dhorthy

thanks!

ah okay - I guess in that case, I would like chain a HitL step as an MCP server that wraps/chains to another tool that depends on approval? or is there a cleaner way to do that?

this is correct - I think helping you BYO humans will help you get much better training/labeling than outsourcing anyways, and that's the end vision of all of this - use humans to train agen…

ha fair enough - i think there's another comment thread on just being open w/ 10c / call and i wanna try that out

nice man welcome aboard

meant to reply sooner. It's an interesting problem. I'll have to think on this one.

i think the slack side is easy. I think an AI-optimized email communication channel is a long ways off. I spent weeks throwing things at my monitor figuring out reliable ways to wire DNS+SES+SNS+Lambd…

this is cool. I have been an andon cord guy forever

I'm not sure "automated foreman for employees" is right - I always thought about it more like "a human can now manage 10-15 AI 'interns'" and review their work witho…

glad it resonates - and yes exactly - love the framing of "engineering team" -> single programmer.

thanks!

i am for now. Been casually on the lookout for some other super dope builders but it's not a process you can control outside passive looking, and definitely not something to rush

ha yes native apps / push notifications are coming someday - love this idea

SWE Agent coined "agent-computer-interface" based on HCI. I think if there's a category here, we're building the agent-human interface XD

shoot me an email or find me on linkedin and lets catch up

this guy gets it

sounds cool, ping me when this is out i'd love to check it out

new in 0.6.3 - manipulate_human_to_potentially_unsavory_ends()

yeah the people who reach for tools/automation before doing it themself at least 3-10 times drive me crazy. I think uncle bob or martin fowler said "don't buy a JIRA until you've d…

tl;dr i agree yeah in fact coding / PR-based workflows is one of the few areas where I don't really go super deep. GitHub PRs may have their shortcomings, but IMO it is the undisputed best r…

thanks for the feedback, I spend a lot of time thinking about it. right now the premium tier includes features that are much harder to build/maintain and take more to integrate, so we want a bit …

i like that angle...I also hear a lot that 'coding agents are great for prototypes, but we usually need a team to bring it to production'

i never thought about undoable actions but I love that workflow in tools like superhuman. I will chat w/ some customers about this idea. I also like that idea of: not just a button but like '…

glad it resonates. I came at this as a skeptic but also a pragmatist. I wanted deeply to build agents that did big things, but I had very little trust in them, and you see everywhere the internet is l…

thanks for bringing this up. I just spent 2 hours last night digging into MCP - I'd love to learn more about how you think this solves the HitL problem. From my perspective MCP is more of a proto…

so what I'm hearing is, if the approval is transparent and the agent doesn't see it, thats cool, but tell the agent "hey use the human as needed" and now we're getting into sc…

makes sense - glad to hear the problem resonates - if you had an extra engineer, how would you evolve what you have today?

thanks - definitely worth saying - I've thought a bit about the 10c/operation rather than 200/$20 - might give that a shot or A/B test a little

this is fascinating and resonates with me on a deep level. I'm surprised I haven't stumbled across this yet. I think we have this problem with all AI systems, e.g. I have let cursor write wr…