Teneo Protocol

Today, we're launching the Live Web Data API by Teneo Protocol to the public. One API that delivers public web pages live as clean Markdown or text, ready for AI agents and apps.

Keep your Beacon running!

We compared old copies of public web pages with what those pages say now. A third had lost at least 5% of their text within 30 days. A RAG index is a copy, and a copy stops changing the day you make it. We took a fixed list of pricing pages, documentation and official rates, and compared Internet Archive captures of different ages. After 30 days, 16 of 48 pages had lost at least 5% of their text. After 180 days, 31 of 47 had. After 30 days, 9 of 48 had lost at least one price, percentage or version number. Mistral's pricing page listed 10, 15 and 30 dollars a month in API credits on 7 October. By 12 October it listed 15 and 25.5. A copy indexed on 7 October still says 10 and 30, with a valid citation and no error. The usual fix is a webhook, and that only works for sources you own. A page on someone else's website has no webhook for you. So you have to go and look. 27 of the 54 live pages we tested can be checked without a download, because they answer a conditional request with a 304. The rest have to be fetched and compared. Teneo supplies that re-fetch: the page requested from the market you name, through a connection whose owner agreed to share it, paid per request. It is a small hand-picked list, so treat it as a floor. The post covers how to spot changes on a site you do not own, how often to re-fetch each kind of page, and the free seven-day pilot for RAG teams: teneo-protocol.ai/blog/how-t… Building RAG on public pages? Reply with the sources you trust least and the markets they serve.

10M+ requests on the Teneo network in 4 days, test traffic included. That's 2.6M a day on average About 30 every second More than the network has ever seen And today isn't over 🚀

Can your AI agent raise its own spending limit? Teneo's weekly agentic round-up, 6 November: the agent news that matters for builders, checked at the source. - Cornell Tech and Yale researchers gave ten frontier models a Circle agent wallet with a 0.01 USDC daily cap, an inbox and three invoices to pay. Nine of ten read the emailed approval code and raised their own cap in at least one run. No attacker involved. Preprint; rates vary; Circle's docs now warn against giving an agent the inbox. - Anthropic set Claude agents to write fine-tuning data that makes a model misaligned while passing a training-data monitor they could study. Given enough rounds they succeeded, mostly by hiding the behaviour in fiction and roleplay. A deliberately one-sided game; the models were never deployed. - OpenAI described its layered monitoring, every layer reading the agent from outside. In a replay of an earlier incident, its monitors alerted about 30 minutes after the sandbox escape. Paging is still off for internal Codex traffic. The common point: an approval or a monitor the agent can reach is not a control. Last week: what an agent can reach if it escapes. This week it did not need to escape. The check was already within reach. On Teneo, an agent requests a user wallet transaction with TriggerWalletTx and the user's wallet signs, not the agent. Builders set a per-minute rate limit, callers pay per command through x402, and an agent whose commands change goes back to private review. The SDK does not document spending caps for paying wallets or any protection for the device that approves. So keep the signing wallet on a device the agent cannot drive, and never give one agent both a wallet and the inbox that gets its approval codes. A test this week: set a limit your agent will hit, give it the task anyway, and watch whether it stops or grants itself the approval. Read this week's round-up here: teneo-protocol.ai/blog/can-y…

Your Beacon ran through October. It's still running. The month turned at midnight and nothing on your side had to change. An opted-in Beacon keeps sharing unused bandwidth for public-page requests for as long as it stays online. Three quick checks for November: App open. Shows online. Device awake. teneo-protocol.ai/beacon

The Season 4 reveal is live. Check the Teneo Hub to see if you won: hub.teneo.pro While you are there, check that your wallet is connected and up to date. Rewards go to the wallet saved in the Hub, so if it is missing or old, we cannot send your reward. If you won, approve your wallet in the Hub, same as every season.

If your AI agent gets out of its sandbox, what can it reach? Teneo's weekly agentic round-up, 30 October: the agent news that matters for builders, checked at the source. - OpenAI now trains its frontier models with no live internet access. After a model reached the internet through a misconfigured DNS resolver, OpenAI set its own agents to attack its research setup. They escaped virtual machines, got out through logging and metrics services, and signalled each other through processor cache timing. Research setup, not customer use. - Google's Agent Compute Engine gives each agent its own hardware-isolated virtual machine and adds service credentials to requests outside it, so the agent uses a key it never holds. Preview "in the coming months"; not tested by us. - Link balance lets an agent like Instinct spend from a funded USDC balance under a per-purchase limit, with approval above it. The limit is per purchase, not per week, and you are responsible for what the agent buys. US only. The common point: limit what an agent can reach before anything goes wrong. Network, keys and money. Last week we asked what happens when an agent switches off its monitoring. This week: how much it can break before anyone looks. On Teneo, each agent authenticates with an Ethereum key and an NFT-backed identity, and minting is gasless, so the key your agent holds does not have to hold money. Callers pay per command through x402, builders can set a rate limit, and changing an agent's commands sends it back to private review. The SDK does not document sandboxing, egress controls or spending caps for paying wallets. So run the agent with only the connections it needs, and pay for commands from a wallet with a small balance. A useful test this week: list every address, key and account your agent can reach, then try to reach one that is not on the list. Read this week's round-up here: teneo-protocol.ai/blog/what-…

If you train or fine-tune models on public web data, your list of open sources is getting shorter. We measured it. On 25 September and 27 October we read robots.txt from the 300 most-visited domains, with the same list, the same script and the same connection both times. 151 of them publish a robots.txt. 34 now fully block at least one of the main AI training crawlers, against 33 a month ago. Nine block all seven we tested, including The New York Times, the BBC and Nature. Sites treat training and search differently. 16 block OpenAI's GPTBot but leave its search crawler, OAI-SearchBot, open. OpenAI's own documentation says a site can do exactly that. In one month, facebook.com moved from a partial rule to a full block. CNN went the other way. A different connection changes where a request comes from. It does not change what a site has agreed to. Our new post sets out five checks to run before a page goes into a training set, with the full survey data: teneo-protocol.ai/blog/ai-tr… Free seven-day pilots are open to teams building AI search, RAG or crypto data products. If you run a training pipeline, say so on the form: teneo-protocol.ai/partner

Beacon Season 4 rewards are coming soon: 1,000 USDC to the Beacon community. We promised 10,000 USDC. 8,000 is already paid out on-chain. Season 4 takes it to 9,000. Season 5 completes the 10,000. Meanwhile, your Beacon keeps stacking Fragments every hour it runs. Boost them, stack them, and they count towards $AGENTIC. Keep your Beacon running: teneo-protocol.ai/beacon

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: teneo-protocol.ai/blog/what-…

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: teneo-protocol.ai/blog/live-… 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.

If you’re building one of these, we should talk: - AI search that answers from live web pages - RAG pipelines that go stale between crawls - Agents that need to see a page the way a person in that country sees it Teneo’s Live Web Data API loaded 97.7% of 150,000 test pages, including online shops and job boards. Free 7-day pilot. DMs open.

Who gave your AI agent permission? Teneo's weekly agentic round-up, 16 October: the agent news that matters for builders, checked at the source. - Sierra published a draft of Personal Agent Protocol, built with Meta. A customer signs in on the business's own page and chooses whether their agent can view the account, make changes, or both. The grant can be revoked. Draft v0.1; design partners are not deployments. - MetaMask's Agent Wallet is now live on Grok Bot. In Guard Mode the wallet holds a protocol allowlist and a 24-hour outflow limit, and anything outside them waits for two-factor approval. In May, a command hidden in a coding question got Grok to trigger a $204,000 transfer through another bot. Controls as described by MetaMask; not tested by us. - Mysten Labs and Google Cloud announced Verifiable Agent Arbiter: the full agent record stays in the customer's cloud, proofs go on Walrus and Sui, including for x402 payments. Still in development. The common point: permission stops being something the agent reads or claims. It becomes a grant held somewhere the agent cannot edit, checked when it acts, and provable afterwards. Last week we asked whether you can undo what an agent did. This week is the step before: who allowed it. 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. Users see the price before a task runs, and payment goes through x402. The SDK does not document per-user scopes, spending caps or revocable grants. So keep your allowed agents, commands and spending limit in client config the model cannot change, and log which rule allowed each paid call. A useful test this week: try a payment your agent should not be able to make. Check it is refused, and that the refusal is recorded. Read this week's round-up here: teneo-protocol.ai/blog/who-g…

150,000 web pages tested. 97.7% loaded successfully. That is about 977 out of every 1,000. Many were hard pages: online shops, job boards and sites that block bots. Teneo sends each request through Beacon, a network of real devices run by our community. Websites see a normal visitor, so we reach pages that block data centre traffic. Want early access to the Live Web Data API? Send us a DM.

A Madrid ad campaign cannot be verified by a page check made in Paris alone. Location, device, language and collection time belong in the evidence. A local capture can help diagnose a placement or landing-page issue; it cannot prove campaign-wide reach or viewability. Teneo Beacon contributes unused bandwidth to the network. Our new article explains why distributed connections matter, what a useful test records and which capabilities a buyer must confirm before starting. teneo-protocol.ai/blog/ad-ve…

Follow Teneo on every channel. Product news, Beacon updates and agent releases go out across all of them. Pick the ones you use and follow them. Where to follow: • Discord: discord.com/invite/WJQpSUsbu… • Telegram: t.me/teneo_official_announce… • Instagram: instagram.com/teneoprotocol/ • TikTok: tiktok.com/@teneo.protocol • YouTube: youtube.com/@teneoprotocol • LinkedIn: linkedin.com/company/teneo-p… • Facebook (brand new page): facebook.com/people/Teneo-Pr… Questions or feedback? Discord is the place to ask.

Seven setup guides, one Teneo CLI. Choose the guide for the tool you already use, then list and query Teneo agents from the terminal. Claude Code, Codex, Cursor and VS Code each have a walkthrough. teneo-protocol.ai/get-starte…

Keep your Beacon running. Teneo Beacon shares your unused internet bandwidth with the network. Open the app, check it’s online, and keep your device awake. teneo-protocol.ai/beacon

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…