Deterministic Core, Agentic Shell
DavidKPiano · x · 2026-07-20
The author outlines a system design philosophy developed over the past two years:
- Initially, allow the model to perform reasoning for all steps, observing its behavior to determine correctness.
- Gradually strip away the steps that can be replaced by deterministic logic.
This eventually leads to a "deterministic core + agentic shell" architecture: most reasoning is eliminated, yet the system remains more stable than purely deterministic approaches while handling a wider array of tasks.
More from coding & agent
- Dev builds interactive 3D product experience with GPT-6 Astra + Hyper3D Rodin — nikola_mr64990 · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11