#workflow

workflow shows up across 3 section(s) and 17 page(s) in this workspace. Use this page as a topic map, not just an archive.

Start here

If you are new to this topic, begin with the strongest entry points first, then move into related notes and supporting material.

Where it appears

  • Systems 8 page(s)
  • Shelf 8 page(s)
  • Sticky Notes 1 page(s)
systems

AI Agents vs AI Workflows

A practical explanation of the difference between autonomous-seeming agents and controlled workflows, and why the distinction matters in production systems.

systems

Agent Instructions and Handoff as an Operating System

A practical architecture for running AI agents reliably using instruction contracts, handoff memory, and measurable quality gates.

systems

Designing Reusable AI Skills

How to design AI skills with clear boundaries, input and output contracts, tool limits, side-effect controls, and escalation paths.

systems

Evaluation as a Runtime Discipline

Why evaluation should live inside the operating loop of an AI system instead of being treated as an occasional review ritual.

systems

From Ad-Hoc Prompts to Repeatable Agent Workflows

A practical case study showing how structured instructions, handoff memory, and quality gates improved consistency and coverage in this repository.

systems

Skill Evaluation and Versioning

How to define expected behavior, detect regressions, version skill changes safely, and decide when rollback is the right move.

systems

Skills vs Prompts vs Agents

A systems-level comparison of prompts, skills, workflows, and agents so teams can stop mixing up instruction surfaces with execution architecture.

systems

What a Skill Is in AI Systems

A practical definition of skills as reusable execution units that sit between prompts and workflows in modern AI systems.

shelf

Ollama launch: integration handoff

A new launcher flow that hands local models into tools like Codex and OpenCode.

shelf

Notes: Knowledge Surface Weekly Map

A weekly pass format for keeping note structures coherent, linked, and retrieval-ready.

shelf

Notes: Observability Logbook Pattern

A compact weekly review format for tracing decisions, evidence, and outcomes in AI workflows.

shelf

Notes/Tools: a daily Obsidian scratchpad

One file per day, minimal structure, and a quick export habit.

shelf

Notes/Tools: a plaintext logbook

Short markdown logs + ripgrep to keep the archive searchable.

shelf

Tools: Git

The simplest way to keep experiments honest and reversible.

shelf

Everything as Code deck

A control-plane framing where policy, infrastructure, workflows, and quality checks become versioned artifacts.

shelf

AI skill design templates

Three compact templates for defining, reviewing, and composing AI skills as reusable execution units.

sticky notes

Observe before you optimize