cat ~/ai4se/README.md
## Methodology • Process • Tools • Harmony • Measurement
Notes on how AI4SE / Agentic Engineering reshapes methodology, process, tools, human–agent collaboration, and productivity measurement.
man -k ai4se
Methodology — SDD, Agentic Engineering, AI4SE system
Process — human–agent workflows, review pipelines, loop design
Tools — MCP, Harness Engineering, browser automation
Harmony — HITL/HOTL/HOOL, Planner/Generator/Evaluator
Measurement — DORA, SPACE, DevEx, agent effectiveness
grep -r "featured" ~/notes/
The Cordis preprint from DeepSeek-affiliated authors is long, but its core fits two dimensions of spatiotemporal composability: revertible side effects and reactive dependencies. This piece critiques length and jargon, then explains the mechanisms, confluence, and validation limits in engineer language.
A first-principles abstraction of AI Harness as function composition: freeze the foundation map M(x), orchestrate the outer chain H. Single-turn is strict multi-layer composition; multi-turn fuses composition with a state machine. Optimize H, not weights by default.
After AI enters software engineering, efficiency comparisons often become apples-to-oranges. This article proposes three anchors—comparability (fixed backlog / team / window), separability (freeze the complexity baseline), and honesty (expectation, not fake measured ROI)—plus reading rules for throughput, cycle time (speed framing), and paired aggregation, with common anti-patterns.
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.
AI agents and automation scripts can take on standardized execution, but only humans can decompose, decouple, and bound complex work. The bottleneck is not model ceilings—it is human systems thinking and abstraction. Human–machine handoff is essentially: humans define, machines execute.
AI moves the bottleneck from writing to review. Artifacts widen beyond code and review spans the E2E path—humans cannot inspect every output. This piece argues for layered review (scripts → AI → humans): automated review can run inside the inner loop, while the team uses the outer loop to jointly own whether those methods themselves are sound—and how to correct them when they drift.
dpkg -l | grep ^i