Shawn Simister
@narphorium.com
Building AI powered tools to augment human creativity and problem solving in San Francisco. Previously @GitHub Copilot, @Google, 🇨🇦
narphorium.com
narphorium.com
Pinned
Structured Prompting | Shawn Simister
Organizing Complexity in the Age of Language Models
narphorium.com
Recent developments like subagents and agent planning tools have got me thinking: what are the right abstractions for natural language programming?
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
I’m seeing confusion about Claude Skills and why you need them. It sort of feels like Anthropic is building tools that fix problems many people won’t know that they have until next year
www.anthropic.com/engineering/...
www.anthropic.com/engineering/...
November 10, 2025 at 1:26 AM
I’m seeing confusion about Claude Skills and why you need them. It sort of feels like Anthropic is building tools that fix problems many people won’t know that they have until next year
www.anthropic.com/engineering/...
www.anthropic.com/engineering/...
I’m seeing a lot of AI coding tools trying to figure out multi-agent UX. To me, delegating feels like the least interesting part of the problem…
October 30, 2025 at 2:28 AM
I’m seeing a lot of AI coding tools trying to figure out multi-agent UX. To me, delegating feels like the least interesting part of the problem…
Reposted by Shawn Simister
Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost.
Paper, code & demos: gabegrand.github.io/battleship
Here's what we learned about building rational information-seeking agents... 🧵🔽
Paper, code & demos: gabegrand.github.io/battleship
Here's what we learned about building rational information-seeking agents... 🧵🔽
October 27, 2025 at 7:17 PM
Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost.
Paper, code & demos: gabegrand.github.io/battleship
Here's what we learned about building rational information-seeking agents... 🧵🔽
Paper, code & demos: gabegrand.github.io/battleship
Here's what we learned about building rational information-seeking agents... 🧵🔽
Reposted by Shawn Simister
More detail including a code sample for trivially implementing linking in an agent on my blog: mbleigh.dev/posts/co...
Links were powerful enough to build the entire web...I think they'll be critical for building the context for agents as well.
Links were powerful enough to build the entire web...I think they'll be critical for building the context for agents as well.
Context engineering is sleeping on the humble hyperlink
The dream of hypermedia can come to fruition in a world where clients can not only parse, but navigate with intent.
mbleigh.dev
October 23, 2025 at 1:39 PM
More detail including a code sample for trivially implementing linking in an agent on my blog: mbleigh.dev/posts/co...
Links were powerful enough to build the entire web...I think they'll be critical for building the context for agents as well.
Links were powerful enough to build the entire web...I think they'll be critical for building the context for agents as well.
Reposted by Shawn Simister
Discerning what is at the core, and how to communicate it with others, has taken years. This might be the closest I've come so far.
Part 2 of The Interfaces With Which We Think is out now...
Start at the intro: alexanderobenauer.com/think/
Start at Part 2: alexanderobenauer.com/think/2/
Part 2 of The Interfaces With Which We Think is out now...
Start at the intro: alexanderobenauer.com/think/
Start at Part 2: alexanderobenauer.com/think/2/
The Interfaces With Which We Think
The concepts in modern operating systems — apps, windows, desktops, notifications, and so on — have so permeated our understanding of personal computing, it’s hard to imagine anything else, let alone ...
alexanderobenauer.com
October 23, 2025 at 2:26 PM
Discerning what is at the core, and how to communicate it with others, has taken years. This might be the closest I've come so far.
Part 2 of The Interfaces With Which We Think is out now...
Start at the intro: alexanderobenauer.com/think/
Start at Part 2: alexanderobenauer.com/think/2/
Part 2 of The Interfaces With Which We Think is out now...
Start at the intro: alexanderobenauer.com/think/
Start at Part 2: alexanderobenauer.com/think/2/
Recent developments like subagents and agent planning tools have got me thinking: what are the right abstractions for natural language programming?
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
Structured Prompting | Shawn Simister
Organizing Complexity in the Age of Language Models
narphorium.com
October 23, 2025 at 2:38 AM
Recent developments like subagents and agent planning tools have got me thinking: what are the right abstractions for natural language programming?
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
I wrote about how we're rediscovering structured programming but this time for prompts instead of code.
Reposted by Shawn Simister
New post 🎉
Going back to my roots on writing about the inner workings of things, a breakdown of key-value databases and how you might make one from scratch:
nan.fyi/database
Going back to my roots on writing about the inner workings of things, a breakdown of key-value databases and how you might make one from scratch:
nan.fyi/database
October 21, 2025 at 3:00 PM
New post 🎉
Going back to my roots on writing about the inner workings of things, a breakdown of key-value databases and how you might make one from scratch:
nan.fyi/database
Going back to my roots on writing about the inner workings of things, a breakdown of key-value databases and how you might make one from scratch:
nan.fyi/database
Reposted by Shawn Simister
An AI coding approach I've liked using, which I first used on this project:
Vibe code the first version. Investigate the code for its shape, complexities, needs, failure points.
Then scrap all that and engineer a new version.
Vibe code the first version. Investigate the code for its shape, complexities, needs, failure points.
Then scrap all that and engineer a new version.
This article is now public! Link in reply.
I recreated Jef Raskin's 1987 'Canon Cat' user environment and observed myself as I lived in it for a week.
Implementation details, surprises, and more in the essay.
(Why touch grass when you can read 3.2k words on user environments?)
I recreated Jef Raskin's 1987 'Canon Cat' user environment and observed myself as I lived in it for a week.
Implementation details, surprises, and more in the essay.
(Why touch grass when you can read 3.2k words on user environments?)
October 20, 2025 at 3:01 PM
An AI coding approach I've liked using, which I first used on this project:
Vibe code the first version. Investigate the code for its shape, complexities, needs, failure points.
Then scrap all that and engineer a new version.
Vibe code the first version. Investigate the code for its shape, complexities, needs, failure points.
Then scrap all that and engineer a new version.
Great analysis of spec-driven development tools and recommendations for how to make them more effective: more variety of workflows, smaller iteration cycles, and better spec review tools
I tried to make sense of "spec-driven development" by looking at 3 tools: Amazon's Kiro, GitHub's spec-kit, and the Tessl Framework
martinfowler.com/articles/exp...
martinfowler.com/articles/exp...
Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl
Notes from my Thoughtworks colleagues on AI-assisted software delivery
martinfowler.com
October 15, 2025 at 5:41 PM
Great analysis of spec-driven development tools and recommendations for how to make them more effective: more variety of workflows, smaller iteration cycles, and better spec review tools
Reposted by Shawn Simister
Some thoughts on LLMs, Autopilot, and VibeCoding rahulpandita.me/blog/2025-10...
October 13, 2025 at 2:30 AM
Some thoughts on LLMs, Autopilot, and VibeCoding rahulpandita.me/blog/2025-10...
These new Windsurf codemaps look a lot like Project Copernicus from @kcieslak.io
githubnext.com/projects/cop...
githubnext.com/projects/cop...
October 13, 2025 at 1:45 AM
These new Windsurf codemaps look a lot like Project Copernicus from @kcieslak.io
githubnext.com/projects/cop...
githubnext.com/projects/cop...
Reposted by Shawn Simister
6/
That said, HRM and TRM are fascinating proof‑of‑concepts that show what’s possible with relatively small and efficient architectures. I'm still curious what the real‑world use case will look like. Maybe they could serve as reasoning or planning modules within a larger tool‑calling system.
That said, HRM and TRM are fascinating proof‑of‑concepts that show what’s possible with relatively small and efficient architectures. I'm still curious what the real‑world use case will look like. Maybe they could serve as reasoning or planning modules within a larger tool‑calling system.
October 9, 2025 at 4:23 PM
6/
That said, HRM and TRM are fascinating proof‑of‑concepts that show what’s possible with relatively small and efficient architectures. I'm still curious what the real‑world use case will look like. Maybe they could serve as reasoning or planning modules within a larger tool‑calling system.
That said, HRM and TRM are fascinating proof‑of‑concepts that show what’s possible with relatively small and efficient architectures. I'm still curious what the real‑world use case will look like. Maybe they could serve as reasoning or planning modules within a larger tool‑calling system.
Reposted by Shawn Simister
We have 🤖 AI notetakers in meetings but continue to silo know-how every time we close terminals. Not just the how but also the why and what.
Sign up for beta access to visr.sh: it's like as if Granola AI and #tmux had a kid.
Sign up for beta access to visr.sh: it's like as if Granola AI and #tmux had a kid.
Visr: The Agentic Terminal Notepad Integral to Your Docs
The Agentic Terminal Notepad Integral to Your Docs
visr.sh
October 7, 2025 at 5:05 PM
Fun panel discussion on spec-based development with @kiro.dev team.
Especially interested in upcoming features to ground the specs to verify that the work is done correctly
Especially interested in upcoming features to ground the specs to verify that the work is done correctly
October 7, 2025 at 3:45 AM
Fun panel discussion on spec-based development with @kiro.dev team.
Especially interested in upcoming features to ground the specs to verify that the work is done correctly
Especially interested in upcoming features to ground the specs to verify that the work is done correctly
Reposted by Shawn Simister
What, if anything, do LLMs change about interface design?
Interfaces are languages
Is there a universal translation?
shimmeringvoid.leaflet.pub
October 4, 2025 at 2:56 AM
What, if anything, do LLMs change about interface design?
As autonomous agents tackle larger tasks over longer trajectories, we’ll need tools like Trailblazer to quickly walk us through how problems were solved so verification doesn’t take as long as solving it ourselve
Today at #uist2025 my student Jeffrey Tao presented our new paper "Answering Developer Questions with Annotated Agent-Discovered Program Traces" While it is too late to catch the talk, you can still find Jeff! I'm happy to make connections over email.
Paper: andrewhead.info/assets/pdf/t...
Paper: andrewhead.info/assets/pdf/t...
October 3, 2025 at 11:33 PM
As autonomous agents tackle larger tasks over longer trajectories, we’ll need tools like Trailblazer to quickly walk us through how problems were solved so verification doesn’t take as long as solving it ourselve
Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
arxiv.org/abs/2509.13351
arxiv.org/abs/2509.13351
September 27, 2025 at 5:07 AM
Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
arxiv.org/abs/2509.13351
arxiv.org/abs/2509.13351
Reposted by Shawn Simister
My ideas are faster than my fingers so I've did some Figma prototyping and video editing to talk about some of my new ideas before they are actual coded reality
youtu.be/2DRWUgK-RdA
youtu.be/2DRWUgK-RdA
hirba - Legible live programming through rich in-context representations
YouTube video by watware
www.youtube.com
September 17, 2025 at 1:27 PM
My ideas are faster than my fingers so I've did some Figma prototyping and video editing to talk about some of my new ideas before they are actual coded reality
youtu.be/2DRWUgK-RdA
youtu.be/2DRWUgK-RdA
Reposted by Shawn Simister
Want to visualize the response format constraints on the LLM when working in a Jupyter notebook?
Then you might be interested in my new project `litelines`.
Litelines lets you visualize the selected path by the LLM.
It supports a Pydantic schema as a response format, as well as regular expressions.
Then you might be interested in my new project `litelines`.
Litelines lets you visualize the selected path by the LLM.
It supports a Pydantic schema as a response format, as well as regular expressions.
September 16, 2025 at 7:20 AM
Want to visualize the response format constraints on the LLM when working in a Jupyter notebook?
Then you might be interested in my new project `litelines`.
Litelines lets you visualize the selected path by the LLM.
It supports a Pydantic schema as a response format, as well as regular expressions.
Then you might be interested in my new project `litelines`.
Litelines lets you visualize the selected path by the LLM.
It supports a Pydantic schema as a response format, as well as regular expressions.
Sometimes you need to build the wrong thing to get in the right headspace to build the right thing
September 15, 2025 at 2:33 AM
Sometimes you need to build the wrong thing to get in the right headspace to build the right thing
Reposted by Shawn Simister
"Generative, Malleable, and Personal User Interfaces" by Haijun Xia (2025)
www.youtube.com/watch?v=MbWg...
www.youtube.com/watch?v=MbWg...
www.youtube.com
March 1, 2025 at 9:48 PM
"Generative, Malleable, and Personal User Interfaces" by Haijun Xia (2025)
www.youtube.com/watch?v=MbWg...
www.youtube.com/watch?v=MbWg...
Reposted by Shawn Simister
Advanced context continuity with Projects and the Claude Pruner bookmarklet whtwnd.com/austegard.co...
Managing Context Continuity in Claude Projects | Oskar
Managing Context Continuity in Claude Projects
The Problem
You're deep in a productive Claude conversation. You've built up complex context, made breakthroughs, developed solutions. Then you hit the...
whtwnd.com
September 10, 2025 at 3:11 PM
Advanced context continuity with Projects and the Claude Pruner bookmarklet whtwnd.com/austegard.co...
Reposted by Shawn Simister
Need to rethink my gesture math and try some polarizing film, but basics of panning the canvas are in there.
September 9, 2025 at 8:33 PM
Need to rethink my gesture math and try some polarizing film, but basics of panning the canvas are in there.
Cursor limits me to 5 custom modes so I reserve those slots for coding-specific tasks and do all my broader design thinking in Claude Desktop instead. Interesting how small constraints in our tools quietly redirect our entire creative process.
September 6, 2025 at 1:32 AM
Cursor limits me to 5 custom modes so I reserve those slots for coding-specific tasks and do all my broader design thinking in Claude Desktop instead. Interesting how small constraints in our tools quietly redirect our entire creative process.
Reposted by Shawn Simister
Is there a name for the pattern where you try building the same thing (feature, project, ...) a bunch of times with different agents to get a sense of the implementation design space?
I usually run things at least 2 or 3 times until I "feel" what is the way I want it to be built.
I usually run things at least 2 or 3 times until I "feel" what is the way I want it to be built.
September 4, 2025 at 9:22 AM
Is there a name for the pattern where you try building the same thing (feature, project, ...) a bunch of times with different agents to get a sense of the implementation design space?
I usually run things at least 2 or 3 times until I "feel" what is the way I want it to be built.
I usually run things at least 2 or 3 times until I "feel" what is the way I want it to be built.