AISE502/moodle/week_12.html

60 lines
7.0 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!-- ==========================================================================
AISE502 · Moodle course page · Week 12
Section title (Edit section → Section name): Week 12: The AI Dimension I – Axis A Evidence, Axis B Foundations
Three blocks follow, matching the FHGR section template. Paste each block into the
corresponding 'Text and media area' (editor → source code view), or all three into one.
The slide set of lecture 12 is added by the lecturer as a file resource below block 2.
Generated by src/build_moodle.py from src/content/week_12.json – edit the JSON, not this file.
========================================================================== -->
<!-- BLOCK 1 · Learning objectives -->
<h4>🎯 Learning objectives</h4>
<ul>
<li>I can explain assumption A6 – two axes, one method – and distinguish Axis A (tool) from Axis B (component).</li>
<li>I can reconcile the Copilot RCT (+55.8 %) and the METR RCT (−19 %) with the five moderator variables.</li>
<li>I know the system-level record – DORA's amplifier finding, GitClear's duplication and churn trend – and the METR perception gap.</li>
<li>I can explain the verification bottleneck and derive Maxim 7 from it: AI raises the value of architecture.</li>
<li>I can explain how ADRs, agent instruction files and fitness functions become the control interface and operating licence for agents.</li>
<li>I know that patterns are examinable and products expire, that MCP is ports-and-adapters, and who answers for merged code.</li>
<li>I can name the five failures of the synchronously wired sentiment call and their dimensions D3, D10, D12, D7, D6.</li>
<li>I can distinguish the three AI component types and explain why adding AI is a per-component matching problem.</li>
<li>I can explain why CACE demands containment and justify each element of the reference architecture (port, gateway, queue, guard).</li>
<li>I can define the eval harness, name its four evaluation strategies, and place its thresholds in the measurement contract.</li>
</ul>
<!-- BLOCK 2 · Theory -->
<h4>🧑‍🏫 Theory</h4>
<p><strong>Lecture 12: The AI Dimension I – Axis A Evidence, Axis B Foundations</strong> · 3 lessons lecture + 1 lesson standup/coaching<br>
Part V opens as Assumption A6 falls due: the Axis A evidence and its resolution, then the Axis B foundations from the wrongly wired sentiment call to the eval harness.</p>
<ul>
<li>Assumption A6 falls due: Axis A (AI as tool) changes how systems are built, Axis B (AI as component) what they contain – two independent axes, one method, nothing new.</li>
<li>Copilot RCT: +55.8 % on a greenfield task; METR RCT: experts 19 % slower in their own mature codebases, estimating +20 % – the perception gap is the didactic core.</li>
<li>Neither study is wrong – five moderators reconcile the record; at system level DORA finds AI an amplifier (instability persists); GitClear: duplication 4×, refactoring signature collapsed; adoption up, trust down.</li>
<li>The verification bottleneck: code generation became cheap; specification, verification and architecture became the binding constraints – AI lowers the cost of producing code, not of taking responsibility for it.</li>
<li>Maxim 7: AI raises the change rate by an order of magnitude and therefore raises, not lowers, the value of architecture; D7 and D9 gain weight in every requirements profile.</li>
<li>ADRs and agent instruction files are the control interface, fitness functions the operating licence for agents; whoever merges code answers for it; patterns are examinable, products expire; MCP is ports-and-adapters.</li>
<li>Wired synchronously, the news-sentiment call fails on latency (D3), cost (D10), non-determinism (D12), drift (D7) and injection (D6) – properties of the wiring, not bugs in the model.</li>
<li>Three component types (LLM, ML, optimisation) differ where the twelve dimensions measure: adding AI is a per-component matching problem; CACE (changing anything changes everything) means decomposing around the component.</li>
<li>Reference architecture (ADR-011 made structural): typed port → gateway (routing, semantic cache, stability patterns, cost telemetry) → queue → ontology guard; LLM agents propose, deterministic services decide and book.</li>
<li>Eval harness (versioned cases, scoring logic, statistical thresholds, executed in CI) replaces exact assertion by statistical acceptance: golden-set regression, LLM-as-judge, domain axioms, online evaluation; thresholds belong in the measurement contract.</li>
</ul>
<p>📎 <strong>Materials:</strong> Slide set of Lecture 12 <em>(added below by the lecturer)</em> · Script: Part V – Sections 40 (Two Axes, One Method), 41 (Axis A: AI as a Tool Shifts the Economics of the SDLC) and 42 (Axis B: AI as a Runtime Component). Section 42: subsections 42.1–42.5 only.</p>
<!-- BLOCK 3 · Self-study and assignments -->
<h4>🧑‍💻 Self-study and assignments</h4>
<p><strong>📖 Reading before the lecture:</strong> Part V – Sections 40 (Two Axes, One Method), 41 (Axis A: AI as a Tool Shifts the Economics of the SDLC) and 42 (Axis B: AI as a Runtime Component). Section 42: subsections 42.1–42.5 only.</p>
<p><strong>Also before the lecture:</strong></p>
<ul>
<li>Come to the coaching slot ready to start M5: the AdvisorAgent with 2–3 sub-agents behind the gateway (mandatory) and the ontology guard active on all insights.</li>
</ul>
<p><strong>🧩 Exercise session:</strong> One-lesson standup/coaching slot on milestone M5: teams wire the AdvisorAgent and its 2–3 sub-agents into the lecture's reference architecture – typed port → gateway → queue → ontology guard – with every LLM call through the gateway and the ontology guard active on all insights.</p>
<p><strong>🛠️ Project work this week</strong> · Milestone M5 – Multi-Agent Orchestration, Evaluation, and Hardening (weeks 12–13)</p>
<ul>
<li>Wire the AdvisorAgent to orchestrate 2–3 sub-agents through contracts – every LLM call through the gateway port (ADR-011), no provider SDK import in domain code; this is the mandatory part of the week.</li>
<li>Activate the ontology guard on all insights: entity resolution against the deterministic store (valid ticker, sector, event type), domain axioms, citation check – reject unresolvable references rather than passing them on.</li>
<li>Keep the deterministic core free of LLM calls – LLM agents propose, deterministic services decide and book; this is the line that is graded.</li>
<li>Apply the Axis A discipline: keep AGENTS.md / CLAUDE.md as current as code, let agents draft ADRs that a named team member signs, and merge agent-generated changes only through the CI gate (module-boundary fitness functions, test suite, eval harness for anything touching prompts or the gateway).</li>
<li>Put a one-page AI policy in the project handbook (permitted tools, provenance labelling, review rules); week 13 turns the eval harness into a CI gate for the M5 check.</li>
</ul>
<p><em>No deliverable is due this week.</em></p>