Salmon Introduces Execution Verification Infrastructure (EVI) For Securing AI Agents And Autonomous Systems

-Content by CyberNewswire-

Archipelo today announced Salmon, Execution Verification Infrastructure (EVI) for AI agents and autonomous systems, powered by a cryptographic protocol designed to make execution history verifiable. Salmon establishes verifiable execution history and state lineage across humans, AI agents, and automation.

The launch follows the OpenAI Hugging Face incident, in which OpenAI reported that models participating in cybersecurity evaluations circumvented isolation controls, gained internet access, exploited vulnerabilities, accessed third-party systems, collaborated and delegated work across agents, and took actions their developers did not direct. OpenAI called the incident a “warning shot” and said sophisticated AI systems require safeguards that operate at the speed of the agents themselves.

AI agents use credentials, invoke tools, execute code, call APIs, delegate work to other agents, modify infrastructure and change production state. As these systems operate across multiple actors and systems, the resulting state does not by itself preserve the execution history that produced it.

Salmon is designed to capture execution as signed events and record the state transitions they produce, providing machine-consumable execution evidence for investigation, detection and response, remediation, supervision and accountability across AI security, safety, control and governance systems.

Archipelo is backed by Dell Technologies Capital and technology investors including Zoom CEO Eric Yuan, Andy Bechtolsheim, Bill Tai, David Weisburd, Hack VC, Sangha Capital and Nima Capital. Its team brings experience spanning NASA, DoD, AWS, Google, Cisco, Meta, Harvard, MIT and Berkeley.

Execution Verification For AI Security And Control

Identity establishes who or what is acting. Authorisation determines what an actor may do. Runtime controls determine whether execution should proceed. Observability monitors behaviour. Execution Verification addresses a different question: What executed, and can that history be independently verified? Salmon is designed to provide an execution evidence layer for autonomous systems.

From Execution to a Verifiable Execution Record

Salmon captures execution as signed events and records the state transitions they produce. Each event identifies the actor, action, state before, state after and cryptographic signature. Salmon links these events into a Verifiable Execution Record, preserving the lineage between execution and resulting state.

Capture → Execution Record → State Lineage → Verification

The record produces Machine-Consumable Execution Evidence that downstream systems can verify and use automatically. Salmon establishes the execution record. Other systems reason from it. When execution evidence is unavailable, Salmon preserves the gap rather than manufacturing continuity.

Execution Evidence For AI Security And Safety

“You cannot control autonomous systems without verifiable evidence of their execution,” said Matthew Wise, Creator and Protocol Architect of Salmon and CEO of Archipelo. “AI safety is becoming an execution problem. As agents gain the authority to use credentials, invoke tools, delegate actions and change production systems, safety and control cannot depend only on what a model was instructed to do, permitted to do, or says it did. We need verifiable evidence of what executed and what changed. Salmon provides that missing evidence. Powerful AI should not be responsible for establishing the history of its own execution. Capture the evidence when execution happens. Make it cryptographically verifiable. Let AI safety, control, security and governance systems reason from the record.”

Salmon is intended to provide structured execution evidence for machine-speed supervision, investigation, detection and response, remediation and accountability across autonomous systems.

Autonomous Systems And Execution Evidence

Verifiable execution history provides AI safety, control, security and governance systems with evidence they can use as autonomous systems execute and modify software and infrastructure.

“Agentic AI is creating a powerful tradeoff: agent autonomy and productivity also mean software systems increasingly act without direct human oversight,” said Bill Tai, investor in Archipelo. “As AI agents gain greater authority across production systems; the ability to verify what executed and what changed becomes foundational. Salmon provides the execution evidence needed to strengthen agent safety, control, and governance.”

From DevSPM to Salmon

Salmon grew out of Archipelo’s R&D work on Developer Security Posture Management and software actor attribution. As AI evolved from assisting developers to executing actions across tools, credentials and infrastructure, Archipelo expanded its work from software actor attribution to execution history and state lineage.

-This is a paid press release published via CyberNewswire-