Back Send feedback to ilkka.kuivanen@me.com

AI roundup 2025-07

"AI roundup" is a curated collection of links I've gathered in the past related all aspects of AI, including LLMs, generative AI, etc.. I've added a brief summary (mostly for myself) next to the links so I have some memory what was the reason I collected the link in the first place. Consider these roundups as public bookmarks.

Common pitfalls when building generative AI applications

Summary:

https://huyenchip.com/2025/01/16/ai-engineering-pitfalls.html

Model Context Protocol Tutorial

Matt Pocock has a tutorial for MCP to get started.

https://www.aihero.dev/model-context-protocol-tutorial

Use Local Models With Vercel's AI SDK

Connect Vercel's AI SDK to model running locally, or anywhere.

https://www.aihero.dev/use-local-models-with-vercel-ai-sdk

Four AI Superpowers: Where AI Improves Products

When using AI consider its four "superpowers": content creation, summarization, basic data analysis, and perspective taking.

As you approach the use of AI in your product, don’t race to adopt a new technology for its own sake. Instead, you should aim to craft solutions that help users achieve their goals effectively and efficiently. The most innovative products of the future will not just be powered by AI, they will be designed with a deep understanding of human needs, with AI as one part of the equation. By combining clear intention, thoughtful design, and the right application of AI’s strengths, your team can create experiences that are not only functional but also transformative.

https://www.nngroup.com/articles/ai-superpowers/

Scope in Generative AI Features

When designing an AI feature, its scope (how broad or narrow its capabilities are) influences its usability. Our research shows that narrower AI features are (typically) easier for new users to understand and adopt.

https://www.nngroup.com/articles/scope-ai-features/

UX Leads Adoption of AI Chat

UX ranks among top fields adopting AI, mostly in writing, design, and coding tasks — though complex or human-centric UX activities remain largely AI-free.

https://www.nngroup.com/articles/ux-ai-adoption/

Prompt Suggestions

System-generated suggestions for AI prompts must be contextually relevant, personalized, and specific to the task and the user’s level of experience.

https://www.nngroup.com/articles/prompt-suggestions/

AI is a Prism, Not a Source

This one is a bit more philosophical.

While AI excels at both splitting ideas and bringing them back together, the final convergence—that last mile of refinement—remains distinctly human.

https://www.unknownarts.co/p/creativity-flows-like-light

Is Your Team Ready for AI-Enhanced Design?

Checklist for AI tool evaluation for design:

https://uxmag.com/articles/is-your-team-ready-for-ai-enhanced-design

The TypeScript Agent Framework

Typescript agent framework from the team behind Gatsby.

https://mastra.ai/

What I learned building an AI coding agent for a year

In context of building AI agents focus on: context management, accumulated "knowledge" files and reliability. Do periodic e2e evals and cut every feature that is not essential.

https://jamesgrugett.com/p/what-i-learned-building-an-ai-coding

Stop Building AI Agents

Agents are overhyped and overused. Most cases needs simpler patterns. Agents excel in human-in-the-loop scenarios. Build with observability and explicit control.

https://decodingml.substack.com/p/stop-building-ai-agents

Challenges in Rethinking User Interface Design for Age of AI

Prompt-driven interfaces can overwhelm users. Designers should ease input with templates and suggestions. Since AI outputs can be opaque or incorrect, it's vital to show reasoning, confidence levels, and sources to build trust. Transparency – like memory controls and feedback channels – helps users feel in control. AI tools must fit into workflows, while addressing bias and keeping responses fast with smart loading strategies.

https://www.uxness.in/2025/06/challenges-in-thinking-uiai.html

The rise of the AI-native employee

This one is a take for "AI native employee" – I am honestly a bit lost with the core of the idea.

No headcount asks. No project briefs. No handoffs. Just action.

Plain action, no strategy? It feels the rationale is centered around powerful AI tooling and implied efficiency benefits. It's like having access to Ferrari and thinking that would be good for setting up logistics operation to transport cargo.

Don't get me wrong, I am all about finding the essence and cutting of the fat out of any process, but there is a reason these activities exists. Removing them does not resolve needs behind them.

The comment section has interesting take:

Today I saw this at a YouTube video of young team working by slack with cursor and MCPs… for changes and updates of their site without even the engineer being there (good practice or not, they are moving and improving).

I think that doesn't sound like a good practice and not all "movement" is good movement.

https://www.elenaverna.com/p/the-rise-of-the-ai-native-employee

“Powered By AI” Is Not a Value Proposition

Achieving product-market fit and practicing user-centered design become difficult when AI is presented as a product’s main value.

We should think about how to deliver product value only after firmly establishing what that value is going to be. This is because the experience we want to create determines which technologies and form factors are most suitable.

https://www.nngroup.com/articles/powered-by-ai-is-not-a-value-proposition

Why most startups are building AI the wrong way

I'm not sure I'm fully on board with the sentiment, but the general idea is intriguing.

Don’t start by copying an existing product. Start by asking what should exist if you had no constraints. Then use AI to make that possible. The biggest winners are not adding AI to software. They are replacing software entirely.

https://www.productmarketfit.tech/p/why-most-startups-are-building-ai

Why I’m Betting on LLMs for UI Testing

For all the time we spend talking about GenAI generating code, we spend very little time talking about GenAI generating and executing tests. I believe they are so much better at the latter than the former.

https://carloarg02.medium.com/why-im-betting-on-llms-for-ui-testing-ac44e30e14c1

The AI Replaces Services Myth

VC incentive is to make every investor out there to believe that this is the biggest opportunity in history. You are either in or out. And you do not want to be the guy who missed AI.

https://aimode.substack.com/p/the-ai-replaces-services-myth

Introducing ChatGPT agent: bridging research and action

OpenAI has released an agent.

ChatGPT now thinks and acts, proactively choosing from a toolbox of agentic skills to complete tasks for you using its own computer.

https://openai.com/index/introducing-chatgpt-agent

All AI Models Might Be The Same

Language modeling is fundamentally compression. Better models compress data more effectively. This one goes academic.

https://blog.jxmo.io/p/there-is-only-one-model

From Memo to Movement: The non-obvious insights, tactics and workflows Shopify used to bring an ambitious memo to life

More prototypes are now part of Shopify's product-building process — specifically, increasing the ratio of prototyped attempts to build attempts. This enables one of Shopify’s principles, the “green path of product-building,” where the only way to figure out a problem is by trying many things. … “There are an infinite number of bad solutions and probably 10,000 good ones. Your job is to find the best solution among the 10,000. What you just showed me is the first one that worked vs. the best one. Why did you stop there?”

https://www.firstround.com/ai/shopify

Reflections on OpenAI

Interesting read about author's short journey at OpenAI.

https://calv.info/openai-reflections

I've been a designer for 20 years – here's the kind of AI we actually want

Designers think through the creative act of doing.They shape ideas by moving materials, trying options, and reacting to feedback in real-time. The act of creation is not just the moment you press “render” – it’s the whole messy, intuitive, back-and-forth path to getting there.

Practical AI must be built inside that act. Inside the creative flow, and enhance the flow with practical heavy lifting. It must live inside the creative loop — not stand off to the side with a clipboard.

That’s why the right metaphor isn’t, ‘’the future is a robot assistant.” It's an exoskeleton.Extra arms. Extra speed. Better reach. But still your hands. Still your craft. Still your vision is in control.

https://www.creativebloq.com/ai/ive-been-a-designer-for-20-years-heres-the-kind-of-ai-we-actually-want

The AI IDE for prototype to production

Decision fatigue kicks in with the overload of choices. How many of these things we need? When are we expected to try these things out AND do actual work AND to effectively incorporate AI into our workflows? Maybe the best strategy is to sit down during this phase and be in the early-majority, once the dust settles.

Kiro helps you do your best work by bringing structure to AI coding with spec-driven development.

https://kiro.dev