ls -la ~/notes/methodology/
METHODOLOGY
15 articles
cd ../Run AI4SE as a Business: Double Diamond, Specs, then Skills
Treat AI4SE as a business and the deliverable cannot stop at slides. Consulting engagements can run Spec-Driven: use Design Thinking / Double Diamond to move through pains, opportunities, and solutions; clarify IT4IT-related specifications; then agentify and skillify—atomic Skills first, Goal-driven Agents later, plus Commands, Hooks, and MCP. The hard part is defining the problem and converging on a solution.
Design Thinking in AI4SE: Rhythm from the Double Diamond, Shape from Templates
In AI4SE, Design Thinking plus classic thinking templates (elevator pitch, journey maps, story maps, and the like), paired with AI brainstorming, sharply improves how teams define problems and converge on solutions. Using software requirements analysis as the running example, this post lays out a three-layer stack—Double Diamond for rhythm, templates for shape, AI brainstorm for the engine—and two playbooks: online elevator-pitch convergence and offline whiteboard workshops fed back into AI.
Lean Design-Dev Handoff: Cutting AI Codegen Token Cost by an Order of Magnitude
Traditional design-dev handoff relies on screenshots and natural language, so agents re-parse, re-translate, and re-emit redundant styles every turn. This article starts from three root waste patterns, proposes a tool-agnostic Design-to-Code DSL stack and HCP tiering, and uses Figma Dev Mode + MCP + Code Connect as a validation instance.
Designing the Project Knowledge Layer for Coding Agents: The Underestimated Piece of the User Harness
Strong AI coding depends on the user harness. An underestimated piece is the project knowledge layer—minimize load, lazy-load external knowledge on demand, and bound the taxonomy so the repo becomes a controllable knowledge surface, not a dump.
An AI4SE Workshop Is Not a Training Class: Staffing, Cadence, and Funnel Convergence
An AI4SE workshop shouldn't be a tool-demo week — it's about converging opportunity areas on a real project into a reusable playbook. The keys are staffing the right people, locking in a weekly/daily cadence, and persisting decisions through a Pair -> Group -> Plenary convergence funnel.
The Next-Step Dojo: An Airborne Kata for the AI Era That Lets Anyone Master Unfamiliar Tech Fast
Building on the deliberate practice of the traditional Code Kata, driven by a standalone kata folder + a Coding Agent + a spoken 'next step' — upgrading the path to learning new technology from 'find a tutorial' to 'drop in and get hands-on mentoring.'
Stop Arguing About What an SDD Spec Is: The Home Renovation Metaphor That Explains It Completely
The Spec in SDD isn't a document written after the fact — it's a delivery contract signed before development starts. It can be coarse or fine-grained depending on context, and its only real standard is eliminating every foreseeable ambiguity.
Anthropic's 2026 Agentic Coding Trends Report: Eight Predictions From Assistance to Collaboration
Distilled from Anthropic's 2026 report: the SDLC gets reshaped by agents, single agents evolve into collaborating teams, and long-running work builds entire systems — yet with AI used in 60% of work but only 0-20% fully delegable, human-machine collaboration remains the throughline.
Core Concepts of Agentic Coding Agents: Beyond the Model Lies the Harness
A Coding Agent isn't a chatbot that's better at writing code — reliability comes from the Harness: Instructions, Tools, Memory, Permissions, and the Verification Loop working together.
SDD Tools Compared: GSD, Spec Kit, OpenSpec, and Taskmaster
SDD is not one single tool — it's a spectrum running from spec purity to execution depth. Choosing the right one depends on whether you need to standardize process, manage existing-codebase changes, or orchestrate autonomous parallel execution.
AI4SE End-to-End Software Delivery Best Practices
The 2025-2026 industry consensus: AI is an amplifier, not a cure-all — end-to-end success depends on the closed loop of spec -> context -> execute -> verify -> measure, not IDE autocomplete.
AI4SE Pilot Transformation for Mid-to-Large R&D Organizations: From Uncertainty to a Verifiable Path
AI4SE is not a tool purchase — it's a transformation of how R&D works. Through four capability chains — SDD, Agentic, Harness, and Operating Model — a real pilot lets an enterprise form its own path.
The AI4SE Layered Technology Model: Effectiveness as the Foundation, Harmony as the Cross-Cut
How Pressman's classic four-layer model evolves in the AI era: the foundation is upgraded to Effectiveness, a new Harmony cross-cutting layer emerges, and the three layers change their meaning from 'human + tools' to 'human + Agent + Harness'.
Spec-Driven Development: Making the Spec the Single Source of Truth in the AI Era
SDD isn't a new concept, but it takes on structural significance in the AI4SE era — when code is generated by agents, the spec replaces code as the only human-readable source of truth.
Agentic Engineering Capability Maturity: From Vibe Coding to Production-Grade Collaboration
Agentic Engineering is not a binary switch — it's a maturity spectrum from "fully human-written" to "spec-driven and fully automated." Understanding where you sit on that maturity curve matters more than arguing over which extreme is better.