Stop Defining Agent Workflows in Plain Text: Why Deterministic Code Beats Fragile Prompts
gerardsans · x · 2026-11-12
In a debate on agent orchestration, gerardsans argues that even in modern agentic systems, defining complex workflows in plain text is a classic bad practice.
Key points: turn workflows into code for predictable behavior; never use a distribution-based system as a Turing machine due to fragility — deterministic runtimes exist for a reason; and most researchers lack the software engineering expertise to make good calls here.
Related event: Paper proves more reasoning tokens unlock harder problems, sparking debate(3 posts)→
More from coding & agent
- AI agent finds sponsor leads via People Search MCP: 10 contacts for under $2 — cneuralnetwork · 2026-11-12
- Microsoft Ignite to host lab on taming agent sprawl with Agent365 and Foundry — donasarkar · 2026-11-12
- Old mental models now hurt products more than coding agents' limits, says Jon Finger — mrjonfinger · 2026-11-12
- PydanticAI 2.57.0 adds ApprovalReviewer: a second model pre-clears safe agent tool calls — KhuyenTran16 · 2026-11-12
- Engineer says coding agents cost him understanding of his own code, proposes intent-as-source-of-truth — the_juan_1 · 2026-11-12
- Agent kill switches are reactive: shared API keys mean you can't spot a rogue agent — victorialslocum · 2026-11-12