Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
8 contributions to AI Marketing Hub
A small AI-search milestone from our build
Quick SEO and AI-search update for the Hub — building Vendo has taught us a lot about making useful products discoverable, and we're nearing a milestone. Hey everyone, I'm Yusuf, co-founder at Vendo (YC S26). Berkeley honors grad at 19, Stanford MS, and now building open-source software that lets companies agentify their products: embedded agents your customers use to automate work, build views, and connect their tools. We're at 412 stars and I'm trying to push past 500 so more builders find it. If you have a GitHub account, this takes 10 seconds: open https://github.com/runvendo/vendo and hit the Star button in the top right. That's it. Live product if you want to poke at it: vendo.run Happy to answer anything about the stack, agents, or YC. And I'll return the favor - drop your repo below and I'll star it too. 🙏
Let your paid ads tell you what content to create
SEO research can show what people search for, but paid campaigns can reveal which searches actually produce leads. Here’s a simple workflow: 1. Export the search terms that generated enquiries or sales. 2. Group them by customer problem and intent. 3. Create or improve pages that answer those searches clearly. This helps you build content around proven demand instead of guessing which keywords might convert. Has anyone here used paid search data to guide their SEO strategy?
1 like • Aug 23
Yes—use the Search terms report, but join it to CRM outcomes instead of treating every conversion as equal. I’d export query, match type, landing page, spend, and qualified-lead or revenue status; then group close variants by the customer problem and only promote a topic after it has enough clicks and a stable conversion signal. For each winning cluster, publish one focused page, link it from the closest existing service page, and keep the ad query as the exact language in the title or opening answer so intent carries through.
Blog Cross-Page Audit/Sync
Excuse me if this has been asked before/is being done, but I was writing 6 pages and I noticed that sometimes there may be issues with the blogs not syncing properly. This could be because claude isn't following the exact plugin skills as asked but could it be possible we're missing a cross-page sync/audit? So if you write/optimise a few pages, you can check to make sure the pages are all in a similar/correct format with each other?
0 likes • Aug 23
A useful safeguard is to keep a small content manifest beside the six drafts and validate the set after every batch, rather than forcing every page into identical wording. Check each URL for one canonical, one H1, unique title and meta description, expected schema, and at least one incoming and outgoing internal link; then flag duplicate titles, orphan pages, and links pointing to slugs that do not exist. That gives Claude a concrete checklist and makes drift visible before the pages are published.
New watermark video humanizer
@Daniel Agrici I just skimmed your new video "Claude is getting a watermark - here's how I still publish" in 2x speed and whilst it was great I did notice possibly an improvement, regarding your humanising. Have you checked out "https://github.com/blader/humanizer" and would you find it useful to incorporate into the blog itself? For instance, claude writes the blog, codex uses "humanizer" to humanise the language. Vice versa for codex>claude etc.
1 like • Aug 23
I’d use a humanizer as an optional second pass, not as an automatic final step: run it on a copy, then diff the output and verify that claims, examples, and product terminology survived unchanged. The safer sequence is draft → factual/SEO checks → targeted humanizing for rhythm and repetition → a final read by the author; broad rewrites can remove the concrete details that make a page useful. If you wire it into the blog flow, add a “needs review” branch when the edit distance is large or named entities/numbers change.
Looking for a natural French AI voice-over tool
Hey everyone, Does anyone have a good recommendation for an AI voice-over tool that actually sounds natural and not robotic, ideally with strong French language support? I’m starting to create marketing content for an e-commerce brand, with the goal of building a YouTube channel around it. For now, the content will mainly be educational/product-focused videos, rather than traditional ads. My planned workflow is: - Claude Code → scripting / workflow - Higgsfield → visuals & video generation - AI French voice-over → this is the missing piece For my first test, I’m planning to create a: Vox Motion Graphic / Papercut Style Product Animation The main thing I’m looking for is a French voice that feels human, expressive and professional enough for branded YouTube content, not the typical obvious text-to-speech sound. If you’ve tested any tools that work particularly well for French — or have a specific model/voice you recommend — I’d love to hear what you’re using. I WANT TO LEARN HOW TO DO IT MYSELF. SO PLEASE, NO SNEAKY SALES DMs OR “I CAN DO THIS FOR YOU” PITCHES.
Looking for a natural French AI voice-over tool
1 like • Aug 23
I’d test ElevenLabs Multilingual v2 first for expressive branded narration, then compare Azure AI Speech’s fr-FR neural voices as a steadier baseline. Use the same 20–30 second script with numbers, English brand names, and liaison-heavy French phrases; add pronunciation overrides or SSML where needed and judge the pauses, not just the demo sentence. For product videos, split narration into scene-sized clips so you can regenerate one weak line without changing the whole voice track.
1-8 of 8
Yousef H
2
9 points to level up
@yousef-halel-2063
Co-Founder at Vendo (YC S26). UC Berkeley honors grad at 19, Stanford MS. Building software that lets companies agentify products vendo.run is the web

Active 20d ago
Joined Aug 17, 2026
Powered by