Trish

Designing how humans and AI agents work together. Agentic Experience (AX) @Microsoft Foundry. Writing about it at Code:Words. Views are mine, typos are free.

[Thariq @trq212]

We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. https://t.co/6DZwSrZjE9

[John Maeda @johnmaeda]

Last kitchen call for the "Mr. Maeda's Cozy AI Kitchen" show. Thanks to everyone who came to cook with us for the past two *unusual* years! Stay cozy! —JM

[Ryo Lu @ryolu_]

the crazy thing about Cursor mobile
is @rikcreation coded most of the real thing with Cursor, as a “designer”

titles don’t mean shit.
you can just build.

[ASHA @asha_shar]

Xbox or XBOX?

[Microsoft Dev Docs @docsmsft]

Generating with AI is easy. Keeping it on track is the hard part. @johnmaeda's final tip from #SXSW explains why every workflow needs a “standing beacon”: clear evaluation, guardrails, and a standard to measure outputs against.

#CozyAIKitchen: https://t.co/syildoKDwI

[Microsoft Dev Docs @docsmsft]

Here's @johnmaeda's second tip from #SXSW: use a tuned harness to shape how models behave, from prompting to tool calling. Tools like GitHub Copilot CLI make it a lot easier to go from “interesting” to actually useful.

#GitHubCopilot SDK: https://t.co/C7LTz0amXc

[John Maeda @johnmaeda]

From UX to AX: #DesignInTech Part 2

Taste is non-deterministic. It’s human. It’s fickle. Not random. Emergent. https://t.co/qT7H5cUapG

[Ryo Lu @ryolu_]

when software had a soul

there was a moment around 2005 when using a Mac felt like touching something alive.

the dock bounced. the genie effect swooped. exposé scattered your windows like cards on a table. none of it was strictly necessary. all of it felt like someone cared – not about metrics, but about the feeling of using a machine.

software back then had texture. it had a philosophy. you could feel the person behind it. someone made a decision to make that icon beautiful, to animate that transition just so, to write that error message with a little warmth. apps had personalities. some were weird. some were over-designed in ways that would make a modern PM flinch. but they were alive.

the web was the same. personal sites were genuinely personal. blogs felt like letters. forums had regulars. you knew who made what. the internet had neighborhoods, and each one felt different.

nothing was optimized for scale. things were made by people who loved what they were making.

somewhere along the way, we traded all of that for growth.

A/B tests flattened the edges. design systems standardized the personality out. everything got faster, smoother, more consistent – and somehow less interesting. the quirks were removed because they didn't test well. the warmth got cut because it wasn't measurable. we optimized our way into a world of things that work perfectly and feel like nothing.
now every app looks the same. every interface follows the same patterns. every product speaks in the same calm, frictionless voice, siloed in their own little islands. the humanity got rounded off.

and then came AI agents. and the speed got inhuman.

now you can generate an entire product in an afternoon. ship a feature before lunch. spin up ten variations before anyone's had their coffee. the gap from idea to code is basically zero.

which sounds incredible. and it is. but there's a catch.

when making things are too easy, the slop comes for free too. mediocre things don't look obviously bad – they look fine. they work. they ship. they pass review. and now there are infinite of them. the internet is filling up with software that functions but means nothing. interfaces that are correct but feel dead. products made by agents, reviewed by no one, shipped into the void.

this is the thing that keeps me up at night. not that AI will replace people who care. but that it will drown them out.

here's what I still believe: the best things are made by people who couldn't help themselves. someone who lost sleep over an icon. who rewrote the same line of copy twelve times. who added an animation nobody asked for because it made the thing feel right. that obsession – that's not inefficiency. that's the whole point.

AI doesn't make that irrelevant. it actually makes it rarer and more valuable. taste is not a markdown skill. caring is not a parameter. the weird, specific, "soul" thing you put into something – that can't be programmed into existence.

the path forward isn't to make more slop faster. it's to finally give people with real vision the tools to make the thing they always imagined but couldn't build alone. the designer who had the idea but couldn't code. the kid who saw something nobody else saw. the person who cared too much about something most people wouldn't notice.

if we get this right, we don't get a faster factory. we get a renaissance. more strange, personal, opinionated software made by teams of people who care and mean it.

that's still possible. but only if the people who care get the space and tools to actually express themselves – and don't just hand the wheel to the agent and walk away.

[Burke Holland @burkeholland]

Wow

[claire vo 🖤 @clairevo]

I’m also against giving my AI agents titles.

Ineffective. Trite.

Instead I give them lore. Little vendettas against Cathy in marketing. Adolescent love, lost. That time they really disappointed dad. A chip on their shoulder the size of 7th grade.

Then: an AdWords account.

[Trish @FrigidNobility]

Don't miss the latest Design in Tech Report from @johnmaeda!

[John Maeda @johnmaeda]

#DesignInTech Report 2026 https://t.co/lxyTXh5Y6e

[ASHA @asha_shar]

I agree. Faking would be a terrible idea and wouldn’t work. I also didn't expect my gamertag to blowup and the reality is more boring. I created it recently to learn and understand this world. I’ve played with my family, and it’s a shared home account across devices (which you can see in the range of games /achievements). Fixed that this weekend and everyone is only playing on their own GTs.

But I get where this is coming from. I don’t pretend to be the best gamer and even though I’m playing, that’s still not my goal. My focus is to make Xbox the best place to play, return to our roots, ship great things, and become stronger for the future.

And yes, I’m writing my own posts :)

[Trish @FrigidNobility]

Thanks and works cited belong to @JayaGup10 and @ashugarg for their article inspo on @FoundationCap and @hangfei_ for the article inspo on @googledevs

[Trish @FrigidNobility]

Your multi-agent system just recreated every org dysfunction you've ever hated.
Same agents. Same info. No role clarity = total deadlock. https://t.co/a6gz1Od8EP

[Trish @FrigidNobility]

"ai doesn't replace systems thinking – it amplifies the cost of not doing it."

[Ryo Lu @ryolu_]

software is still about thinking

software has always been about taking ambiguous human needs and crystallizing them into precise, interlocking systems. the craft is in the breakdown: which abstractions to create, where boundaries should live, how pieces communicate.

coding with ai today creates a new trap: the illusion of speed without structure. you can generate code fast, but without clear system architecture – the real boundaries, the actual invariants, the core abstractions – you end up with a pile that works until it doesn't. it's slop because there's no coherent mental model underneath.

ai doesn't replace systems thinking – it amplifies the cost of not doing it. if you don't know what you want structurally, ai fills gaps with whatever pattern it's seen most. you get generic solutions to specific problems. coupled code where you needed clean boundaries. three different ways of doing the same thing because you never specified the one way.

as Cursor handles longer tasks, the gap between "vaguely right direction" and "precisely understood system" compounds exponentially. when agents execute 100 steps instead of 10, your role becomes more important, not less.

the skill shifts from "writing every line" to "holding the system in your head and communicating its essence":

- define boundaries – what are the core abstractions? what should this component know? where does state live?
- specify invariants – what must always be true? what are the constants and defaults that make the system work?
- guide decomposition – how should this break down? what's the natural structure? what's stable vs likely to change?
- maintain coherence – as ai generates more code, you ensure it fits the mental model, follows patterns, respects boundaries.

this is what great architects and designers do: they don't write every line, but they hold the system design and guide toward coherence. agents are just very fast, very literal team members.

the danger is skipping the thinking because ai makes it feel optional. people prompt their way into codebases they don't understand. can't debug because they never designed it. can't extend because there's no structure, just accumulated features.

people who think deeply about systems can now move 100x faster. you spend time on the hard problem – understanding what you're building and why – and ai handles mechanical translation. you're not bogged down in syntax, so you stay in the architectural layer longer.

the future isn't "ai replaces programmers" or "everyone can code now." it's "people who think clearly about systems build incredibly fast, and people who don't generate slop at scale."

the skill becomes: holding complexity, breaking it down cleanly, communicating structure precisely. less syntax, more systems. less implementation, more architecture. less writing code, more designing coherence.

humans are great at seeing patterns, understanding tradeoffs, making judgment calls about how things should fit together.

ai can't save you from unclear thinking – it just makes unclear thinking run faster.

[Visual Studio Code @code]

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it!

Here’s what’s new in the latest @code release:

🗂️ Unified agent sessions workspace for local, background, and cloud agents
💻 Claude and Codex support for local and cloud agents
🔀 Parallel subagents
🌐 Integrated browser
And more...

[Dona Sarkar @donasarkar]

So everyone vaguely knows how to BUILD an Agent but how do you get out of your cute sandbox experiment thing and actually INTO production.

🤷🏽‍♀️How do you deploy an Agent
👮🏽How do you govern and monitor the Agent
😭How do you FIRE an Agent?

All will be revealed to all you current and future AgentBosses by @meetdux at #MSIgnite.

Title: Protect your data with confidence in the age of autonomous agents

When: Today, Wednesday
1:30-2 pm

Where: Moscone South
Theatre A

[Trish @FrigidNobility]

Come grab a sticker and try your luck with the claw machine to win an Xbox! #msignite

[Trish @FrigidNobility]

@MSWindowsITPro I need a Clippy stuffy!

[Microsoft Developer BR @msdevbr]

Dê as boas-vindas ao @ClaudeAI no Azure 👋 Hoje anunciamos no #MSIgnite 2025 que os modelos Claude Sonnet 4.5, Haiku 4.5 e Opus 4.1 estão disponíveis no Microsoft Foundry.