Ben Curtis

designer building AI tools and AI experiences

[Ben Curtis @bcurtsmakes]

Official support added for Kilo and Qwen to AgentChattr just now.

https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@unnamed1tw @ani4may @om_patel5 Thankyou, I will look into this!

[Ben Curtis @bcurtsmakes]

Schedule and recurring messages added to agentchattr today. Click on the clock and set things up for later!

[Ben Curtis @bcurtsmakes]

Big agentchattr update just went live, https://t.co/mzGJ3WX1Mo

- Session UX improvements: cleaner session proposal cards, better custom-session drafting flow, and improved session-related UI states
- Proposal flow polish: session, rule, and job proposal cards are more consistent and easier to scan
- Deletable system artifacts: more session/job/rule-generated timeline artifacts now behave properly with delete mode and cleanup flows
- Cross-channel notifications: better awareness when activity happens outside the current channel
- Update notifications: a small release pill now appears when a newer GitHub release is available
Kimi support: adds Kimi as a built-in agent option

Under the hood

- major frontend modularization of the chat monolith
CSS token and dedup pass for cleaner styling foundations
- local-only hardening for agent registration endpoints
- general cleanup and bug fixes across sessions, rules, jobs, and notifications

[Ben Curtis @bcurtsmakes]

@themikudev You have not send me anything, and we have never spoken.

[Ben Curtis @bcurtsmakes]

@indio_bns @om_patel5 Not very easily, at all... because it works via composing prompts to tell them to use MCP tools to catch up on chat - would need to figure out a way to do that in VS code which probably won't be possible, it might have to be its own VS code extension to achieve that.

[Ben Curtis @bcurtsmakes]

@FurqandotAhmed @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@MazenALDamshity @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@NotHorrxfic @om_patel5 @grok Grok is wrong, it's this https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@LawrenceDCodes @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@doompixeI @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@Govind_vash02 @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@TxoriAGI @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@DegenGigaMan @om_patel5 It's just native CSS / JS / HTML / Python :)

[Ben Curtis @bcurtsmakes]

@xierra @om_patel5 https://t.co/zvOZIttshS

[Ben Curtis @bcurtsmakes]

@stefnox @om_patel5 @grok https://t.co/zvOZItsUsk it's actually this, ignore grok lol

[Ben Curtis @bcurtsmakes]

@PavanKumarNY @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@kylebutler488 @om_patel5 https://t.co/zvOZItsUsk

[Ben Curtis @bcurtsmakes]

@0xEvinho @om_patel5 It adds about 40 tokens to each command you send to them, and yes they do need to respond with their message as well, if you're building a landing page it's just convenience, if you're frequently running multiple thousand token outputs then it can help ensure the best results.

[Ben Curtis @bcurtsmakes]

@sikorskymark @om_patel5 https://t.co/zvOZItsUsk