Teneo's weekly agentic round-up:
What happens when an AI agent can switch off the monitoring meant to watch it?
- OpenAI reported two internal coding agents that weakened monitoring during routine work. One emptied the alert recipient lists after reading an old "don't send messages" instruction too broadly. The other removed a monitoring integration, then told the user it had not. Two internal cases, not a rate.
- Microsoft says a model should not be its own security authority. The controls on what an agent can reach, do and whether it keeps running must sit outside the model. It is introducing Guardian Agents and graded responses, from blocking writes to stopping the agent. Vendor post; no availability dates.
- Kraken's app is live in ChatGPT, read-only. You can ask what you made today, but ChatGPT cannot place trades or move money. Kraken's description; not tested by us.
The common point: if the agent can reach the switch, a routine task can turn it off. The watching has to sit where the agent cannot edit it.
Last week we asked who gave your agent permission. This week is the next question: what checks that permission while the agent works?
On Teneo, every agent has a wallet-authenticated identity, starts private and goes public only after review. Changing its commands sends it back to private. Builders can set a rate limit that rejects requests before a task runs, users see the price first, and payment goes through x402.
The SDK does not document behaviour monitoring, audit logs, spending caps or a mid-task stop. So keep the log of every paid call, the alert list and the spending limit in your client, where the model cannot change them.
A useful test this week: give an agent a task that would be easier with an alert turned off. Check that the change is blocked and a person still hears about it.
Read this week's round-up here:
https://t.co/frnl9KflJb
The most powerful storytelling engine isn't AI. It's imagination.
AI should help bring it to life.
Meet OptimAI Story Studio: turn an idea into illustrated storybooks, manga or comicsβwith Creative Agents, recurring characters and narration.
π https://t.co/2QGP4qMmlV
For builders: we're developing OptimAI Creative Agents as an open-source toolkit.
Explore the templates, customize creative recipes, or contribute new capabilities.
The next creative breakthrough might be what we build together.
https://t.co/CxtHiwdjjo
Keep building.
Open models. Real machines. One connected network.
A first look at model hosting in Core Node: the infrastructure we're building behind OptimAI Router.
OptimAI is building an interconnected agentic stack spanning model access, data, execution, and decentralized infrastructure.
Router, DePIN, and DeHIN represent complementary parts of that direction.
The objective is to make distributed intelligence useful - not merely available.
wild to see how differently websites treat cloud servers vs residential connections. AI agents are basically seeing a totally different web.50M retail banking users getting crypto access is pretty wild. tradfi adoption moving faster than expected. π€
If your AI product reads the live web, the page it gets depends on where the request comes from. We tested how much.
AI search engines, research agents and data products all fetch live web pages to answer questions. Most of them fetch from cloud servers. Websites can tell, and many answer a cloud server differently from a person at home.
The test: we requested the homepage of the 300 most-visited websites from two places in the same minute, with identical headers. One request came from a cloud server in Paris. The other came from a home broadband connection near Dublin.
What came back: 213 sites answered both. Google refused the cloud server with its "unusual traffic" page and gave the home connection its homepage. Three sites refused the cloud server only; none refused the home connection. Eleven sites, including Microsoft, PayPal, Stripe and HP, served their French site to the server and their Irish site to the home connection. Same URL, different page, and no error to tell you.
So the first question to ask any live web data provider is simple: where does the request leave the network from? On Teneo, it leaves from opted-in devices in real households, so your agent gets the page a person in that market sees.
Our new guide gives you six questions to ask before you sign, the full data, and a test you can run on your own pages:
https://t.co/9icbsjyarB
Building AI search, RAG or crypto data products? Reply with the markets that give you wrong answers and we will set you up with a free seven-day pilot.