Post

Josh
@joshtuddenham.dev

1/ Your AI agent dispatches 3 tools in parallel. The database lookup times out silently. The merge node proceeds with whatever arrived. The agent generates a confident answer from 2/3 of the information it needed. Your logs look clean.

Josh
@joshtuddenham.dev

2/ This isn't hypothetical. It's the default behavior in n8n (append mode merge), LangGraph (implicit state), and every ReAct loop. If one branch fails quietly, nothing stops the agent from continuing with partial context.

Josh
@joshtuddenham.dev

3/ The fix is a join that blocks until every dispatched path resolves. Not "proceed when something arrives." "Proceed when everything arrives." Skip a tool? Fine. Place the done token directly. But the join won't fire until all tokens are present.

0 reposts0 likes

Josh
@joshtuddenham.dev

4/ This is a Petri net synchronization primitive. It's been in the formal methods literature since the 60s. I built it into an open-source safety layer for AI agents that works with the Vercel AI SDK.

Josh
@joshtuddenham.dev

5/ The library is called PetriFlow. MIT licensed, works today. Blog post with full benchmarks: joshtuddenham.dev/blog/agent-s... GitHub: github.com/joshuaisaact... Site: petriflow.joshtuddenham.dev

joshtuddenham.devYour Agent's Safety Net Is an If-Statement. Mine Is a Proof. | Josh TuddenhamTwo weeks ago, security researchers found over 1,800 exposed OpenClaw instances. Every vulnerability maps to the same failure mode - a code path that didn't hit the check. Petri nets fix this.