Your agent wants permission to run a migration and you’re not at your desk.
Cuttlefish, our iPhone app for Managed Agents, puts the approve button in your pocket with your agent's requests on screen. Send a correction mid-run, or stop it if it goes sideways. https://t.co/GbEKlRQTlY
Who is going to @TomorrowXSummit next week in Austin!? @kevinvangundy & I are organizing a dinner at one of my fave new ATX spots. @digitalocean has also has some extra passes to giveaway.
Interested in joining? let me know!👇🏻
@gagu_sh Agreed, Gagan. “Fails loudly before the agent starts improvising” is the key part.
Here the fix was four env vars in the agent’s environment, and the Simulation stays in place as a regression test, so if the gap ever comes back, it fails again.
A coding agent ran 40 times and opened 40 working PRs.
All 40 hit the same bug. The sandbox had no git identity, so every first commit failed and the agent invented one.
DigitalOcean Signals caught it, and a Simulation proved the fix before production changed. https://t.co/kq47PjpcV5
Hello,
Thank you for reaching and we're sorry to know that the droplet was deleted.
In order to resolve this issue, we’ll need a support ticket for our engineers to review it thoroughly. If you’ve already created a ticket, please share the ticket number with us.
Alternatively, we can create the ticket for you—just send us your registered email address in a direct message. You can also create the ticket yourself using our Contact form - https://t.co/LsKDKMrHD7
“Agents need memory, agents need data services, agents need complex orchestration, agents need secure operating environments called sandboxes.”
@paddix on the software it takes to run agents in production. On @theinformation’s TITV.
Everyone has figured out how to generate code. Almost no one has figured out how to QA it at scale or monitor it in production.
@rbren_dev of @OpenHandsDev on agents that start work on their own, and the cloud they run in. https://t.co/XtbCJDvQIU
@chriskim_dev@Box Thanks for having us at BoxWorks 2026!
We loved showing people how @Box and DigitalOcean Cuttlefish work together to keep agents moving, even when you’re on the go.
@wrftr We're sorry to hear about this. Our security team would need to investigate this for you. Please submit a report at the link below.
https://t.co/i6QQFMZOGL
QM, @ycombinator's open-source agent harness, now deploys in one click on @digitalocean: compute, sandboxes, inference, database and storage.
One cloud. One bill. Your choice of models.
Meet us in SF this month alongside our
friends @DigitalOcean + @gumloop:
⏵ merge(happy_hour)
Date: Thu, Nov 12
Talks/demos on self-improving agents
⏵ Gumloop x Linear Design Gallery
Date: Thu, Nov 19
40 designers sharing their work
“DigitalOcean makes it easy to get started.” @ycombinator Labs’ Joshua France on the first one-click deployment for QM, YC’s open-source agent harness.
Check out QM on DigitalOcean today: https://t.co/BuSB6NqSd1. To learn more: https://t.co/fjA0yxRcbi.
The agent sends. The key stays out.
@neimuc27 let an AI support agent reply on its own without ever holding the credential. 57 of 335 customers got answers with no human click, and nothing sensitive went out.
https://t.co/HXfgF1gw8w
Last time, my AI support agent sent zero replies. On purpose.
This time it sent 57 of 335 on its own. Nothing sensitive went out.
It never held the credential. But two things still broke that I didn't see coming: a policy that never fired, and an attack the agent caught and still let through.
https://t.co/GztICJFBqb
Check out Claude Fable 5.2 on @digitalocean serverless. We have faster Day 0 access on our serverless platform than I have on my Claude desktop. Go figure !!
.@digitalocean Cuttlefish looks absolutely amazing on iPhone Duo! You can now work side by side with your Artifacts and prompt your agent. Install it new update out!! https://t.co/2AeHAoYIGF
Claude Fable 5.2 from @AnthropicAI is live on DigitalOcean Serverless Inference.
Anthropic calls it its most capable GA model for technical work and reports output up to 30% faster than Fable 5.1. 8/40 per 1M input/output tokens. One account, one bill. https://t.co/U09mgujj3R