Jess T

founding designer @societies_ai.
prev: maths @ oxford, swe @ cisco, ux @ strawberry. :))

[Jess T @jesstoudic]

big day today: we launched Radiant!

since joining @societies_ai, i've been designing and building our new simulation platform.

it lets organisations test their most consequential decisions.

a super fun first few months!

[Artificial Societies @societies_ai]

Introducing Radiant, our flagship simulation platform. Built to inform the world’s most pivotal decisions.

For too long, decisions had to be made blindly: it's too hard to research thought-leaders at scale, get insights in a crisis, and some decisions are simply too sensitive to expose to participants.

How to steady a trillion-dollar market cap during geopolitical crisis?

How to position a $100B+ AI bet to regulators and enterprise buyers?

How to de-risk a product launch, without revealing the strategy?

Radiant is built for these critical decisions. It lets you run interviews, focus groups, and survey experiments to simulate decisions before they’re made, powered by Artificial Societies’ state-of-the-art Large Decisions Model and Network Dynamics Engine.

Some of the world’s most strategic organisations already use Radiant for their most critical decisions. And now, we’re making Radiant available for general enterprise access.

Explore Radiant. Link below.

[Artificial Societies @societies_ai]

Introducing Rothko, a foundation model of human behaviour designed from the ground up to simulate the world’s most consequential decisions.

Rothko is the result of over three years of frontier research at the intersection of behavioural science and machine learning.

We’re only just starting to uncover the model’s value across domains ranging from market research to AI safety and swarm alignment.

[Jess T @jesstoudic]

another super inspiring evening at @meetgranola for den10 last night!

loved hearing some of the thinking behind @mappletons' speculative design prototypes.

and great deep dives into @paper’s colours from @vladmoroz, and design tools from @alex_barashkov!

thanks to everyone for making it such a lovely event (as always) :))

[Jess T @jesstoudic]

@seb_thunman thanks Seb! :))

[Jess T @jesstoudic]

big day today: we launched Radiant!

since joining @societies_ai, i've been designing and building our new simulation platform.

it lets organisations test their most consequential decisions.

a super fun first few months!

[Artificial Societies @societies_ai]

Introducing Radiant, our flagship simulation platform. Built to inform the world’s most pivotal decisions.

For too long, decisions had to be made blindly: it's too hard to research thought-leaders at scale, get insights in a crisis, and some decisions are simply too sensitive to expose to participants.

How to steady a trillion-dollar market cap during geopolitical crisis?

How to position a $100B+ AI bet to regulators and enterprise buyers?

How to de-risk a product launch, without revealing the strategy?

Radiant is built for these critical decisions. It lets you run interviews, focus groups, and survey experiments to simulate decisions before they’re made, powered by Artificial Societies’ state-of-the-art Large Decisions Model and Network Dynamics Engine.

Some of the world’s most strategic organisations already use Radiant for their most critical decisions. And now, we’re making Radiant available for general enterprise access.

Explore Radiant. Link below.

[Jess T @jesstoudic]

most conversational ai interfaces are missing a feature: bookmarks.

when the conversation is the artefact, there’s no way to mark things for later.

artefacts get a side panel. bookmarks should too.

anything worth keeping should get held onto, not lost in a sea of conversation.

[Jess T @jesstoudic]

i analysed the design of claude design.

how it handles:
- the articulation barrier
- the ai latency problem
- chat as an observability and control surface

here: https://t.co/9tLvNNPYhT

[Jess T @jesstoudic]

anthropic gave @claudeai a new way to ask you questions.

here's ~2,000 words on what works, what doesn't, and what it points toward.

https://t.co/Dbz4YJtShR

[Jess T @jesstoudic]

clarifying intent with a block of questions is overwhelming.

so, I designed a new way: questions one at a time, in a contained phase within the conversation.

@AnthropicAI has since addressed this in @claudeai. more on that next.

[Jess T @jesstoudic]

- guidance spans the full interaction.
- you can type through the submenu hierarchy.
- multi-word items can be searched naturally.

have a play here: https://t.co/WeZ5awTXUN

[Jess T @jesstoudic]

@claudeai's slash commands almost got it right.

discoverability (a prompt hint) is excellent, and 'type to filter' begins to guide you nicely.

but then guidance stops. and submenus aren't fully navigable by typing.

so, i redesigned it.

(link & more in comments)

[Jess T @jesstoudic]

i have landed on x.

here to share about the design & ux of ai products.

also here to follow peeps doing the same. if that’s you, say hi. :))

[Oxford Mathematics @OxUniMaths]

Before she left town to hunker down, as have many students across the world, @OxUniMaths 3rd-Year Jess Toudic shared the things on her mind; things that will be with us long in to the future - our brains, our skies & #rollerskating (at safe-distance of course).

#WhatsOnYourMind