Tommy MacWilliam

Ask AI how OpenClaw can automate workflows in your business, then send me a message and I'll get that all setup for you. Setting up an agentic system can be tricky. Northstar AI Labs has been deep in the weeds, developing AI solutions. If you have heard of AI automation, but you don't want to DIY, a hassle free installation is just 1 message away.

1

rqlite -- and the way I develop it -- is fundamentally changing. LLMs are in the loop -- from ideation to Pull Request. https://lnkd.in/ejwXGddR

27

1 Comment

Curious: has anyone found a particular sub-agent role or setup that's been especially powerful? Would love to compare notes. I've been experimenting with Claude agent teams lately, and one thing stands out: the software paradigms we've always relied on (API design, test coverage, modularity) matter more when working with AI, not less. Giving each sub-agent a specific role (Team Lead, Frontend Dev, Backend Dev, QA Engineer) produced noticeably better results than asking one agent to do everything. Wrote up what I learned using a calculator app as the example. Link in the comments.

12

1 Comment

Euclid Power has raised a $20M Series A! Since my network is largely designers and tech friends not typically working in finance or energy: the company provides services and a platform that people use to bring renewable energy power plants to the grid. I've been working with the team on designing the platform interface and experience. It's been eye opening to dive into the details of the workflows of energy developers, investors, and independent power producers, and to design for clarity, efficiency, and calmness for work that can get chaotic and stressful.

56

8 Comments

Thrilled to share my latest article: "The Mixed-Initiative Interface: Designing Control Handoffs Between Humans and AI." In a world where AI handles more decisions, the real UX frontier is the seamless transfer of control—ensuring humans can step in without losing context, state, or accountability. We're moving beyond rigid autonomy to dynamic systems where handoffs are graceful and empowering. Key insights include: - The Handoff Problem: Mixed-initiative systems allow bidirectional control shifts; the challenge is preserving state during transitions to avoid confusion. - Decision Ledger: An append-only log of actions, confidence scores, and reasoning to brief humans on AI's prior steps. - Non-Destructive Overrides: Use proposal queues for AI suggestions that can be reviewed or modified without halting workflows. - Calibrating Confidence: Dynamic thresholds based on consequence, reversibility, and confidence—err toward escalation to build trust. - Reversibility and Intervention Windows: Leverage event sourcing for undos and strategic delays to enable human oversight in high-stakes scenarios. This is essential for anyone building AI-powered products: think pricing optimization, fraud detection, or any domain blending human judgment with machine efficiency. Does this align with challenges you're facing in your work? Read the full piece here: https://lnkd.in/dX_y7YMa

5

For solo founders and small teams, the leverage asymmetry is now absurd. One person in flow can out-ship a committee. The bottleneck moved from "can we build it?" to "do we have the clarity and uninterrupted time to build it?" Protect your focus like it's your most valuable asset. Because it is. #ClaudeCode #Convex #Greptile

39

1 Comment

Here at Birdie AI, it's been 2 weeks that 100% of designers and PMs have been shipping PRs. "Design debt" is no longer a hassle, every detail matters. What a time to be a #builder. Thanks for the inspiration Koji Pereira 🔥

25

3 Comments

💥 I just found a foundational flaw in Claude. All models, all interfaces. Repro steps below: 1. Go to Claude settings 2. Attempt to update your email address 3. If you can’t find how to do it on your own, ask Claude how to change your Claude email address 4. Validate that Claude is not hallucinating by going to https://support.claude.com and searching for “How do I change the email address associated with my account?” 5. Shake your head and think “sorry users, I know we kind of slid past this when you signed up. Hope the email you used to sign up never gets compromised or needs to change – magic links or SSO are the only option (darn it). And if it does, hope you didn’t buy an annual PRO plan because no refunds / transfers even if to the same human ✌ (grrrr…)” Perhaps this behavior is the result of conscious prioritization based on a thorough understanding of needs / trade-offs. If this behavior was an oversight, then based on prior trips on the modernization train, this could be a massive slog of tech debt. Particularly in a hyper-growth business dependent on uninterrupted & high-integrity data access / entitlements / provenance. Product people – let's use this moment to build foresight! - Don’t abdicate PM or UX from “technical” discussions about data models, identity, or access control – decisions within these domains have incredible implications - Customer onboarding & admin workflows are foundational CX, not afterthoughts - If you’re using Claude Code, invest in Git + GitHub integration for improved resilience (and much more)

3

More than $4 trillion in equity compensation (RSU, ISO, ESPP etc) remains unmanaged for employees. Founded by veterans in this field, Grantd helps financial advisors transform this complex, often-overlooked benefit into actionable tax-informed strategies for clients and new business opportunities for advisories. We’re excited to see our strategic partners share this vision and place their trust in the team.

8

Experimentation isn’t the hard part. Knowing which decisions are reversible—and which aren’t—is. In the latest episode of Pendo.io’s Hard Calls podcast, Trisha Price and Jeff Lash break down how thinking in one-way vs. two-way doors helps product teams move faster without creating long-term drag. Give it a listen! #ProductLeadership #ProductManagement #DigitalAdoption #HardCalls

1

PostHog is perfect for engineers. PMs need a different lane. PostHog nails what engineers care about. But sticky adoption comes from deep hypothesis testing and measurement - work that lives squarely with PMs. Engineers should be shipping. Context-switching between code and funnels is a tax. 👉 Our take: -Engineers wire up the data. - PMs own the hypotheses - what’s working, what isn’t, and why. - That job can easily be full-time. 🌟 So we’re building a PM-native layer on top of PostHog: - Write a hypothesis → instantly pull the sessions/users that prove or disprove it - Measure intent, hesitation, and friction (not just clicks) - Trigger chatbots/pop-ups at the right moment - Map replays to customer conversations for fast follow-ups PostHog stays the engine. We’re giving PMs the perfectly handcrafter flow for hypothesis testing around adoption If you’re a PM using PostHog today, what’s the one workflow you wish existed?

4

For those of you prototyping with your actual codebase: are you handling both ideation and deliverables in the same tool? At UrbanBound, we've experimented with tools like v0, Gemini, and Figma Make during our ideation phase, helping us significantly leapfrog the blank slate portion of the design process. During that phase, we don't really care if the prototype matches our app; we're focused on UX and usability. When it's time to create deliverables for engineering, though, we DO care. Currently we're delivering high-fidelity Figma design files alongside a Figma Make prototype to communicate user flow. We'd like to get to the point where the prototype IS the spec. The dilemma: Figma doesn't know our codebase, and while it can approximate our design system, it can't do so with 100% fidelity. Our goal is to move away from static files and toward prototypes that use our actual design system and code. This approach would: 1) let our engineering teammates fully experience the UX and functionality;  2) free them to focus on building that functionality vs sweating the UI details, and  3) save design a lengthy documentation step. Goodbye marked up design files attempting to explain functionality! Our engineers use Cursor, and it feels like that could be the design prototyping tool, too (we're kicking the tires). If you are prototyping with code: is your design team in the same IDE as engineering? Or are you finding a middle ground? I'm asking from both a process perspective, but also a credit management perspective; what's worth burning credits on? Curious how others are navigating these new waters. #ProductDesign #UX #DesignSystems #Prototyping #AI

3

4 Comments

Taste, Privacy-by-Design & AI-Native Product Teams I’ve been noodling on where privacy work actually might land now that Cursor-style IDEs can spin up a PRD, design doc, and draft pull-request before you finish your coffee. Faster loops aren’t the enemy (even though that's all of our first reactions)—thought-free loops are. Here are three places I see privacy pros adding real value without slowing the train: Sit in the design sprint, not the review queue. AI-generated mocks hit Figma in minutes—jump in that same hour. Ask: Does this risk control feel natural or bolted on? Fix the pattern before it hardens into code. Raise the bar for your toolchain. Adopt better privacy toolchains. Push vendors toward policy-as-code, field-level lineage, and region toggles so AI agents can wire 90 % of controls automatically. Your time is reserved for the edge cases that need human judgment. Point AI at your own work—red-team style. Let models stress-test consent flows, purpose limits, retention rules. Security teams already do this for exploits; direct the cannon at data-use risks, too. Caveat: retrofitting these habits onto a legacy “spaghetti” stack is tougher than starting greenfield—but I think the principles will hold. I'm curious what else your teams are doing today to keep privacy in the loop while the build cycle keeps shrinking? 

34

A) allow AI tools in the interview B) test for what people are hired for that AI can't do well. Rn that's system design, tradeoffs, etc. Will change every 6 mo as AI gets better. Biggest companies in the world (F500, INC5000, and Tier 1 VC startups) have alr started to prepare for AGI using Rounds, have you?

19

3 Comments

I am excited to share with you the first post of our Engineering Blog! In this issue we cover some of the key engineering decisions we made that have enabled our lean team to build a multi-cloud, regional platform that is used by enterprises today. We will be sharing deeper dives into many of the topics mentioned in this post. If the problems and the tech we are building at Thread AI excite you, we'd love to hear from you!

48

2 Comments

I’ve been writing a series of posts on the design principles behind Looping, a product I’m building to help teams run and evolve software over time. These principles shape the architecture underneath and have helped me prioritize clarity, composability, and long-term maintainability from the start. The latest post in the series is about Composable Services. In Looping, every service follows the same interface: it takes a hash of input and returns either Success() or Failure(). That consistency makes services easy to test, reuse, and chain together without resorting to sprawling conditionals or unpredictable side effects. The post walks through the structure, shows real examples, and touches on how it tracks source chains for observability and event logging. https://lnkd.in/ePkn-pF6 #ruby #rails #softwarearchitecture #buildinpublic

7

2 Comments

Many of you ask: What exactly do you do? We match companies with fractional CTOs/CPOs and vetted dev agencies across five engagement models to build software with a human-in-the-loop: — Project work Going to a restaurant. You order. They cook. You eat. — Team augmentation You are cooking at home. Tonight is ambitious. You bring in an extra pair of hands. — Build-Operate-Transfer You love the restaurant so much, you open your own. We build it, run it, then hand you the keys. — Product discovery Before you cook anything, you taste-test. Figure out if the dish is worth making at all. — Fractional CTO/CPO You do not need a full-time head chef. But once a week, you need someone to fix the menu. We match you in hours as we have all the data to triage to your requirements.

20

20 Comments

Will conversational AI UX become a "boring" platform feature like copy and paste that users expect to be available across all apps they use? One thing that feels clunky right now is that each app has its own "agent" you chat with but they don't interoperate smoothly. Imagine copy and paste only worked in excel and you couldn't copy cell contents into an email. This is what it's like to use Notion AI to rewrite a product plan and then switch over to using Claude Code to implement it. I need to explicitly tell Claude what we're working on. MCPs, ChatGPT apps, and AI-native browsers are a step in the right direction. I know there are competitive reasons companies want to have separate agents and to keep their user data as context only available for themselves, but I wish I could seamlessly switch between working on a doc, chatting with a coworker about a project and implementing the code for it in a single conversation with the same agent.

15

1 Comment

Complex Group Onboarding just got a whole lot easier! Client onboarding sounds straightforward: send a request, they complete it, done. But what happens when that "client" isn't just one person? What if they have a Family Trust? A spouse? They're a director of a company, and there's another director you need to ID because you're also servicing the business? That's where it gets messy. Until now. Our latest update solves this. We've built multi-user onboarding so you can handle complex client structures without the headache.

9

1 Comment