ThirdKey — Zero Trust for AI
001 — Newsroom

News & press.

Announcements, product releases, and media coverage from ThirdKey. For interviews, briefings, or background on our work in zero-trust AI agent infrastructure, reach the press desk directly — we typically respond within one business day.

002 / Announcements

Recent releases.

Product launches, specification publications, and milestones. Older items are archived but stay reachable by DOI.

May 5, 2026
Press release

ThirdKey AI demonstrates elimination of AI agent exploits across multiple attack classes

3,760-trial comparative evaluation across seven hosted LLMs and three substrates: Symbiont records 0 successful exploits out of 560 trials on pure-action vectors. Docker sandboxing fails to stop 88% of filesystem-enumeration, 89% of network-boundary, and 84% of state-mutation attacks. Orchestrator-injection cut from 59% to 3.6% (1.5% excluding GPT-5). Companion preprint DOI 10.5281/zenodo.20043247.

May 1, 2026
Specification

ToolClad specification published: declarative tool interface contracts for agentic runtimes

A specification for .clad.toml declarative tool contracts — typed parameters, validation, invocation, output parsing, and Cedar policy across CLI, sessions, and governed browser execution. Replaces freeform shell generation with allow-list-validated tool invocation. DOI 10.5281/zenodo.19957595.

April 26, 2026
Preprint

ThirdKey publishes “Typestate-Enforced Agent Loops” preprint

A compile-time approach to enforcing policy gates in AI agent loops via typestate encoding. Evaluated across nine hosted LLM providers — 263 forbidden tool-call attempts refused without execution at 30–95µs per check. DOI 10.5281/zenodo.19746723.

April 17, 2026
Specification

Open Agent Trust Stack (OATS) specification released

A system specification for zero-trust AI agent execution — declarative tool contracts, the Observe-Reason-Gate-Act loop, and structural separation of policy from model influence across five architectural layers. DOI 10.5281/zenodo.19636533.

All preprints on the research page →
003 / Press

Press contact.

For interviews, embargoed briefings, or technical background, email the press desk. Founder Jascha Wanger is available for comment on AI agent safety, policy-governed runtime, and supply-chain integrity.

Press desk

Talk to a human about ThirdKey.

We respond to journalists, analysts, and conference organizers within one business day. For sales or technical questions, please use sales@thirdkey.ai instead.

About ThirdKey

One-paragraph boilerplate.

ThirdKey is an AI safety and security company building open, interoperable trust infrastructure for autonomous AI agents — cryptographic identity, schema verification, declarative tool contracts, and a policy-governed runtime. The company ships four open-source primitives (Symbiont, SchemaPin, AgentPin, ToolClad) and a commercial enterprise tier of its agent runtime for security teams running agents in production.

A guarantee that can’t be written down isn’t one.
— ThirdKey, research principle