Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

YPO Technology Network AI Brief

YPO Technology Network AI Brief artwork

AI Always-On Agents: The Real Risk Is They Break Silently

Nov 17, 20266 minAudio

On 13 November 2026, Anthropic published a guide on agents that keep working when nobody is in the chat. Always on is the experience, not staying awake all night. The agent sleeps, wakes for a short run, saves what happened, and goes back to sleep. Hours it saves are capacity, not cash. Unattended agents rarely go rogue. They stall, stop, or break silently. Run an agent attended first, then let it run on its own, and have a second agent check the work. If a team or vendor cannot say how the inbox, timers, memory, permissions, and outbox work, the agent is not ready. The later test: would you know if it stalled overnight. Key takeaways. Always on is the experience, not the runtime. Hours saved are capacity, not cash. Run attended first, then unattended, with a second agent reporting success and failure. Automatic replies are a comfort-level choice. Automatic drafting is a different decision. Start the agent quiet, between over-notification and missing what you need to know. Five building blocks (Anthropic). Event inbox. Every trigger writes to one durable queue, with one active worker. If the worker dies, a new one can retry. Ask: does every trigger go through one queue, and what happens if the worker dies mid-run. Timers. Follow-ups the agent sets for itself, and recurring schedules. Ask: can I see them, and can I turn them off. Memory. Keep only what it cannot look up again. Save a pointer if the fact already lives elsewhere. Ask: what does it keep, where does that live, and can we read it. Permissions. A run holds a person's access. Each action should proceed, block, or wait for a named person's approval. A proxy outside the agent adds the password or the key. Ask: does the agent hold the credentials, which actions wait, and what if that person does not answer. Outbox. The user gets the outcome and a few details, not a live stream of every step. Ask: how does it decide when to message someone, can we start it quiet, and is there a log of sent and unsent messages. Checklist (as spoken). You do not need to write this down as you listen. Run the agent attended first. Then let it run on its own. Why: you learn how it behaves while someone is still watching. Have a second agent check the work and report success and failure. Why: they stall, stop, or break silently, and the job can look like it is still running. Write down which messages can go out on their own, and which wait for a person. Automatic replies are a comfort level. Automatic drafting is a different decision. Why: drafting can go first. Sending is still a separate yes. Ask the five questions above. Why: if a vendor cannot answer them, the agent is not ready to run unattended. Once it is running, ask whether you would know if it stalled overnight. Why: that is a better test than asking whether it ever went rogue. Terms. Always-on agent: feels unattended, but sleeps between short runs. Memory: what is kept between runs, and is inspectable. Credential proxy: inserts the password or key. Outbox: how the outcome reaches a person. Start quiet: fewer messages first, then earn attention over time. Examples named. We run agents unattended after an attended check, with other agents reporting success and failure. They rarely go rogue; the watch is for silent stall. Some messages get automatic replies, many do not. Most emails get an automatic first draft. Drafting is not sending. Sources: Anthropic guide; Elvis Saravia on X. The AI Brief from the YPO Technology Network is a daily executive briefing on the AI developments that matter to business leaders. Hosted by Stephen Forte.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. AI Vendor Keys: Cursor's Breach And Why Agent Logs Are Sensitive Data

    Nov 20, 20267 minAudio

    Cursor's breach didn't start with a bug in the app. It started with an access key Cursor issued to a vendor, Fireworks. That key opened old coding-agent session logs, some still holding pasted credentials, which led...

    Credit the people on this episode

  2. AI Plumbing: Microsoft Just Ran The Pipes Through Your Tenant

    Nov 19, 20267 minAudio

    Microsoft Ignite's biggest news was plumbing: who each agent is, who it reports to, what it can touch and what it costs, built into the Microsoft 365 tenant you already pay for. Satya Nadella called Agent 365 Business...

    Credit the people on this episode

  3. AI For CEOs: Hear What The Summary Leaves Out

    Nov 18, 20266 minAudio

    Episode 200. Stephen started this show because almost nobody was talking to CEOs about AI: plenty of tabloid headlines and valuations, little on where the technology is going, what a busy CEO needs to know, and how to...

    Credit the people on this episode

  4. AI Vendor Risk: When Outlook Goes Down, Your Agents Go With It

    Nov 16, 20266 minAudio

    Microsoft's Outlook and much of Microsoft 365 went down late Thursday 12 November and were not fully restored, by Microsoft's public account, until Saturday morning 14 November. Microsoft says this was a technical...

    Credit the people on this episode

  5. AI Computer Use: Connectors First, Screens Last

    Nov 14, 202613 minAudio

    Can your AI actually use your computer? Claude, ChatGPT, and Grok Bot all can, but there are four very different ways an agent touches your systems. Stephen Forte explains why legacy work still needs computer and...

    Credit the people on this episode