charlotte

building @momentalos | swede in the bay area

[charlotte @lottite]

@Vatsalpandya333 You missed

Loops

Loops??

Loops!!!!

Loops?

Loops!

[charlotte @lottite]

observation: product managers are falling behind in ai even though they’re in a unique position to shine

guess they’re less hands on, and busy as always

while designers and dev find it natural to absorb new tools

meanwhile product has never been about tools, and at first glance ai looks like a meeting summarizer

ok cool but then what

then you’re in a position to create anything, because your job was always to gather context, define inputs and clearly explain what you want

exactly what LLMs need

but few PMs seem to have gotten there

[charlotte @lottite]

@SherryYanJiang The question is - is it higher for product, marketing, or both?

[charlotte @lottite]

"it's not about building anything, but about building the right thing"
ok we're reinventing product management

"it's about loops"
oh hello again lean startup

[Mathias Kleverud @mathiiias]

/goal as it should be

actual business objectives as the goal
key results as verifiable outcomes
problem spaces, possible solutions and tasks as the work tree

[charlotte @lottite]

now, make the objective a business goal

[JUMPERZ @jumperz]

peter is right.. in other words you have to know how to coordinate and give the right roles to your agents.

for example, i'd bet most people running /goal on codex don't have a system behind it... they're still prompting some big block of text..

the point of /goal is to stop answering and start coordinating well.

/goal "<objective>"

don't give me one answer turn my objective into a multi-agent loop:

>decompose the work
>assign the right agent
>coordinate dependencies
>execute in order
>review against the original goal
>gate before shipping
>save what worked
>report only what matters

this will 10x your output, because you basically will stop prompting big text and start using codex's agents the way they're meant to while everything has its role so your goal gets executed perfectly and big part of this is that you just stop being the bottleneck...

apply this eveyrwhere not just codex btw.. decompose, assign, coordinate, gate, report...claude code, your own agent stack, anything...

[Daksh Gupta @dakshgup]

boris cherny goes on a podcast every three months and says something like “i’ve stopped breathing now i just wrote a breath.md” and the next day everyone in sf stops breathing

[Paul Graham @paulg]

"What if the model companies do this?" is the new "What if Google does this?" I.e. the meaningless question investors ask that shows either that they're stupid or that they dislike you and are looking for ways to find fault.

[charlotte @lottite]

@pzakin 💯

what we’re seeing is that the autonomous product org - or just the autonomous org - is just about providing good leadership

clear goals, definition of success, principles

[charlotte @lottite]

@Winterrose using @momentalos (and building it, disclaimer)

[charlotte @lottite]

@petergyang 👋

[Mathias Kleverud @mathiiias]

figuring out what's between us and reaching our goal.

&gt; suggestions to review and edit
&gt; grounded in our company context
&gt; smooth ui

[charlotte @lottite]

ramen profitable in the bay area with a family means &gt;20k MRR

[charlotte @lottite]

poke but nice

is the new

uber for x

[charlotte @lottite]

We set out to build the infrastructure that enables agents to run businesses autonomously, and thought we’d get there by answering “What do agents need to succeed without constant guidance?”.

But the answers we found, in the pursuit of autonomous agent teams, are profoundly similar to what good management looks like, and what any human needs to thrive at work.

This is the tool I wish I'd had as a product manager.

[Momental @momentalos]

Assign an agent to a key result - they'll take care of it.

Break down goals into tasks, based on your analytics, customer conversations and strategy.

Drag and drop cloud agents, your human team member or your Claude Code.

Agents connected via MCP picks up the task with full context of what needs to be done at why.

[charlotte @lottite]

@mattcassinelli @jakebathman 100%. It feels like a very small clique on x - the same that thinks that rage bait is great marketing - would appreciate it

[charlotte @lottite]

@jakebathman @mattcassinelli

[charlotte @lottite]

I used to make goal visualizations in Miro and then try to capture the why and big picture behind every task in Jira.

It was a mess. But humans absorb the implicits and keep a model of how everything fits together.

Agents don't.

Well, didn't.

In @momentalos, agents keep the hierarchy of every task in their context when picking up work, so they know why they're doing it. It's the most important context they can get.

And for human 👀, you can seamlessly switch between a view of your goal, and a kanban of tasks.

[charlotte @lottite]

@grepmoney codex not stupid, codex efficient