
What an Unverifiable Agent Chain Costs You in an Audit
Why durable execution isn't enough for agent systems, and how Diagrid Catalyst, built on Dapr, brings verifiable execution lineage to agent workflows.

Why durable execution isn't enough for agent systems, and how Diagrid Catalyst, built on Dapr, brings verifiable execution lineage to agent workflows.

Watch the on-demand recording: the Dapr maintainers walk through what's new in 1.18, with live demos of workflow access policies, tamper detection, concurrency limits, and Dapr Agents.

Open source workflow project Dapr's 1.18 release introduces "verifiable execution" – cryptographic signing, history propagation, and attestation built directly into the workflow engine.

Catalyst now shows where workflows fail and reruns them in bulk from the failed step, finds workflows waiting on human input so you can unblock them, and runs in Catalyst Cloud or inside your own Kubernetes cluster.

Dapr 1.18 brings workflow history propagation, tamper detection, access policies, global concurrency limits, and secure MCP, so production workflows and agents stay trustworthy, controlled, and auditable. All these features are available in Catalyst today.

Learn how to give any LLM agent reliable, real-time web knowledge without relying on the model to decide when to search. We'll build a durable expert agent end-to-end using Dapr Agents' new Hooks system, Tavily, and Chainlit.

Latest release enables organizations to prove the authenticity, integrity, and lineage of workflow and AI agent execution. New capabilities digitally sign execution history, propagate trusted provenance across services, and generate attestations that allow auditors to verify exactly how work was performed.

Dapr 1.18 brings attestation, provenance, and tamper-evident history to workflows and AI agents, so teams can verify how execution happened, not just recover from failure.

Join the monthly Dapr Community Call for real-world use cases from EVA Systems, Workflow Access Policies deep dive, .NET SDK updates, and live Q&A with the maintainers.

Most agent projects stall before production, and the model is rarely the cause. The four failure modes behind it: durability, security, cost, and observability.

Join Diagrid at LDX3 London — the Festival for Modern Engineering Leadership. Find us at Booth 302 and get 10% off tickets with code DIAGRID.

Yaron shares how building on established open source standards can help developers manage LLM costs, optimize day-to-day operations, and streamline the architecture behind Agentic AI.

Yaron shares how building on established open source standards can help developers manage LLM costs, optimize day-to-day operations, and streamline the architecture behind Agentic AI.

A recap of the May 20, 2026 Diagrid webinar on why agents need cryptographically attestable identity, why MCP gateways are not enough, and how SPIFFE, Dapr, and Catalyst bring zero trust to agentic systems.

A guided builder for any of Dapr's 130+ components, right in the Diagrid Dev Dashboard.

A guided builder for timeout, retry, and circuit breaker policies, right in the Diagrid Dev Dashboard.

AI agents lack verifiable identity, enforceable authorization, and tamper-proof audit trails. See how Diagrid Catalyst delivers cryptographic identity, zero-trust policies, and a signed chain of custody for production AI agents.

Learn why API keys are not enough for agent identity and how Dapr and Diagrid Catalyst enforce scoped delegation and access control for agents and MCP servers.