(1) right now, i think this is a better tool for the tech lead / senior engineer. they can enter a loop like:
start brainstorming with their agent -> agent writes code -> agent writes Whiteboard session (connected to the underlying code) for them to iterate on.
(eliminates the middle plan mode phase)
(2) i don't think every piece of work fits in that way, so we're working on a "scratchpad" mode your agent can use for planning via versioned artifacts for architecture + behavioral specifications. Then it can update that plan when the implementation is complete! when this feature rolls out I think an "architect" would be using that feature more in collaboration with an engineer.
(the boundary b/w architect and engineer does seem a bit fuzzy to me, esp. these days, so hopefully we share a similar mental model)
I looked up Luma and some events near me have 100s of people attending. Is it fake numbers, pulling them from somewhere else or is Luma very popular and I've just never heard of it?
1. Luma is quite popular with some communities, and has been for a while.
2. Disoverability still kind of sucks on luma, both the platform itself and between events even on the platform, so not really surprising.
3. Online rsvp's almost always exceed actual attendees by a lot if you aren't charging money or otherwise penalizing people for no-showing... it's typical to see 30-50% attendance.
"My job is to figure out the right context and guardrails so that when you prompt “Build me a dashboard,” the result actually looks like your existing product."
What is the challenge here? Yes if you don't guide an LLM it will come up with it's own design.. but you can just tell it to use your brand and assets and it works pretty well
Define better. Faster to literally write the code - LLM. Deeper understanding of how it works - write yourself. Less skill atrophy - write yourself. More fun - write yourself. You can argue all these points and they’ll be different for everyone, but my feeling is that everything I listed in the original comment are clear additives to my process/learning.
reply