Brian Tol

Going live is one thing. Seeing real work get done is another. Now that Akron AI is live, our focus is simple: how AI behaves once it’s inside real workflows. We didn’t design this to be another tool people have to manage. We designed it to manage work on their behalf. Agentic AI, for us, means: ● understanding intent ● deciding the next step ● taking action without constant prompts No babysitting. No manual handoffs. No switching between ten tools. Just AI that fits into how teams already work and quietly takes things forward. This is only the first phase. What matters now is learning from real usage and improving where it counts. #AkronAi #AgenticAI #ProductLaunch #AIStartup #BuildingInPublic #ProductThinking

9

1 Comment

This is a great tutorial for folks looking to do some automated refactoring to their PHP codebase. I’ll be speaking on the same tool Saturday.

4

With no affiliation, sharing this as I know it will be good. Peter Merholz's ideas have been instrumental in my shaping of design teams. As iF Design point out here - the right environment around the design team is key to producing a successful team. The role of the leader is to create that environment.

14

2 Comments

uncannyuse now has schema pages for Reality Composer Pro components—showing the exact USDA block RCP writes, field-by-field with types and sparse-authoring behavior, plus annotated fixture examples. 20 components covered so far. https://lnkd.in/dpsT2A-8

9

Spec-driven development has roughly doubled my coding output over the last couple months. It's also created a ton of documentation exhaust. Most discussion about spec-driven workflows ends at "ship the feature." Nobody talks about what to do with the spec after. I've iterated several times on this — from deleting specs immediately, to keeping a graveyard folder, to a new approach I'm pretty excited about: graduating spec content into permanent documentation when work ships. I wrote up a post covering what we learned through all three iterations, plus the templates and skills we're using in production today. Link in the first comment.

25

9 Comments

Remember the last time you saw "hacking" in a movie? Or someone coding? Do you ever wonder how folks write a different language to communicate with computers? I mean how does that even work? There's website builders like Wix and Shopify but like what's happening under the hood? Well... At Django Girls, they have the perfect opportunity for you to learn!

7

4 Comments

First pass at an agent skill that helps agents contribute back to Drupal (without overwhelming maintainers): https://lnkd.in/gvdE8VqC. Background: I noticed that when working with coding agents, they’d often roll a local only patch to solve an issue they found - and while it would work - the process ended there. This skill instructs the agent to: - Search the Drupal issue queue for similar issues prior to developing a patch. - If it finds an issue, it helps test the recommendations or existing patches and reports back. - If not, the agent will create the patch, test it locally, and encourage the human user to submit it. Crucially, at no point will it submit a patch on its own. Still a lot of work to go, but I'd love to hear if it helps (for both contributors and maintainers)

17

Some people think metadata is "industry stuff." Nah. Metadata is "getting paid stuff." It's "knowing what you own stuff." It's "responding to opportunities stuff." The industry didn't invent metadata. They just take it seriously. You should too.

4

Tried something new with this month’s WRITER developer newsletter! I dove into how context engineering shaped our approach to building WRITER MCP Gateway, a control plane that sits between WRITER agents and external MCP servers, and how those same principles apply to tool calling approaches like RAG-MCP. Would love to hear what you thought of this month’s issue! If you missed it, you can find the sign-up link at the bottom of the WRITER engineering blog and I’ll be sharing a deeper dive there soon :) 🔗 https://lnkd.in/gm72k4eC

8

2 Comments

Why neutrality in #SoftFurnishings is harder than boldness (And why I’ll always choose it.) 1️⃣ Neutral isn’t minimal. People often confuse neutral palettes with playing safe. But designing a neutral space that feels complete takes far more restraint than going bold. It’s easy to fill a room with colours and patterns. Much harder to know when to stop. 2️⃣ It takes discipline to edit. When clients see an empty corner, their first instinct is: “Let’s add something.” My job is to pause, feel the energy, and ask, “Does the space need more? Or are we avoiding stillness?” #HealingSpaces often breathe through the things we remove. 3️⃣ Quiet choices hold deeper power. A soft textured rug or a muted sheer aren’t background details. They are anchors. They guide the way you feel, move, and think. 4️⃣ Neutrality requires deep listening. Not just to the client, but also to the space. The walls. The light. The emotional weight of what already exists. If you listen carefully, you’ll often realise: The space always says something. You just need to honour it. 5️⃣ Bold is easy, but balance is tricky. Using statement colours is easy.  It takes a calibrated mind to design a space that feels peaceful and subtle. That is what makes neutral spaces feel timeless. Not boring, but deeply human. 💬 Have you ever walked into a room and felt instantly calm, without knowing why? *********** 🏡 Follow Darsha Manek for more on Soft Furnishings. *********** #LuxuryDesign #Entrepreneurship #EnergeticAlignment #Fabrics #Trends #HealingSpaces #SoftFurnishing

13