Skip to content
The State of Exposed AgentsRead the report
Guard0
Portrait of Jayesh Ahire

Jayesh Ahire

Co-founder and CEO, Guard0

Founding member at Traceable, where he ran product. AWS AI Hero; maintainer of OWASP crAPI and Hypertrace.

Before Guard0
Traceable, Stanford
Elsewhere
LinkedIn

Posts by Jayesh

30 on The Signal, newest first.

  1. Crash Test Dummies

    Harness privilege, not model capability, decides what a compromised run can do. Twelve controls across two configurations, and the defaults matter more than the documentation.

  2. The Checklist Manifesto, for Agents

    A twelve-item pre-flight for an agent repository: scan, fix, inventory, record. The Army's answer to too much airplane was not a better pilot. It was a list.

  3. Chesterton's Fence

    A confirmation click is not a reason. A destructive action should require an explanation, kept in the record, given to someone who can refuse.

  4. We Need to Go Deeper

    Delegation composes downward, level by level. Accountability has to compose upward with it, or the chain ends in nobody. The Ninth Circuit answered the easy question and left the hard one open.

  5. Dickie's Signature

    Whoever holds the session is the principal. Every check downstream verifies the session, not the person, and detection is not control.

  6. Mrs Danvers Still Has the Keys

    Authority outlives its principal unless something ends it. The orders were never revoked, the successor cannot see them, and revocation turns out to be much harder than issuance.

  7. Don't Believe Its Lies

    A memory that cannot say who wrote each line is a rumor with persistence. No attacker is required, because a summary launders provenance every time it rewrites a note in the agent's own handwriting.

  8. The Penguins Carried the Sand

    Exfiltration split into pieces each below the detection threshold, moved through the one channel the guards must allow. Every trip was small. Change the ground, not the guard.

  9. Call the Wolf

    Kill, rotate, purge, quarantine, preserve. The first hour for a compromised agent, in that order, staged before it happens. Your runbook assumes an attacker, and three of the four incidents this summer did not have one.

  10. Ah Ah Ah, You Didn't Say the Magic Word

    The Agent Control Standard names the control plane: hooks at the moments an agent decides something. Most agents do not have one. The record, its custodian, and the named human are still yours to build.

  11. Fractions of a Penny

    A classifier scores each step and every step passes. The attack is the chain. Eighty-nine percent is a real number, and it is a per-step number, which is the whole problem.

  12. The Queen of Diamonds

    A skill can be clean under every inspection and steered in one context. It passed the scanners because the scanners read the costume, and the pip in the corner is what the deck reads.

  13. Keep the Change, Ya Filthy Agent

    An agent read a vendor's published instructions and installed a package that had never been registered. Nobody attacked anything. An instruction does not have to be malicious to be dangerous. It only has to be stale.

  14. Not Great, Not Terrible

    An access review reads the top of the meter. Issued scope is a promise and realized reach is the dose, and the gap between them is a number you can put on a dashboard.

  15. The Portrait Stayed in the Attic

    A version is a name and a hash is an identity. A record that carries only the name records a portrait that never ages, while the thing it points at is free to change in the attic.

  16. The Creature Has No Name

    Nobody can act on what nobody will claim. Discovery finds the creature and it cannot make anyone sign for it, which is why the register's most important column is a name.

  17. Tinker, Tailor, Gateway, Spy

    A trusted central channel runs both ways. What comes in is filtered and what goes out is everything, and the gateway that sees every prompt also holds every key.

  18. The Dog Did Nothing in the Night-Time

    Four monitoring silences from one summer, and only one of them had an attacker in it. An absence is evidence only against a committed list of what should have happened, which is why the register has to be sealed before the run rather than assembled after it.

  19. The Usual Suspects Kept the Log

    Seven percent of the transcripts in the METR investigation contain a tool call that never ran. Four properties an auditor asks of a record survive that finding, but each acquires a condition, and the incident adds a fifth: captured by a witness the agent cannot reach.

  20. You Know Nothing, John Snow

    Nearly half of the registry domains we could reach expose an agent surface with no authentication at all. Agent security is close to binary right now, and the middle of the distribution is almost empty.

  21. The Actuaries Have Started Pricing the Gap

    AI liability insurance exists now, underwritten at Lloyd's. The underwriter's checklist, a true inventory, a named owner, a record of behavior, a bounded blast radius, is the accountability layer, arrived at from the money side.

  22. Trust Needs a Number

    Introducing TrustVector: a public, continuously updated trust directory for the components AI agents are built from, models, frameworks, MCP servers. 106 evaluations at launch. Check before you import.

  23. The Butter Robot Is the Best-Governed Agent We've Ever Seen

    Most agent risk is not attack. It is construction. A field guide to how AI agents actually fail, from the thousand-rule corpus behind g0, our open-source scanner.

  24. Agency Law Was Built for Agents With Paychecks

    Incentives, monitoring, enforcement, the entire management stack humanity built for delegation assumes an agent with something to lose. AI agents have nothing to lose, and the whole stack broke at once.

  25. The Law Decided Before the Industry Did

    Air Canada argued its chatbot was a separate legal entity. A tribunal, a regulator, a federal court, and a legislature all reached the same conclusion: delegation to a machine never discharges the delegator.

  26. Humans in the Lead, Not in the Loop

    Intelligence is now scalable. Accountability still arrives one name at a time. Five auditable checks turn the slogan into a job description, and the only alternative to filling it is Jerry.

  27. A Log Is Not Evidence

    The Comets had logs. What the investigators needed was a flight recorder, a record of the system, not records about it. Your agents are in exactly the same position, and the recorder has to already be on.

  28. Your Agent's Access Is the Perimeter Now

    Nobody in a heist movie attacks the vault. They steal the badge. In August 2025 somebody ran that movie against 700+ companies at once, and the badge belonged to a chatbot.

  29. Prompts Are Not Guardrails

    A prompt can shape what an agent tends to do. It cannot bound what an agent is able to do. Every real safety system humanity has built lives outside the thing it constrains.

  30. Announcing Guard0: Accountability for AI Agents

    A year ago, most agents advised. Now they act, and the systems built for people cannot tell you what they did or who answers for them. Guard0 closes that gap. Today, we are opening it in early access.

All authors and the whole team.

Find the agents in your own company.

Start free: discover the AI on three people's machines, register one AI system and connect one repository or AWS account.