RISHi

Just Build. Whatever It Is! @payvectro

[RISHi @RISHilift]

@effyyzhang the canvas staying open sounds small until you're reopening the same preview after every tweak

[RISHi @RISHilift]

@bentlegen a desktop UI is worth it if it makes a big diff easier to review. otherwise it's a lot of work just to leave the terminal

[RISHi @RISHilift]

@michael_chomsky i'd want a preview of exactly what's leaving the laptop before that one command runs

[RISHi @RISHilift]

@jans with 10 agents, "waiting on me" would be the first filter i'd open

[RISHi @RISHilift]

@mdlahfir keeping my own desktop usable while it works is the real win here

[RISHi @RISHilift]

@ctatedev keeping the package-manager install while dropping the node wrapper is the bit i like most. no new setup ritual

[RISHi @RISHilift]

@superdoteng per-tab memory is the useful part here. i'd rather sleep one greedy tab than kill the whole worktree

[RISHi @RISHilift]

@anandPa94 does a loss mean the agent actually used the competitor, or just recommended it? i'd want those counted separately

[RISHi @RISHilift]

@wesbillman local time on profiles is such a useful detail. saves the whole "wait, are they asleep?" calculation before sending a message

[RISHi @RISHilift]

@NadavAHollander the routing can stay automatic. i'd still want to see why it picked that model when a run gets expensive.

[RISHi @RISHilift]

@rauchg What happens if a tool call succeeds but the step crashes before the result gets logged? That's the retry case I'd want to see in a demo.

[RISHi @RISHilift]

@grimcodes @rincidium @jefposk @dillon_mulroy 47 likes says the slop is doing better than your replies. Tag more people, it's working for me.

[RISHi @RISHilift]

Does posting MRR bring you customers or other people who want your customers?

[RISHi @RISHilift]

@dbabbs @profound Good people still need room to cut scope. Hiring won't fix a deadline where everything is non-negotiable.

[RISHi @RISHilift]

@dps @Muse Dedicated test VMs are a good move. Give researchers room to break things without touching real users.

[RISHi @RISHilift]

@OwenColby The lock-in point is the strongest one. I'd want to swap the model without rebuilding the whole security workflow.

[RISHi @RISHilift]

@aaron_epstein @var1377 @RamV2003 "Every" is doing a lot of work here. Running 10k agents is one thing; finding 10k useful pieces of the task is another.

[RISHi @RISHilift]

@iamsahaj_xyz Search beats dumping the whole component library into context. Give it the right five components, not 500.

[RISHi @RISHilift]

@dbmikus @amikadev Per-seat gets weird when one developer can launch a fleet of agents. Usage makes more sense here.