https://www.dailymotion.com/video/x9z8no4

Anyone know what happened?

Comments URL: https://news.ycombinator.com/item?id=48151051

Points: 12

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=47252486

Points: 1

# Comments: 1

The interesting part is the review layer — AI traces each acceptance criterion to specific lines in the PR diff, catching semantic gaps that lint and type-check miss.

We also run browser tests against the live deployment with database-level verification. Happy to answer questions about the tooling or where it breaks down.

Comments URL: https://news.ycombinator.com/item?id=46970829

Points: 3

# Comments: 1

I’m Nico, one of the co-founders of BrainGrid.

We built this after spending the last year building software almost entirely with AI coding tools like Claude Code and Cursor. Writing code was fast. Finishing anything reliably was not.

Coding was not the bottleneck. planning was. It was everything before the code: unclear scope, missing edge cases, poor sequencing, and vague intent. Once a project went beyond a single prompt, small changes started breaking unrelated parts of the app.

In traditional teams, product managers and tech leads handle this. I was a Director of Product at Twilio for over a decade. In AI-native development, that role is missing, especially for solo builders and non-technical founders.

BrainGrid is an attempt to fill that gap.

It’s a product planning agent that helps you think through what to build before asking an AI to write code. You describe a feature or product idea, and BrainGrid:

- asks clarifying questions

- maps basic user flows and specs UIs

- writes structured requirements

- produces clean, scoped inputs you can hand to AI coding tools

The output is not code. It’s a plan that AI tools can actually execute without drifting.

The product is live today. You can try it in the browser, or hand tasks to Claude Code or Cursor via copy-paste, CLI or MCP. There’s a free tier, and you can explore it without committing to anything heavy.

https://www.braingrid.ai

Comments URL: https://news.ycombinator.com/item?id=46964575

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46859101

Points: 2

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=46636582

Points: 1

# Comments: 0

We added /brand.json and /brand.txt to our website - structured files that define how we sound, what words we use, and what to avoid, what colors to use, and where to get the logos from. Now AI tools have context instead of guessing.

Feels like this should be standard. Curious what others think.

Comments URL: https://news.ycombinator.com/item?id=46470542

Points: 2

# Comments: 2

When we rebranded BrainGrid, I wanted a simple, repeatable way to tell any LLM or coding agent what the brand is, without re-explaining it in prompts every time.

I ended up creating two files:

https://www.braingrid.ai/brand.json

https://www.braingrid.ai/brand.txt

Together, they describe tone, voice, terminology, naming conventions, and visual guidelines in a way that is easy for both humans and LLMs to consume.

I tested this by having Claude Code update the branding across our docs site: https://docs.braingrid.ai/ . The experience was smooth and required very little back and forth. The agent had the context it needed up front.

This made me wonder if we should treat brand context the same way we treat things like README files or API specs.

Would it make sense to standardize something like /brand.json or /brand.txt as a common convention for LLM-assisted development?

Curious if others have run into the same issue, or are solving brand consistency with AI in a different way.

Comments URL: https://news.ycombinator.com/item?id=46356890

Points: 1

# Comments: 1

Curious any thoughts. What's working / not working for folks

Comments URL: https://news.ycombinator.com/item?id=46207216

Points: 2

# Comments: 1

When you create Gemini Flash Cache with a TTL of 1 or 3 hrs, it creates the cache and TTLs it correctly, but the billing system keeps charing the hourly rate for the cache making the charges grow exponentially.

We've seen charges go up since 9/19 even though we turned off all the services from that account.

Struggling to get the attention of folks at Google (ticket, account manager, sales engineer: no one responds)

Comments URL: https://news.ycombinator.com/item?id=45339822

Points: 1

# Comments: 3

Instead of juggling spreadsheets or paying for expensive SaaS cap table solutions, Captan stores everything in a simple JSON file that you can version-control in Git.

It supports:

- Stakeholders (founders, employees, investors)

- Security classes (Common, Preferred, Option Pool)

- Share issuances

- Option grants with vesting schedules (monthly, cliff)

- SAFEs (record + simulate conversion at a priced round)

- Cap table math (Outstanding vs Fully Diluted)

- CSV/JSON exports

- Audit log ("the ship’s log")

Overall a JSON in git will offer better auditability and version control than most commercial solutions out there.

Modeling different scenarios is super easy, just create a git branch and model whatever you need.

Quick taste:

---------------------------------------

npm install -g captan

$captan init --name "Acme, Inc." --pool-pct 20

$captan enlist stakeholder --name "Alice Founder"

$captan issue --security sc_common --holder sh_alice --qty 5000000

$captan chart

Example output:

Captan — Cap Table (as of today)

Name Outstanding %

Alice Founder 5000000 100.00%

Totals

Issued equity: 5000000

Vested options: 0

Outstanding total: 5000000

Fully diluted total: 7000000

---------------------------------------

Why I built it: early-stage founders (myself included) often don’t need Carta or Pulley yet — just a clean, hackable way to track ownership. I wanted something transparent, developer-friendly, and Git-native.

Repo: https://github.com/acossta/captan

npm: https://www.npmjs.com/package/captan

I’d love feedback on what features would make this more useful to you?

Thanks!

Comments URL: https://news.ycombinator.com/item?id=45078113

Points: 6

# Comments: 0