baetylus

First, I love this concept and I think your demo is great! Collaboration with existing harnesses makes a ton of sense. Just had a conversation with some folks in the non-tech world raving about using Claude.

A few questions:

- How do you think about competing with ChatGPT Canvas or Anthropic's artifacts, when these are shareable, native experiences in their products where users already work?

- Is a "dashboard" limited to analytics or are you trying to expand it to include written reports?

Since teams are connecting MCPs like Granola, Slack, I imagine BitBoard would facilitate sharing demos, PRDs/briefs, or customer reports. This seems like a natural expansion and trivial functionally, so I'm wondering if that's part of the sell now or something you're looking at expanding into as you grow.

I think this is cool! Maybe not your focus, but is there a place for using AI to help figure out who to send photos to / which pockets to send to?

Done!

Threw together some of these skills that'll just plug and play with your AI agent. You can download the skill to use them or just copy and paste the ones you like/want to edit.

Lmk if you'd like any added or modified. :-)

It's free btw! Works with any agent that supports skills.

Hey HN,

I built a skill to help you turn your preferred AI tool into a Chief of Staff. It'll work with any connectors you have.

Some pre-packaged commands:

`/debrief gm`: your morning briefing `/debrief triage`: your priority list today.

It's out-of-the-box private: all data stays between you and your agent.

If you want to use it cross-device or keep command history across agents, then you can create a free account.

Working on making the local version much better. It's free to start using!

LMK if you have any feedback, thanks! -Will

Hey HN,

This tool creates non-technical summaries of git pushes for engineers to share with their team.

Hopefully that makes status updates less cumbersome when you get pinged.

Usage — just run this in a repo you want to track (you'll need to login):

  npx @trydebrief/cli@latest init

Features:

- Local git hook (no GitHub auth)

- Option to run fully local (run your own AI script and send us results)

- ZDR: we discard code once summarized; only using models with ZDR policy

- Open source CLI

Would love your thoughts. Thanks!

Hey HN!

I built VibePM to help me turn outlines/specs in my markdown files into small tasks for Cursor to execute.

Some task managers are very heavy duty, so I made this as a lightweight alternative.

Some cool features: - Directly integrates into your editor via MCP - Reusable prompts - Lets you track task implementation

Any feedback is welcome. It's free to try! You just have to make an account.

Thanks! -Will

Hey HN,

A couple weeks ago I shared a GTM repository that *took off* here. After a bunch of user data and feedback, I wanted to offer a simple way for founders to pitch their products to each other.

It is really hard for early-stage founders to connect with buyers and partners in the B2B world.

So, I was hoping this could be a step in that direction toward making pitching, surfacing great products, & learning from each other that much easier.

Curious what y'all think. I just threw this together over a couple days, so lmk bugs too!

- Will

None - but I imagine we'll see some of these in the future, which we ought to handle (e.g. discerning marketing functions v. practical utility)

Thanks, added all this. Send me your thoughts (will at fellowry dot com)

So happy to read this comment. I really wanted that to come through!

Exciting idea and seems like a well-proven team. Good luck to you guys here and don't mind the endemic snark in the other threads. A couple basic questions --

1. How will you handle one-off events like volcanic eruptions for instance? 2. Where do you start with this too? Do you pitch a meteorology team? Is it like a "compare and see for yourself"?

You may be among a growing number, but for now, this stance is the exception -- especially in other executive positions.

There's an active de-dollarization effort from BRICS. Unsure how effective it'll be with the LIO

An idea's existence doesn't mean you can't build it. It's a good sign that it's been validated. Since you're not shooting for the moon, even more so.

I would pick something you're interested in, which you can do for a long time. That'll sustain you when you can't get customers or your product misses the mark.

Another underappreciated effect of dogfooding may be its reduction in bloated functionality.

If you're not dogfooding, you rely harder on a mental user model. Just conjecturing -- not only does that model diverge across your organization, but it could result in more top-down decisions about what a user wants, which probably creates more politics and friction all around your teams.

hey all - thought this would be a fun experiment. This is just a GPT-wrapper, but I'm wondering if it'll have any utility for folks.

The tool is free and at limited functionality. I would love any suggestions/feedback. Thanks. -Will

Love this idea - a huge pain point for many teams. I've had this issue, and am looking forward to trying this out.

I know there are a couple competitors too. How do you distinguish yourself from something like Merge.dev?

>> the hard part is contextualizing it in a way it is immediately useful. That depends on understanding the company/domain lingo, understanding users, etc.

How do you control this deterministically? It sounds like the "hard part" is variation in prompting & selectively choosing the right data to include, both of which I could see being good enough right now but hard to deliver definitively.

[ deleted ]