AI Compaction: Shorten the Context, Not the Business Record
Design long-running AI workflows with durable application state, explicit compaction boundaries and tests that catch lost constraints before actions execute.
Timour Spiridonov
ARGONAUTE DIGITAL / NOTES TECHNIQUES
Des retours concrets sur Next.js, TypeScript, le cloud et l’ingénierie assistée par IA.
Les articles sont actuellement rédigés en anglais.
Design long-running AI workflows with durable application state, explicit compaction boundaries and tests that catch lost constraints before actions execute.
Timour Spiridonov
Design AI tool approvals around immutable proposals, explicit arguments and server-side checks, then test the gap between confirmation and execution.
Timour Spiridonov
A practical evaluation plan for tool-using AI agents: verify persisted outcomes, protect permissions, inspect traces and compare releases honestly.
Timour Spiridonov
A practical architecture for AI-generated code: separate planning, authorization and execution, limit capabilities, and verify results independently.
Timour Spiridonov