Waferira is an agent operating system for semiconductor front-end fabs. Specialist agents control litho and overlay, etch and deposition, CMP and implant, classify defects from inline, e-beam and SEM inspection, measure every wafer virtually, dispatch the WIP and move the carriers, rehearsed on an as-run fab twin and bounded by a policy engine the fab controls. IP never leaves the fab.
Illustrative scenario: Module M2 · 300 mm · metal-1 · lot L-48213, one lot through metal-1, one approval gate
Design partners wanted · 2 to 4 IDMs or foundries · modules we are looking for
Pre-launch. No customers, pilots or logos are claimed. The first cohort gets a paid, IP-isolated pilot on one module against a baseline agreed in writing.
Every Waferira run is an ordered, inspectable sequence. This is run_7b2e9c on Module M2 · 300 mm · metal-1 · lot L-48213. Scenario completes in 10 steps with one approval gate. Overlay and CD predicted inside spec, one reticle-repeater signature caught and held for review, dispatch re-optimised, lot released with full genealogy.
Fab Orchestrator · Pulled lot L-48213 from fab MES: 25 wafers, 300 mm, metal-1 layer, route, reticle, overlay and CD spec and the standing cycle-time target. Locked the target envelope for the run.
Fab Twin · Simulated 64 candidate correctable, recipe and dispatch sets on the as-run fab twin and ranked them on predicted overlay residual, CD uniformity, excursion risk and cycle time.
Litho-and-Overlay · Per-field overlay correctables and a focus-dose trim written to scanner SCN-07 over SECS/GEM after the previous lot's residual trended toward the control limit. Predicted overlay residual back inside spec.
Etch-and-Depo · Chamber B on etcher ETCH-12 showed an edge-fast uniformity drift in FDC. Pressure and RF trims written within the qualified recipe window; predicted CD uniformity recovered.
CMP-and-Implant · Downforce and platen-speed trim on CMP-03 against the virtual removal-rate estimate to hold post-CMP thickness and dishing inside the window.
Defect-and-Inspect · Inline optical, e-beam review and SEM imagery fused at the tool edge. 1,412 events classified, most dispositioned nuisance; one reticle-repeater signature on three dies flagged for review.
Metrology-and-Virtual · Virtual metrology scored every wafer at post-etch and post-CMP from tool-sensor and FDC signatures. Two wafers routed to physical metrology on predicted variance; the rest sampled at plan.
Fab Orchestrator · The reticle-repeater signature called for a reticle inspection hold and a recipe move outside the qualified window. Held for the module process engineer and approved at 03:14:27.
Yield-and-Dispatch · Dispatch re-optimised across 1,840 lots in WIP under reticle, chamber and qualification constraints. The lot routed to the qualified chamber with the shortest predicted queue; AMHS move issued to the stocker.
Quality-and-Conformance · Lot L-48213 moved on: genealogy written (recipe moves, correctables, FDC signatures, VM scores, defect map, approvals) and checked against the layer spec.
Every tool invocation, argument and result is written to an append-only, IP-isolated, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the fab.
Plan, thought, action, observation, exactly as the orchestrator would record it.
Run lot L-48213 through metal-1 on module M2, hold overlay and CD inside the layer spec, catch any excursion before physical metrology, and dispatch on cycle-time target.
Simulate the lot on the twin first. Lead with litho so the correctables are right before etch, then trim etch and CMP against virtual metrology, keep inspection continuous, and hold anything outside the qualified window for a human.
The previous lot's overlay residual on SCN-07 trended toward the control limit. On the twin, a per-field correctable update with a small dose trim brings the predicted residual back to 2.6 nm without touching focus.
twin.simulate(candidates=64) returns set #41: per-field correctables and dose minus 0.3% on SCN-07, chamber B pressure and RF trims on ETCH-12, downforce minus 2% on CMP-03.
Set #41 predicts overlay residual 2.6 nm, CD uniformity inside window and excursion risk 0.05. Nine candidates cut cycle time further but routed the lot to an unqualified chamber and were discarded.
Execute set #41 under autonomy level L3: seven recipe writes inside the qualified window, the reticle hold and the out-of-window move routed to the module process engineer.
Reticle-repeater signature on three dies at 03:09:40 from the fused inspection stream. Virtual metrology routed two wafers to physical measurement on predicted variance.
Scenario complete. Overlay and CD predicted inside spec, the repeater held and reviewed with the OCAP linked, the lot dispatched to a qualified chamber and released with full genealogy.
Nothing about a Waferira run is implicit. The goal is declared, the plan is simulated on the fab twin, each step is typed and bounded to a qualified recipe window, and the outcome is written to the lot record.
A run starts as a goal, becomes a plan, and executes as a graph of typed steps across litho, etch, CMP, inspection, metrology and dispatch. The active path is always visible, always logged, always reversible.
L1 advisory, L2 supervised writes, L3 bounded autonomy inside the qualified recipe window, L4 reserved for loops the fab has qualified. Each fab sets the level per agent, per tool, per shift, and every hold, out-of-window move and lot release waits for a named approver. The four figures above are design targets, not measured results.
Each agent owns a module or a function of the fab, a bounded tool set and a metric the fab already measures. They negotiate for shared tools and recipes through the orchestrator, never directly. Five of them ship as named products.
Photolithography, overlay, focus and dose, CD
Predicts overlay, CD and focus-dose response per scanner, reticle and layer from metrology and inline defect signals, and closes run-to-run control by writing corrected correctables and focus-dose recipes over SECS/GEM, with computational-lithography context for mask-aware moves.
Etch and deposition uniformity, rate, film properties
Controls etch and deposition uniformity, rate and film thickness, stress and composition across the wafer from tool-sensor and FDC signatures, with Vmetra's virtual metrology grounding every move and the fab twin validating it before the lot runs.
CMP planarisation, implant dose and uniformity
Holds CMP removal rate, dishing and erosion and implant dose and uniformity within window, scoring excursion risk in real time from FDC signatures and virtual metrology and trimming recipes inside the qualified bounds.
Cleans, diffusion and thermal budget
Controls cleans, diffusion and thermal budget against the process window, tracking particle and chemistry signals and the energy, gas and chemical use the fab pays for at every step.
Defect classification, particles, reticle excursions
Fuses inline optical, e-beam and SEM imagery at the tool edge to classify and predict defects, particles and yield-limiting excursions, auto-dispositions nuisance against killer defects, triages reticle and pattern excursions and raises inline holds.
Virtual metrology, run-to-run and advanced process control
Predicts metrology for etch, deposition, CMP, implant, clean and diffusion on every wafer from tool-sensor and FDC signatures, scores excursion risk, decides which wafers go to physical metrology, and closes run-to-run APC by handing corrected recipes to the process agents.
Yield, WIP, scheduling, dispatch, cycle time
Re-optimises WIP, scheduling and dispatch under reticle, chamber, qualification, route and hot-lot constraints, weighting every move by live yield and excursion risk from Scanira and Vmetra, with the fab twin validating the plan before it commits.
FOUP, AMHS and wafer handling
Drives FOUP and AMHS moves and wafer handling so lots arrive when the dispatch plan expects them, with motion perception and exception detection at the fab edge and handling validated in simulation before it touches a carrier.
Excursion response, non-conformance, wafer and lot genealogy
Runs excursion response and OCAP linkage, non-conformance and wafer and lot genealogy, gates lot release against the layer spec and assembles the traceability record every action on the lot has to leave behind.
Recipes, integration specs, SEMI standards, OCAPs, engineer Q&A
Answers process-integration and yield questions from recipes, integration specs, SEMI standards and excursion and OCAP procedures, with every answer cited to its source and retrieval scoped to the tenant.
As-run wafer and fab twin, process and flow
Fuses process (litho, etch, deposition, CMP, implant, thermal) and flow (WIP, tools, AMHS, routes) into an Omniverse-based twin that simulates candidate recipes, correctables, WIP and dispatch moves, as-run against as-designed, and returns the predicted yield, uniformity and cycle time before the lot runs.
Planning, arbitration, human approval
Plans the run, arbitrates between agents competing for the same tool or recipe, enforces the autonomy level, recipe bounds and tool-state checks, and routes anything outside the qualified window to a named approver.
Waferira is not a dashboard. Each agent closes a loop a fab already measures in yield points, excursions, scrapped lots, review hours and cycle time. The tables show what each loop watches and what it is allowed to move.
Overlay residuals and CD drift are predicted per scanner, reticle and layer from metrology and inline defect signals. When the trend heads for the control limit the agent updates correctables and focus-dose inside the qualified window instead of waiting for a rework lot.
| Signal | Watches | Moves |
|---|---|---|
| Overlay residual | Predicted per field from metrology trend | Per-field correctables |
| CD | Virtual and sampled metrology | Dose trim inside window |
| Focus | Focus-exposure matrix drift | Focus offset or hold |
Physical metrology is sampled, so most wafers go unmeasured while uniformity drifts. Vmetra predicts the measurement from tool-sensor and FDC signatures on every wafer, routes the uncertain ones to the metrology tool and hands corrected recipes to the process agents.
| Signal | Watches | Moves |
|---|---|---|
| Film thickness | Predicted from FDC per wafer | Deposition time and rate trims via Etch-and-Depo |
| Uniformity | Predicted edge-to-centre profile | Pressure and RF trims inside window |
| Removal rate | Predicted from platen telemetry | Downforce and platen trims via CMP-and-Implant |
Inspection tools produce more images than any review team can look at. Scanira fuses optical, e-beam and SEM at the tool edge, classifies each event, auto-dispositions nuisance against killer, and raises a hold on a reticle or pattern excursion while the lot is still in the module.
| Signal | Watches | Moves |
|---|---|---|
| Defect events | Classified and dispositioned in real time | Hold recommendation, signal to control agents |
| Reticle repeaters | Same field position across dies | Reticle inspection hold via approval |
| Particle excursions | Tool and step correlation | Signal to Clean-and-Diffuse and dispatch |
Dispatch runs on rules and WIP bubbles anyway. Dispira re-optimises the dispatch list every few minutes under reticle, chamber and qualification constraints, weighted by live yield risk, and the fab twin checks the plan for cycle-time and yield effect before the AMHS moves a carrier.
| Signal | Watches | Moves |
|---|---|---|
| WIP by step | Live from MES | Dispatch list to qualified chambers |
| Reticle and chamber state | Tool and qualification status | Routing within constraints |
| Predicted cycle time | Twin simulation of the plan | Plan accepted or re-optimised |
Two agents will want the same chamber or the same lot. The orchestrator arbitrates on the run goal, not on who asked first, and the handoff is logged like any other step.
Yield-and-Dispatch wants chamber B for lot L-48213 because it has the shortest predicted queue and the lot is on cycle-time watch.
Etch-and-Depo wants chamber B held for one lot to write a pressure and RF trim after FDC showed an edge-fast uniformity drift.
A uniformity excursion on 25 wafers outranks minutes of queue time under the run goal "no excursion past metrology". Etch-and-Depo holds the chamber for one trim cycle.
Chamber returned with the trim written and predicted uniformity recovered. Dispatch routes the lot in; the twin confirms the cycle-time target still holds.
Illustrative scenario.
A fab does not go from manual APC to unattended control in one step. Waferira makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then graduated autonomy for low-risk APC, defect and metrology loops.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Advisory | Recommends recipe moves, dispositions and dispatch, with citations | Enters every change manually | Shadow mode, first on the design-partner cell |
| L2 · Supervised | Proposes a recipe write or hold; it executes on approval | Approves each move in the review console | Assist mode, where accuracy and ROI are proven |
| L3 · Bounded | Writes inside the qualified recipe window, tool-state checks and OCAP linkage | Approves holds, out-of-window moves and lot release | Graduated autonomy for low-risk APC, defect and metrology loops |
| L4 · Qualified loops | Runs a qualified loop without prompting, inside its envelope | Sets the envelope; reviews the shift record | Planned; reserved for loops the fab has qualified |
These are the figures in our compute plan. None is a measured result. Every pilot measures against the fab's own baseline, reproduced from the fab's own yield, excursion and cycle-time records, not from our telemetry.
Logic and foundry, memory, analog and mixed-signal, specialty and compound semiconductor, and new fabs ramping a node. Most fabs pick one module and one wedge, prove the number, then expand.
Sub-3 nm, gate-all-around and backside-power nodes where overlay and CD budgets decide yield. Lithera and Vmetra on the litho and etch modules first.
High-aspect-ratio etch and deposition uniformity and CMP planarisation on long flows. Vmetra and Scanira where excursions are most expensive.
Many products, many recipes, few engineers per tool. Virtual metrology and defect disposition to cover more wafers with the same team.
SiC, GaN and photonics fabs with their own defect and uniformity physics. Scanira and Vmetra models trained per process family.
Reshored and greenfield capacity ramping under schedule pressure. Fabtwin de-risks the ramp before lots run.
Computational lithography, defect classification on e-beam and SEM imagery, per-wafer virtual metrology and a full-fab twin are among the most compute-intensive workloads in manufacturing. Waferira keeps IP-sensitive inference and feature storage at the fab edge and runs training, simulation and optimisation on GPUs the fab controls.
Inline optical, e-beam and SEM imagery and sensor fusion on fab-edge GPUs. 10 to 50 inspection streams per pilot module and sub-200 ms priority defect triage are the design targets.
High-volume multivariate tool-sensor and FDC time-series scoring on every wafer, 1 to 5 seconds per lot-step in the design, with nightly retraining as recipes and chambers drift.
Defect, virtual-metrology and process-response models retrained per process family; 500 to 2,000 GPU-hours per family per quarter is the design target. Dedicated capacity is planned.
As-run process and flow simulation, 1,000 to 10,000 candidate recipe, metrology and dispatch scenarios per fab per day in the design. OVX access is planned.
Rare defect, particle, overlay-drift, CMP-dishing and film-uniformity variants generated and validated against real distributions before promotion. Planned.
Constrained WIP dispatch re-optimised every 1 to 5 minutes across reticle, chamber, route, tool-state and cycle-time constraints.
Local FOUP and robot perception and exception detection at the fab edge. Jetson Thor is planned for higher sensor density.
Tenant-isolated process Q&A and OCAP reasoning over recipes, SEMI procedures and audit logs, with citations enforced on every answer.
The Waferira SDK is typed Python. Tools are declared with schemas and recipe-window limits and the policy engine enforces them at call time, not in a review meeting. This is a design preview; the API will change before release.
# Design preview. Bound the litho agent to scanner SCN-07.
from waferira import Agent, Tool, Limit, Autonomy
recipe = Tool(
name="secs.write_recipe",
tool="SCN-07",
params=["correctables.per_field", "dose"],
limits=[Limit(window="qualified", max_step="0.5%", per="lot")],
)
litho = Agent(
id="agent.litho_overlay",
goal="overlay residual < 3 nm, CD inside M1 window",
tools=[recipe, Tool("metrology.read_overlay", read_only=True)],
# bounded writes; humans still gate holds and out-of-window moves
autonomy=Autonomy.L3,
# simulate on the fab twin before every write
verify="twin",
)
run = litho.start(lot="L-48213", layer="M1")
for step in run.stream():
print(step.name, step.status, step.duration)The same run engine, the same policy checks, the same IP-isolated audit trail, from the terminal, the review console or the SDK. Design preview.
$ waferira run "lot L-48213 through M1 on module M2" --autonomy L3
→ plan composed 10 steps · 1 approval gate
→ twin.simulate 64 candidates · best #41 · excursion risk 0.05
→ policy.evaluate 7 recipe writes inside window · 1 held for human
→ executing litho.correctables .. ok 1m20s
→ executing etch.uniformity .... ok 58s
→ executing cmp.removal ........ ok 46s
→ executing vm.score ........... ok 2.1s
! approval required reticle_hold · recipe move outside window
→ approved module process engineer · 03:14:27
→ scenario complete 1 hold reviewed · lot L-48213 released
$ waferira lots show L-48213 --format genealogyLand on one workflow with a measured baseline. Expand by module, tool fleet, fab and autonomy level. Outcome components are available on yield-point value, excursions and cycle time. Annual prepay carries a 15 to 20% discount.
APC, defect or virtual-metrology AI for one module: litho, etch, deposition or CMP. For fabs validating ROI on the wedge, IP-isolated from day one.
The whole loop: litho and overlay, etch and deposition, CMP and implant, clean and diffuse, defect, metrology and virtual, yield and dispatch, AMHS and the fab twin.
Multi-fab IDMs and foundries standardising on Waferira, with custom process, device and yield models and a managed fab-edge fleet.
We have no customer quotes to show yet and will not invent any. These are the three roles in a fab we build for, and the problems they bring to the first meeting.
What this person is dealing with today
What this person is dealing with today
What this person is dealing with today
Waferira reads and writes through the systems already in the fab. No rip and replace, no parallel historian, no new HMI to learn. Vendor names are examples of systems found in front-end fabs; connector availability is confirmed per site.
SECS/GEM on scanners, etchers, deposition, CMP, implanters, furnaces and wet benches
Recipe reads and bounded recipe writes
Advanced and run-to-run process control systems (Applied Materials APF and APC, PDF Solutions, in-house IDM APC)
Model state, correctables, control limits
Inline optical, e-beam and SEM inspection and review tools (KLA, Applied Materials, Hitachi High-Tech, Onto Innovation class systems)
Images, defect maps, ADC classes
Overlay, CD, film and OCD metrology (KLA, Onto Innovation, Nova class systems)
Sampled measurements that ground virtual metrology
Fault-detection and tool-sensor streams per chamber
Per-wafer signatures for virtual metrology and prognostics
Yield and defect analytics (PDF Solutions Exensio, Synopsys, Siemens Camline, INFICON class systems)
Yield, bin and genealogy context
Fab MES and schedulers (Applied SmartFactory, Siemens Camstar, Critical Manufacturing, INFICON FPS class systems)
Lots, routes, WIP, dispatch lists
Stockers, vehicles and FOUP handling (Daifuku class AMHS)
Carrier moves and handling exceptions
Waferira writes to production tools over SECS/GEM. Every capability is scoped to a qualified recipe window, every write is policy-checked against tool state, and every action is written to an append-only, IP-isolated audit log the fab owns.
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I and fab-security review | Control plane | QUEUED Planned, first 6 months |
| SOC 2 Type II | Control plane | QUEUED Planned, 6 to 12 months |
| SSO and RBAC | Console and approvals | QUEUED Planned, 6 to 12 months |
| IP-isolation and security assurance package | Fab security and IT and OT review | QUEUED Planned, 6 to 12 months |
| SEMI-standards-cited reasoning | Recipes, integration specs, OCAPs | RUNNING In the design, every answer cites its source |
| Per-tenant IP isolation | Data, models, memory | RUNNING In the design from day one |
| On-prem and fab-edge deployment | IP-sensitive fabs | RUNNING Design option |
One policy model, one audit trail, one benchmark across every module in every fab, with the process, device and yield models kept private to each site.
The questions fab directors and process engineers ask in the first meeting.
Yes, over SECS/GEM, but only inside the qualified recipe window for that tool, with per-parameter limits and tool-state checks, and only at the autonomy level your fab has set. Level 1 is advisory: Waferira recommends and an engineer enters everything. Design partners start there, in shadow mode.
The tool stays on its own controller and its last qualified recipe. Waferira is a supervisory layer on top of the APC, inspection, metrology and MES systems you already run, never a replacement for them, so an outage leaves the module running the way it runs today.
No. Inference and feature storage stay at the fab edge, recipes, device designs, defect libraries and process memory are isolated per tenant, and an on-prem control plane is available for IP-sensitive fabs. Any cross-fab learning is planned, contract-gated and privacy-preserving, and none of it moves recipes or designs.
Advisory recommendations start from the existing APC, metrology and ADC data on the wedge module. Defect classification, virtual metrology and excursion prediction improve as labelled events and lot outcomes accumulate per process family. Rare excursions are augmented synthetically only after validation against real distributions.
You are, the same as with any APC strategy, which is why every write is policy-checked, bounded to the qualified window, logged and reversible, and why holds, out-of-window moves and lot release wait for a named approver with the OCAP linked.
A paid pilot on one process module or tool fleet, scoped to one wedge workflow with a baseline agreed in writing. Shadow mode first, observing and measuring the baseline. Then assist mode, where the agent recommends and your engineer approves and accuracy and ROI are measured. Then bounded autonomy for low-risk APC, defect or metrology loops if the fab is satisfied.
Start with one process module or tool fleet and one measurable baseline. A paid, IP-isolated pilot on defect classification, virtual-metrology-driven overlay and CD control or uniformity APC shows the number before you commit further.
↑↓ navigate↵ openesc close