝘪𝘣𝘭𝘦 𝘸𝘪𝘵𝘩𝘰𝘶𝘵 𝘦𝘹𝘱𝘭𝘪𝘤𝘪𝘵 𝘤𝘢𝘱𝘵𝘶𝘳𝘦. It’s a fantastic piece, linked here in comments.

24

5 Comments

An update on behalf of the .NET Foundation Project Committee... The most active Community projects for January 2026 were: Pull Requests: Bootstrap Blazor (69), Orchard Core (65) Commits: .NEXT (1349), Stride (217) New Contributors: .NEXT (7) Downloads: Polly (45.9M), Fluent Validation (22.3M) Full list: https://lnkd.in/ea2UB3st The most active Microsoft projects for January 2026 were: Pull Requests: .NET Runtime (622), Azure SDK for .NET (474), .NET Aspire (329) Commits: Roslyn (698), .NET Runtime (413)  New Contributors: .NET Runtime (16), .NET Aspire (15) Full list: https://lnkd.in/eCXKbiTx #opensource #dotnet .NET Foundation

20

1 Comment