https://stayfresh.dev/ Static archive of workflow research and patterns for AI-assisted development. en-us Tue, 07 Apr 2026 00:00:00 GMT https://stayfresh.dev/workflows/claude-code-skills-stack/ https://stayfresh.dev/workflows/claude-code-skills-stack/ Tue, 07 Apr 2026 00:00:00 GMT A practical three-layer stack for Claude Code: decision, context, and execution. https://stayfresh.dev/workflows/modular-workflow-stack/ https://stayfresh.dev/workflows/modular-workflow-stack/ Tue, 07 Apr 2026 00:00:00 GMT Right tool, right job, right time: layered orchestration, typed agent delegation, human-in-the-loop gates, parallelism, and loops with real halting conditions. https://stayfresh.dev/research/context-is-a-budget/ https://stayfresh.dev/research/context-is-a-budget/ Tue, 07 Apr 2026 00:00:00 GMT More tokens do not create more truth. Context should be spent where it changes the next decision. https://stayfresh.dev/research/protocol-before-personality/ https://stayfresh.dev/research/protocol-before-personality/ Tue, 07 Apr 2026 00:00:00 GMT Shared artifacts and exit conditions beat charisma, cosplay, and fake seniority. https://stayfresh.dev/research/specs-as-shared-reality/ https://stayfresh.dev/research/specs-as-shared-reality/ Tue, 07 Apr 2026 00:00:00 GMT Agents do not share understanding. They share binding artifacts, versions, and tests. https://stayfresh.dev/research/what-is-prompting/ https://stayfresh.dev/research/what-is-prompting/ Tue, 07 Apr 2026 00:00:00 GMT Prompting is a constrained pipeline where tokenization, max tokens, and control tokens form the operational boundaries that determine agent behavior. https://stayfresh.dev/thesis/ https://stayfresh.dev/thesis/ Sun, 29 Mar 2026 00:00:00 GMT The hard position behind the archive: reward surfaces, legible architecture, and tools that lower comprehension debt. https://stayfresh.dev/workflows/anubis-github-pages/ https://stayfresh.dev/workflows/anubis-github-pages/ Sun, 29 Mar 2026 00:00:00 GMT How to put Anubis in front of a GitHub Pages site with a real reverse proxy and no proxy-loop nonsense. https://stayfresh.dev/workflows/instant-project-sync/ https://stayfresh.dev/workflows/instant-project-sync/ Thu, 19 Mar 2026 00:00:00 GMT Synchronize ticket queues against contract dates and repository evidence, with requirement reconstruction when docs are missing. https://stayfresh.dev/workflows/psay-agent-notify/ https://stayfresh.dev/workflows/psay-agent-notify/ Thu, 19 Mar 2026 00:00:00 GMT Local voice and Notification Center loops for agent completion, handoff, and operator recall. https://stayfresh.dev/workflows/project-ai-philosophy/ https://stayfresh.dev/workflows/project-ai-philosophy/ Wed, 18 Mar 2026 00:00:00 GMT A written position for bounded, evidence-backed AI use in delivery. https://stayfresh.dev/workflows/preference-toml/ https://stayfresh.dev/workflows/preference-toml/ Wed, 18 Mar 2026 00:00:00 GMT Use RLHF-shaped semantics in a simple config DSL for agent evaluation loops. https://stayfresh.dev/workflows/reward-rubric-dsl/ https://stayfresh.dev/workflows/reward-rubric-dsl/ Wed, 18 Mar 2026 00:00:00 GMT A small machine-readable format for scoring coding agent output. https://stayfresh.dev/workflows/prompt-patterns/ https://stayfresh.dev/workflows/prompt-patterns/ Wed, 18 Mar 2026 00:00:00 GMT Common prompt structures for reliable agent behavior. https://stayfresh.dev/workflows/agent-psychology/ https://stayfresh.dev/workflows/agent-psychology/ Wed, 18 Mar 2026 00:00:00 GMT Understanding how agents reason and respond to instructions. https://stayfresh.dev/workflows/ci-automation/ https://stayfresh.dev/workflows/ci-automation/ Wed, 18 Mar 2026 00:00:00 GMT Integrating AI agents with continuous integration workflows. https://stayfresh.dev/research/reward-engineering/ https://stayfresh.dev/research/reward-engineering/ Wed, 18 Mar 2026 00:00:00 GMT Why coding agents optimize the rubric more than the prompt. https://stayfresh.dev/research/reward-hacking/ https://stayfresh.dev/research/reward-hacking/ Wed, 18 Mar 2026 00:00:00 GMT How poorly designed metrics produce plausible but unstable code. https://stayfresh.dev/research/agents-md-effectiveness/ https://stayfresh.dev/research/agents-md-effectiveness/ Wed, 18 Mar 2026 00:00:00 GMT Evaluating repository-level context files for coding agents. https://stayfresh.dev/research/formal-verification-agents/ https://stayfresh.dev/research/formal-verification-agents/ Wed, 18 Mar 2026 00:00:00 GMT Property-based testing and specification generation. https://stayfresh.dev/research/enterprise-agent-design/ https://stayfresh.dev/research/enterprise-agent-design/ Wed, 18 Mar 2026 00:00:00 GMT BCG framework for production-grade agents. https://stayfresh.dev/research/persona-anchors/ https://stayfresh.dev/research/persona-anchors/ Wed, 18 Mar 2026 00:00:00 GMT Character-based instruction patterns for consistent agent behavior.