Can you undo what your AI agent did? - OpenAI launched dots, always-on agents with their own cloud computer. Background work uses read-only tools. Actions that touch your accounts or share information go through auto-review, which decides whether they proceed, need your approval, or stay with you. Rolling out to Pro and Business Premium. OpenAI says to review consequential work. - A new preprint, Planarian, rolls agents back. Local changes are restored from snapshots. Remote changes are reversed by recorded compensating actions. Up to 15x better task quality in the authors' tests. Not peer reviewed. - Restate raised a $20M Series A, reported by Tech.eu, for durable execution. After a crash it skips steps that already completed, so a retry does not pay twice. The common point: some actions restore from a copy, some need a second action to reverse, and some cannot be taken back. The check belongs in front of the last group. Last week we asked what an agent actually did. This week is about what you can do once you know. On Teneo, an agent must pass review before it goes public, users see the price before a task runs, and payment goes through x402 and settles on-chain. The SDK does not document refunds, disputes or duplicate-payment protection. So treat a paid call as a step with no undo: confirm the command, the price and that this request has not already been paid, using a request key your client stores before it sends. A useful test this week: stop one agent run halfway, restart it, and see whether anything runs twice. Read the full round-up here: teneo-protocol.ai/blog/can-y…

A major new Beacon release is live on all platforms 🚀 - Desktop 0.4.9 - Android 0.4.9 - CLI 0.6.0 Massive technical improvements under the hood, with more coming soon that build on this version. A big step forward. Don't get left behind! Everything we ship next depends on this release. Older versions are being phased out step by step, and outdated Beacons will stop earning at some point. Nothing you've already earned is lost. Seeing "update required"? That's expected, not a bug. One tap installs the update and restarts your Beacon. Update today. It takes under a minute: - Desktop: tap the update screen - Android: update in Google Play - CLI: re-run the install script

Your agent asked for a page. Did it get the one a person sees? Some websites treat datacentre traffic differently from people. A request from a cloud server can come back as a check page, with no price and no stock. Teneo carries the request through an opted-in device in a real household or on a real mobile network, so your product gets the page a person in that market sees. Free 7-day pilot for AI search, RAG and crypto data teams. DM us the markets that give you the most trouble.

Teneo just passed 100 million customer requests. 1 request = 1 page fetched from the open web That's around 1 million pages a day Every request goes through a device running Teneo Beacon Much of it feeds AI that needs the live web Next goal: 1 billion. 🚀

Teneo Protocol community update Many of you have asked for an update. Here is where the product stands and what the team is working on. - The product is live and working: The agent network, CLI and bandwidth-sharing network are running. Developers are building with the CLI and agents today. If you have not tried it yet, the setup guides are here: teneo-protocol.ai/get-starte… - Getting ready for TGE: Most of the team's time right now goes into preparing for token launch. That includes fundraising, work with launch partners, and daily calls and due diligence with investors and launchpads. This work does not always make a good public post, but it is moving forward every week. - We will share a TGE date once it is fixed, and not before. - Rewards paid to the community: We have paid out $8,000 in rewards to community members for running Beacon. - SDK, agents and Agent Console: These remain core parts of Teneo alongside our work on Beacon. Developers can continue building with the SDK and using agents through the Agent Console. - Dashboard and contribution points: We know some users are seeing issues with the dashboard and points. We are investigating. - Expedition Hub leaderboard: The leaderboard was part of an earlier InfoFi campaign, which has now finished. We are working on new ways to reward the community and will announce them when they are ready. - Coming up: We will share customer stories and case studies as partners agree to go public. We will also post updates like this every two weeks. Thank you for being part of Teneo.

What did your AI agent actually do? - OpenAI is reviewing its agents' actions from training and evaluation runs, working back month by month. It found agents sending data to third-party services, including 53 user images posted to image hosts as unlisted links. OpenAI says most cases so far are low severity. The review will take months. - NVIDIA announced its Open Agent Safety Platform. OpenShell, now broadly available, limits the files, networks, tools and credentials an agent can reach. Sentry runs on separate hardware, keeps a record of agent activity and can stop an agent. These are announcements, not deployment data. - n8n 2.41 turns agents on by default and separates skills from tools in the session timeline. Both releases are pre-releases. The common point: the result is not the record. When something goes wrong, you need to know which services an agent contacted and what it sent, and the agent's own summary cannot tell you that. Last week we asked who checks an agent's work. This week is about the actions behind it. On Teneo, an agent must pass review before it goes public, users see the price before a task runs, and payment goes through x402 and settles on-chain. Those records show the agent was reviewed and the call was paid for. They do not show what happened during the task. The SDK does not document an audit trail, so the client should keep one: request, command, price, payment reference, response, check result. A useful test this week: rebuild one agent run using only your stored records. If you cannot, fix that before the next run. Read the full round-up here: teneo-protocol.ai/blog/what-…