smallmartial

Hey HN,

We've been working on Reelsy for the past few months and wanted to share what we've learned building a multi-agent AI system for video content creation.

The Problem

Creating short-form video content (YouTube Shorts, TikTok, Reels) at scale is brutal. A single 60-second video costs $500+ with freelancers and takes 3-5 hours. For creators who need to post daily, this is unsustainable.

The bigger technical challenge: AI-generated images have a consistency problem. Ask any image model to generate "the same character" across 15 scenes, and you'll get 15 different-looking people.

Our Approach: Multi-Agent Architecture

Instead of throwing one LLM at the problem, we built a 5-agent pipeline inspired by actual film production:

Director Agent - Breaks down the story concept into a shot list Scriptwriter Agent - Writes dialogue and narration for each scene Character Designer Agent - Creates reference images and locks character identity Cinematographer Agent - Determines camera angles, lighting, composition Hook Generator Agent - Optimizes the first 3 seconds for each platform The agents communicate through structured outputs and can iterate on each other's work. We found this beats a single mega-prompt approach by ~40% on our internal quality benchmarks.

Character Consistency Solution

We use Gemini 2.5 Flash ("Nano Banana" on LMArena) with reference image anchoring. The Character Designer creates a canonical reference image, then every subsequent scene generation includes this reference with specific instructions to maintain identity.

Current results: 85%+ consistency across 15-20 scene generations. Not perfect, but usable for most content types.

Multi-agent coordination is harder than it looks. Race conditions, agent disagreements, and context window limits are real problems.

Character consistency is still the hardest unsolved problem in AI video. Reference anchoring helps but isn't bulletproof.

Platform-specific optimization matters more than raw quality. A slightly lower quality video with proper hooks outperforms beautiful content with weak openings.

Current Pricing

~$0.70 per video (15-20 scenes, voiceover, music). We're not trying to undercut human editors on quality, but for high-volume content needs, this makes previously impossible workflows viable.

Would love feedback from the HN community, especially on the multi-agent architecture. Happy to answer questions about our implementation choices.

Hey everyone!

For those of you doing Amazon affiliate marketing, you’ve probably encountered the common problem of how to quickly scrape large amounts of product data and efficiently export affiliate links for SEO or social media promotion. To streamline this process, I’d like to recommend a newly released Chrome extension called Amazon Product Scraper, developed by a friend of mine who runs independent sites. It has already saved us a lot of time in real-world applications.

Here’s the Chrome Store link: Amazon Product Scraper - Chrome Web Store

What Problem Does This Plugin Solve?

When doing Amazon affiliate marketing, we typically need to search for tons of products using keywords, click through to each product page to collect titles, prices, product details, image links, and then manually generate affiliate links. This repetitive process is not only time-consuming but also tedious, especially when you need to scrape thousands of product listings—manual work is just not feasible.

This plugin tackles exactly that pain point. It automatically scrapes Amazon product information based on keywords, including:

• Product titles • Prices • Product details • Image URLs • Product links

The best part is, it supports bulk exporting this data into CSV files compatible with Excel. You can also predefine your Amazon Affiliate ID so that the exported product links are automatically appended with your affiliate tag, saving even more time.

Key Features:

1. Keyword Search: Enter keywords to quickly filter relevant products. 2. Automatic Data Scraping: Retrieve product titles, prices, images, and details with one click, without manually visiting each product page. 3. Affiliate Link Generation: Predefine your Amazon Affiliate ID, and the plugin will automatically add it to the exported product links for easy commission tracking. 4. Data Export: Export all the scraped data to a CSV file, which can be further processed or analyzed.

Example Use Case

Let’s say you need to create pages for 1000 keywords on your website, and each page requires 30-50 product recommendations. That means you’ll need to scrape 30,000-50,000 product listings. Manually doing this would take an unreasonable amount of time and effort. This plugin automates the entire process, saving countless hours of work.

If you’re interested, feel free to download the plugin from the Chrome Web Store and give it a try. I’ve been using it for a few days now, and it’s been a huge time-saver. If you have any suggestions or run into issues, let’s discuss in the comments!

I have been using this tool for a while now, and so far, it feels pretty good.