ChatGPT Ads multi-image is in open beta: 4 to 6 square images, one destination URL. Build a set around one product story, not four unrelated clicks. Check the rollout in Ads Manager.
OpenAI guide: help.openai.com/en/articles/…
2
11
A saved draft, paused campaign creation and activation are different stages.
In Advarde, review what each action will change before approving it.
advarde.com/docs/chatgpt-ads…
1
4
ChatGPT ad variants can run without per-version approval when creative enhancements are enabled.
OpenAI's current guide says auto-enable starts 29 Oct. Check Ads Manager.
help.openai.com/en/articles/…
2
5
Your GTM tag fired. Check what happened next.
Did the action succeed? Was the right event sent with consent? Is there a receipt? Is it attributed to an ad?
Those are separate checks. A green preview does not answer all four.
Save this for your next tracking audit.
#ChatGPTAds
2
3
ChatGPT ads now run in 60+ countries.
On 30 Sep, OpenAI added Indonesia, Malaysia, the Philippines, Singapore, Thailand, Vietnam and Taiwan.
seroundtable.com/openai-chat…
4/ In the EEA, personalized ads need the user's opt-in. Without it, ads match the conversation, not the person.
1
1
2
Advarde retweeted
Jev is getting a lot of attention right now.
But after looking through the projects people are actually building with it, I think the more interesting story is not Jev itself.
It’s the role it can play inside an agent.
A few examples stood out to me:
1. browser-use/jev-ultrafast (~16.6k⭐)
Jev picks the next browser action without needing another expensive LLM call.
github.com/browser-use/jev-u…
2. tamaratran/fast-jev-compaction (~6.5k⭐)
Uses Jev to decide which context is still useful and what can be dropped.
github.com/tamaratran/fast-j…
3. TheoLeeCJ/SemIf (~4k⭐)
An open-source, local implementation of Jev-style decision making.
github.com/TheoLeeCJ/SemIf-O…
4. jarrodwatts/jev-trader (~2.1k⭐)
A real-time trading loop where Jev chooses between buy, sell, or wait.
github.com/jarrodwatts/jev-t…
5. kerpopule/hermes-jev-skills (~670⭐)
Uses Jev for routing, memory, compaction, and skill selection.
github.com/kerpopule/hermes-…
6. devagrawal09/jev-review (~570⭐)
Code review where Jev helps make decisions instead of relying on one massive prompt.
github.com/devagrawal09/jev-…
7. thruwire/foreman (~520⭐)
Uses Jev as a supervisor for coding agents: continue, retry, verify, or stop.
github.com/thruwire/foreman
8. superagents-lab/jev-search (~400⭐)
Jev decides where an agent should search and how it should search.
github.com/superagents-lab/j…
9. droidrun/mobile-jev (~350⭐)
Uses Jev to choose the next action for Android agents.
github.com/droidrun/mobile-j…
10. gargpratyush/jev-router (~340⭐)
Uses Jev to route different agent tasks to the right model.
github.com/gargpratyush/jev-…
The pattern across these projects is pretty interesting:
1. LLMs generate.
2. Agents execute.
3. Jev decides.
And that decision layer can show up in very different places:
→ Which action should the agent take?
→ Which context should it keep?
→ Which skill should it use?
→ Which model should handle the task?
→ Should it retry, verify, or stop?
→ Where should it search next?
This is probably the most useful way to think about Jev.
Not as another model that replaces your agent stack, but as a decision layer that sits inside it.
I collected these 10 repos as a starting point if you're trying to figure out what you can actually build with Jev.
Which one would you add to this list?







