ID ↗
CS 319 · text: pangmandorin.kamil.web.id

CS 319 · Meeting 9 of 10

Horizons
and the Graph

Where the profession goes — and the July 2026 layer above loops: graph engineering.

Agenda · 100 min

  1. Three horizons, compounding skills (15')
  2. Graph engineering: vocabulary, decision table, gut check (35')
  3. Skeptics, honestly (10')
  4. Case: when Kirana's loops became a graph (10')
  5. Gut-check clinic + capstone kickoff (30')

Reading: chapters 18–19

Core concept · ch 18

Three horizons

NEAR · 2026–27

One foreman per team

3–10 humans + N agents. The foreman is the senior engineer designing loops. ← most of you, next year

MID · 2027–29

One foreman per project

Several loops in parallel; escalation only at four high-leverage moments (ch 13).

FAR

The AI manager is an agent

Humans define strategic context, ethics, the quality bar. Meta-decisions only.

Skills that compound across all three

Loop design · spec writing · verifier discipline · council pattern · context engineering · the managerial mindset. Deprecating: typing code, memorizing syntax, hand-debugging boilerplate.

The moment · ch 19

July 2026: "loops or graphs?"

Peter Steinberger — whose quote opens our textbook — asked on X: "Are we still talking loops or did we shift to graphs yet?"

Within days: a mock-eulogy ("Loop Engineering is dead. Long live Graph Engineering!"), the metaphor that stuck — "agents are graduating from while-loops to org charts" — and skeptics calling it a rebrand. No new capability shipped that week. Only a name for a design problem teams already had: one loop no longer being the right shape for the work.

The five-layer stack (where this course lives)

prompt
context
harness
loop
graph

cumulative: weak nodes make a weak org — M1–M8 are the layers under tonight's topic

Vocabulary · ch 19

A graph is three things

Nodes

Specialized agents or deterministic steps. One job each. "Steps I could inline" are not nodes.

Edges

Routing: straight · conditional · fan-out · fan-in. Drawn before they're coded.

Shared state

The object traveling the edges — task, notes, draft, verdict. State is what makes it a system, not a group chat.

The key identity

A loop is a one-node graph with an edge back to itself. Everything from M1–M7 lives inside one node. You never graduate from loops to graphs — you compose loops into graphs.

The discriminator

"The difference is who decides the path, the agent or you." Loop: agent picks its route to your bar. Graph: you declare the valid paths and checks.

Judgment · ch 19

The decision table — default left

SignalLoop is enoughReach for a graph
Shapeone job, clear finish linesplits into specialties that hand off
Parallelismsequentialfan-out, then a join
Tools/models per stepsame throughoutdifferent model or toolset per step
Control flowagent can free-roam safelyexplicit, auditable routing
Failure isolationbad step retriesone node fails without poisoning the rest
The verifierone check, one thingoverloaded: judging correctness+tone+safety+completeness at once

The last row is the sleeper: an overloaded verifier's fix is not a longer prompt — it's a separate reviewer node. The smallest honest graph is a dedicated reviewer node. Half of "I need a graph" is a weak verifier in disguise — strengthen the verifier, stay in the loop.

The migration path · and the honesty test

Loop → graph in five moves

1 keep the loop — it's node one

2 split off the failing step (almost always the reviewer)

3 write what node one hands node two — the state schema is the real work

4 fan-out only where you already iterate over N things

5 stop when the next node stops paying

Gut check: 4 questions

  1. split one context into specialized ones?
  2. real fan-out/fan-in (not a sequence drawn as boxes)?
  3. control flow readable as a diagram?
  4. did the objective and bar actually change?

0–1 yes: a loop wearing a graph diagram. 2–3: genuinely composing. 4: paradigm shift — and the work demanded it.

Intellectual honesty · required

The skeptics are right (about the word)

Harrison Chase (built LangGraph): "it's basically just langgraph?" — when the reference implementation's author isn't sure the word names anything new, register that.

David Khourshid (XState): directed graphs of states and transitions are decades-old CS.

@PawelHuryn: mechanisms (loops, graphs) are the wrong level — objectives and verification are the substance.

The filter this course runs: teams genuinely escalating to coordinated nodes? Yes. Picking nodes/edges/state a distinct skill? Yes. The word new, load-bearing, slop-free? No. — The label is optional. The escalation is real. Frameworks (LangGraph, ADK, MS Agent Framework) sell the boring infrastructure: checkpointing, resumability, HITL primitives. Hand-roll while small; import when faking those costs more.

Case study · part 9 of 10

When Kirana's loops became a graph

Week 11. Three loops running: triage, dependencies, digest. The digest loop kept failing — its verifier was judging completeness, tone, and invoice-number correctness at once (signal 6), and the researcher step was reading five sources one at a time (signal 2).

They ran the gut check: 3 yeses. Migration, five moves: digest loop becomes node one → reviewer split out (fresh context, read-only, different model) → state schema written — notes: list[Claim{source, quote}], the part the diagrams skip → researcher fans out ×5 → stop. Two nodes + one fan-out. No framework — a script and a queue.

Rasa's line for the retro: "We didn't upgrade our agent. We drew the arrow that was already there."

Clinic + kickoff · 30 minutes

Gut-check each other's loops

Pairs · 15'

Swap A6 loop descriptions. Run the four-question gut check on your partner's system — be the skeptic. Verdict: loop wearing a diagram, genuine composition, or paradigm shift? Which signal fired, if any?

Capstone kickoff · teams of 2 · 15'

Pick your capstone org (student club, family business, your own team, or extend Kirana). Skim the Meeting 10 deck together. One decision tonight: whose verifier is cheapest? — that's your first loop.

Assignment A9 · capstone kickoff · due at Meeting 10

The fleet audit + the graph

Part 1 — three-column audit
Every loop you ran this semester (including abandoned ones). Columns: loop · last landed outcome + date · queue at the human gate. Apply the standing rule to the bottom of the list: kill, defer, or ship. No prompt tuning.

Part 2 — graph design
For your capstone org: draw the napkin — nodes, edges, state object, the one conditional loop-back, where the human gate sits. Run your own gut check. Write the one-breath explanation.

Rubric
Audit honesty (dead loops named dead) 50% · napkin quality + gut-check self-verdict 30% · one-breath explanation 20%.

Next: capstone day. Bring the playbook, the audit, and the napkin.