aPlanner is in MVP validation (Oct–Dec 2026). Figures are design targets. Join the 2027 Korea pilot →
INNOVATION & IP

Yield-aware, scenario-driven scheduling for multi-step wafer processes

The novelty is in combining three things that today live in three different heads: yield, constraints and scenarios. Two of the three are planned as KIPO patent applications.

Join the 2027 Korea pilot programTalk to the founder
Rationale chain behind an explained schedule change
Rationale chain — event → constraints hit → alternatives rejected → KPI delta

Three innovations

Each card answers the same three questions: what it is, what advantages and benefits it brings, and how the IP is protected.

01

Yield-aware constraint scheduling

What it is

The optimizer takes live yield and bin distributions per process step as inputs, so wafer starts, expected good die and bin mix are planned together across 50–100+ steps — instead of scheduling starts and hoping the yield follows.

Advantages & benefits
Plans that survive ±10–15% weekly yield swings
Fewer wafer starts for the same output (target 5–15% yield-adjusted gain)
Bin allocation that maximizes revenue per wafer
No incumbent APS models yield inside the schedule
KIPO patent application #1 — planned Dec 2026
02

Node-migration planning

What it is

Models learning curves, ramp rates and capacity shifts when a line moves 176L → 236L → 300L+, planning old and new nodes as one system with shared tools and demand.

Advantages & benefits
Smooth transitions without demand gaps
Customer commitments protected during the ramp
Capacity decisions visible months earlier
Generic tools treat a new node as just a new product
KIPO patent application #2 — planned Q1 2027
03

Explainable re-planning

What it is

Every schedule change carries the triggering event, the constraints it hit and the KPI delta; frozen / flex / far zones bound how much the plan may move; the planner approves, edits or rejects in Korean or English.

Advantages & benefits
Adoption in conservative fab planning cultures
Auditability for management and quality
Planners keep control while tribal knowledge moves from heads into the system
Korean UI + planner-approval workflow (in the MVP)
UNDER THE HOOD

Supporting technical novelties

The three headline innovations rest on a set of smaller engineering choices that make a fab plan both solvable and trustworthy.

(lot, step_index) as the schedulable unit
Tool × recipe × chamber qualification tensor
Batch-formation constraints inside the solver
Monte-Carlo risk wrap on a CP-SAT solution
Solver-gated language-model co-pilot
SPC-driven tune detector closing the loop to engineering
Plan version lifecycle
Plan version lifecycle — draft → compare → commit → published, with audit entries
IN THE MVP

Explainable re-planning, as the planner sees it

October 2026 MVP build on a synthetic fab dataset: the constraint chain behind a rerouted batch, and the frozen-zone acknowledgement that keeps the planner in control.

MVP · synthetic data
aPlanner MVP — explain popover with the full constraint chain
Explain — the full constraint chain for a rerouted batch
MVP · synthetic data
aPlanner MVP — frozen-zone acknowledgement dialog
Frozen-zone acknowledgement — the planner authorises the 0–72 h override before fan-out

Development stage

Not commercialized; no revenue; no customers yet. Working prototypes of scheduling, simulation and analytics on synthetic fab data; forecasting engine prototyped, dedicated view in the December 2026 build.

Done

Phase 1 — Foundation

Apr–Jun 2026
Done

Phase 2 — Concept

Jul–Sep 2026

Working prototypes on synthetic fab data

Now

Phase 3 — Validate

Oct–Dec 2026

MVP validation, Korean UI

Planned

Phase 4 — Launch prep

Jan–Mar 2027

Validate the innovations on your line

The first Korean fab pilot in 2027 is where these targets become measured results.

Join the 2027 Korea pilot programTalk to the founder