---
id: "action-hardwire-processes"
type: "action-item"
source_timestamps: ["00:09:38", "00:10:25"]
tags: ["system-architecture", "workflow-design"]
related: ["concept-skill-vs-process", "contrarian-agents-need-rails", "quote-ripping-up-railroad"]
action: "Hardwire deterministic routing and logic between agentic skills."
outcome: "Reliable, predictable workflows that do not suffer from agent hallucination or skipped steps."
speakers: ["Nate B. Jones"]
sources: ["s53-agent-100x-review-3x"]
sourceVaultSlug: "s53-agent-100x-review-3x"
originDay: 53
---
# Hardwire Deterministic Processes

## Action

**Hardwire deterministic routing and logic between agentic skills.**

## What to Do

Instead of prompting an agent to manage an end-to-end workflow:

1. Write **deterministic code** to handle routing and data passing — the *"in-between glue."*
2. Decompose the workflow into named, bounded skills.
3. Trigger the agent **only at specific nodes** to execute discrete skills.
4. Validate inputs/outputs at every boundary.

## Outcome

Reliable, predictable workflows that do not suffer from agent hallucination or skipped steps. The architectural justification is in [[concept-skill-vs-process]], reinforced by the contrarian argument in [[contrarian-agents-need-rails]] and dramatized in [[quote-ripping-up-railroad]]. Adjacent tooling: state-machine frameworks like LangGraph that enforce deterministic rails around skill calls.