Typed, ordered, inspectable
A run is a goal, a plan and a graph of typed steps. Every step has an agent, a tool, a duration and a status, and the whole record is kept per part and lot.
Features
Capability by capability, with the limit on each.
Forgiron's features are the mechanics of a system that is allowed to touch production equipment: typed runs, a policy engine, named approvals, fused inspection, a twin, genealogy and an audit log. The list below is design scope, not a shipped feature list.
Illustrative scenario: Cell F-2 · 2,500 t closed-die press · 42CrMo4 connecting rod, one lot, one approval gate
Features
What the platform does
Each capability names what it does and where its limit sits.
Limits enforced at call time
Tag allow-lists, per-tag rate and magnitude limits, the qualified process envelope, autonomy level, shift, part family and interlock state are evaluated before any setpoint moves.
Named humans at the gate
Press-schedule changes, die changes and lot release wait for the approver the forge names. The request, the evidence and the decision are logged.
Five modalities, one model
Vision, thermal, ultrasonic, MPI and dimensional data fused into one estimate of soundness, localised to part, lot, die cavity and stroke.
Rehearse before the stroke
Candidate heating, stroke and die recipes ranked on fill, lap risk, die load and energy before a setpoint moves. Proven setpoints handed to the control agents.
The record of every part
Billet lot, heat curve, stroke record, die cycles, inspection map, approvals, heat-treat record and disposition, exportable for customer, first-article and qualification review.
Approve, correct, feed back
Forging and die engineers see recommendations with their evidence, approve or correct them, and those corrections train the models.
Append-only, exportable
Every agent action with source evidence, the approved process envelope, confidence, predicted yield, scrap, die-life and energy impact, rollback path, approver and lot scope.
Every answer cites its source
Retrieval over recipes, die and forging specs, AS9100, IATF 16949, NADCAP and ASTM documents and quality procedures, tenant-isolated.
The craft, written down
Per-forge yield and quality history and per-operator and die-engineer performance memory, versioned and scoped per tenant.
Rare cases, validated
Rare lap, fold, underfill, crack and die-wear variants generated to augment training and always validated against real inspection distributions before promotion. Planned.
Many cells, one policy
Model versions promoted by cell with canary rollout and automatic fallback; group policy with per-site override on the Enterprise tier.
Run timeline · scenario
One scenario run, step by step
Every Forgiron run is an ordered, inspectable sequence. This is run_7c2e41 on Cell F-2 · 2,500 t closed-die press · 42CrMo4 connecting rod. Scenario completes in 10 steps with one approval gate. Surface temperature held at 1,205 °C with a 14 °C core-to-surface spread, fill predicted and confirmed complete, one lap precursor at the flash land cleared by a blow-energy trim, lot L-80412 released with full genealogy.
run_7c2e41
Cell F-2 · 2,500 t closed-die press · 42CrMo4 connecting rod
illustrative scenario
SUCCEEDED
-
01
ingest.order
SUCCEEDED
0.6 s
Plant Orchestrator · Pulled the part spec for the 42CrMo4 connecting rod from MES: forging window 1,180 to 1,230 °C, two-blow closed-die schedule, flash land 2.4 mm, temper to 28 to 32 HRC, 1,200 pieces. Locked the qualified process envelope.
-
02
twin.simulate
SUCCEEDED
52 s
Forge Twin · Simulated 24 candidate heat-and-stroke recipes on the as-forged twin for soak time, blow energy and spray timing, ranked on predicted fill, lap risk at the flash land, die load and kWh per piece.
-
03
heat.soak
SUCCEEDED
2 m 10 s
Heat-and-Billet · Induction power on IH-2 stepped down 4% in the final soak stage as the pyrometer read 1,205 °C at the surface. Core-to-surface spread estimated at 14 °C against a 20 °C limit, no overheat, scale growth inside the window.
-
04
die.spray
SUCCEEDED
48 s
Die-and-Lube · Lower-die spray dose raised 6% and cooling extended 0.3 s as die surface temperature climbed through 240 °C. Heat-check growth on cavity 2 flagged at 0.31 of the die-change threshold.
-
05
approve.human
APPROVAL
46 s
Plant Orchestrator · Recipe #9 moves second-blow energy 3% below the standing schedule. Press-schedule changes stay supervised on this part family, so the step was held for the shift forging engineer and approved at 05:47:31.
-
06
forge.stroke
SUCCEEDED
1 m 36 s
Forge-and-Press · Two-blow schedule executed with the approved energy. High-speed vision and force curves confirmed complete fill on the first ten pieces; predicted lap risk at the flash land fell from 0.27 to 0.08.
-
07
inspect.fuse
SUCCEEDED
continuous
Defect-and-Inspect · Eight cameras, two thermal cameras and the ultrasonic station fused at the edge. One lap precursor at the flash land on piece 212 flagged and cleared by a 1.5% blow-energy trim inside the approved envelope; the piece was routed to MPI and passed.
-
08
handle.transfer
SUCCEEDED
continuous
Robot-and-Handling · Press-to-trim transfer planned and executed by the handling robot at 11 s per piece, temperature loss in transfer 38 °C against a 60 °C limit, interlock zones clear throughout.
-
09
heat.treat
SUCCEEDED
continuous
Trim-and-Heat · Temper furnace HT-1 zone 2 trimmed 5 °C against the predicted hardness from the recorded heat and stroke history. First hardness checks read 30 HRC, inside 28 to 32.
-
10
lot.release
SUCCEEDED
1 m 20 s
Quality-and-Conformance · Lot L-80412 released: genealogy written (billet lot, heat curve, stroke record, die cycles, inspection map, approvals, temper record) and dispositioned against IATF 16949 criteria with cited evidence for the quality engineer's sign-off.
Tool calls · scenario
The agent shows its work
Every tool invocation, argument and result is written to an append-only, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the forge.
- 05:40:02mes.read_order({ cell: "F-2", part: "CR-42CrMo4-118", qty: 1200 })
- 05:40:02ok envelope locked · 1,180 to 1,230 °C · 2 blows · 28 to 32 HRC
- 05:40:03twin.simulate({ candidates: 24, horizon: "1 lot" })
- 05:40:55ok best recipe #9 · fill 1.00 · lap risk 0.08 · 1.9 kWh/pc
- 05:40:56policy.evaluate({ recipe: 9, autonomy: "L2+" })
- 05:40:56ok 7 writes permitted · press_schedule requires human approval
- 05:40:57induction.set_power({ tag: "IH2.STAGE3_KW", delta: "-4%" })
- 05:43:07ok surface 1,205 °C · core-to-surface spread 14 °C · no overheat
- 05:43:08spray.set_dose({ die: "F2.LOWER", dose: "+6%", cool: "+0.3 s" })
- 05:43:56ok die surface 240 °C · heat-check index 0.31
- 05:43:57approval.request({ action: "press_schedule", blow2: "-3%" })
- 05:47:31ok approved by shift forging engineer · logged
- 05:47:32press.set_schedule({ press: "F-2", recipe: 9 })
- 05:49:08ok fill complete on 10 pieces · lap risk 0.27 → 0.08
- 05:49:09sensors.fuse({ cams: 8, thermal: 2, ut: true })
- 06:21:40precursor: lap risk 0.52 · flash land · piece 212
- 06:21:41press.set_schedule({ press: "F-2", blow2: "-1.5%", within: "approved envelope" })
- 06:21:58ok lap risk 0.52 → 0.07 · piece 212 routed to MPI · passed
- 06:22:00isaac.plan_path({ task: "press_to_trim", cell: "F-2" })
- 06:22:11ok 11 s per piece · transfer loss 38 °C · zones clear
- 06:22:12furnace.set_zone({ furnace: "HT-1", zone: 2, delta: "-5 °C" })
- 06:58:40ok first hardness 30 HRC · inside 28 to 32
- 06:58:41mes.log_forging({ lot: "L-80412", genealogy: "full" })
- 07:00:01ok scenario complete · 10 steps · 0 laps escaped · released
Reasoning trace
Plan, thought, action, observation, exactly as the orchestrator would record it.
GoalRun the 42CrMo4 connecting-rod lot on cell F-2 inside the qual…
Run the 42CrMo4 connecting-rod lot on cell F-2 inside the qualified window, hold full fill with zero laps at the flash land, and land hardness between 28 and 32 HRC.
PlanSimulate heat-and-stroke recipes on the twin first. Lead with …
Simulate heat-and-stroke recipes on the twin first. Lead with heating so the billet state is right before the stroke, then set spray against die temperature, then execute the approved press schedule. Fuse inspection continuously. Hold any press-schedule change for a human.
ThoughtThe standing schedule runs the second blow hot enough to guara…
The standing schedule runs the second blow hot enough to guarantee fill on a cold billet. With the induction soak held at 1,205 °C the twin predicts the same fill at 3% less energy and lower flash-land lap risk, because the metal arrives more uniform.
Actiontwin.simulate(candidates=24) returns recipe #9: stage-3 induct…
twin.simulate(candidates=24) returns recipe #9: stage-3 induction power down 4%, lower-die spray up 6%, second-blow energy down 3%.
ObservationRecipe #9 predicts fill 1.00, lap risk 0.08 and 1.9 kWh per pi…
Recipe #9 predicts fill 1.00, lap risk 0.08 and 1.9 kWh per piece. Two candidates scored lower on energy but pushed predicted die load past the cavity-2 limit and were discarded.
ActionExecute recipe #9: seven bounded writes permitted on heating, …
Execute recipe #9: seven bounded writes permitted on heating, spray, handling and heat-treat; the press-schedule write routed to the shift forging engineer.
ObservationLap precursor at the flash land on piece 212 at 06:21:40. A 1.…
Lap precursor at the flash land on piece 212 at 06:21:40. A 1.5% blow-energy trim inside the approved envelope cleared it in 17 s; the piece was routed to MPI and passed.
OutcomeScenario complete. Fill confirmed, no laps escaped, hardness 3…
Scenario complete. Fill confirmed, no laps escaped, hardness 30 HRC. Lot L-80412 released with full genealogy.
Where it pays
Four loops, four metrics
Forgiron is not a dashboard. Each agent closes a loop a forge already measures in scrap, die changes, kilowatt-hours and inspection escapes. The tables show what each loop watches and what it is allowed to move.
Heating and energy
Hit forging temperature at the least kWh
Thermal imaging, pyrometry and coil telemetry are fused at the edge into a live estimate of surface temperature, core-to-surface spread and soak. Heatrix adapts induction power and furnace zones to land the window without overheating or decarburization, and prices every heat in kilowatt-hours.
- Surface and core state estimated continuously, not from a spot thermocouple
- Per-alloy thermal windows enforced at call time
- Every heat labelled with its downstream fill and property outcome
agent.heat_billet SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Billet temperature | Pyrometer and thermal camera | Induction power, furnace zones |
| Core-to-surface spread | Estimated from heating curve | Soak time |
| Energy per heat | Coil and burner telemetry | Stage power inside the window |
Fill and grain flow
Decide the stroke before the ram drops
Force curves, ram position and high-speed vision are fused with the incoming heat state. Forgeon predicts fill, grain flow and lap or underfill risk per piece and proposes the stroke schedule that hits them at minimum blows and energy, validated on the twin and approved by the forging engineer until the part family is qualified.
- Fill and lap risk predicted from heat and geometry, not judged after cooling
- Blow energy and ram speed moved together
- Press-schedule changes supervised by a named engineer
agent.forge_press SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Die fill | Force curve and high-speed vision | Blow energy, ram speed, under approval |
| Lap and underfill risk | Scored per piece | Energy trim inside the approved envelope |
| Grain flow | Modelled from stroke schedule | Schedule candidates ranked on the twin |
Die life
Pull the die before it scraps a part
Die surface temperature, heat-check growth and lubricant coverage are modelled from thermal and vision between strokes. Diesmith doses spray and cooling to hold friction and fill and schedules the die change in a planned window instead of after the first underfill.
- Die life predicted per cavity
- Spray and cooling controlled between strokes
- Die changes scheduled, not reacted to
agent.die_lube SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Die temperature | Thermal camera between strokes | Spray dose and cooling |
| Heat-check growth | Vision per cavity | Die-change window |
| Lubricant coverage | Vision | Spray pattern and timing |
Laps, cracks and internal defects
See the defect and the stroke that made it
Vision, thermal, ultrasonic, MPI and dimensional data are fused into one model of soundness. Flawnex detects and predicts laps, folds, underfill, cracks and internal defects, routes suspect parts to the right check, and couples each finding back to the heat, stroke and die state behind it.
- Five modalities, one estimate of soundness
- Defects localised to part, lot, die cavity and stroke
- Disposition grounded in AS9100, IATF 16949, NADCAP and ASTM with citations
agent.defect_inspect SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Surface laps and cracks | Cameras and MPI | Energy trim via Forgeon, part routing |
| Internal defects | Ultrasonic station | Lot hold, root cause to heat and stroke |
| Dimension after cool-down | Dimensional scan | Spec envelope to the control agents |
Autonomy
Four levels, set per agent and per tag
A forge does not go from manual to unattended in one step. Forgiron makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then bounded autonomy on low-risk actions. Press control stays supervised until the part family is qualified.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Shadow | Reads thermal, vision, ultrasonic, MPI, press, die, robot and MES signals; predicts and recommends; writes nothing | Runs the cell as today; compares predictions to inspection and engineer outcomes | Shadow mode, baseline 30 to 60 days |
| L2 · Assist | Proposes heating, press, die-lube, routing and handling actions with evidence, confidence, envelope and rollback path | Approves each action in the review console | Assist mode, the remainder of a 90 to 180 day pilot |
| L3 · Bounded | Executes pre-approved low-risk actions: inspection routing, lube timing, heating and soak adjustments, robot path variants, inside PLC and safety limits | Approves press-schedule changes, die changes and lot release | Graduated autonomy, after audited accuracy and ROI |
| L4 · Scaled | Supervised press-schedule adaptation for qualified part families, across cells and sites | Sets the envelope; reviews the shift record and the evaluation results | Planned; after golden-dataset evaluation, simulation validation and quality sign-off |
Accelerated computing
Physical AI, at the press
A stroke lasts a fraction of a second and a billet cools while it waits. Perception has to be local, deterministic and fast, so Forgiron runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud or on-prem.
Edge perception
8 to 24 cameras per line plus thermal, ultrasonic, MPI, press and ram streams fused at the cell. Sub-100 ms visual alerts and sub-500 ms recommendations are the design targets. Jetson Thor is planned for higher sensor density.
Model serving
Defect, ultrasonic and MPI fusion, die-wear, heating, press-fill, property and disposition models behind one orchestrator at the plant edge, routed by latency, tenant, sensitivity and cost, with canary rollout by cell.
Training
Multimodal defect, die-wear, heating, press-fill, property and quality-disposition models trained on thermal images, high-speed vision, ultrasonic and MPI signals, press curves and engineer corrections. Dedicated training capacity is planned.
Forge-line twin
Billet heating, die thermal state, press stroke, fill, stress, die load and robot handling simulated before the stroke. GPU forging FEM is the workload; physics-informed surrogates are planned so recipes rank at production cadence.
Synthetic data
Rare lap, fold, underfill, crack and die-wear scenarios generated and validated against real inspection distributions before promotion. Planned.
Optimisation
Die allocation, press sequencing, heating batches, heat-treat queues, robot and takt coordination and inspection routing.
Robot handling
Hot billet, forging, die and trim handling skills trained and validated in simulation before they run next to a press.
GPU ETL
Daily features from thermal, video, ultrasonic, MPI, press and genealogy data for retraining, drift detection and yield, scrap, die-life and energy benchmarks.
Guardrails
An agent that can move a press schedule needs a leash
Forgiron writes to production equipment. Every capability is scoped, every write is policy-checked against the qualified envelope, and every action is written to an append-only audit log the forge owns.
- Bounded action space. Each agent writes only to an explicit tag allow-list, inside per-tag rate and magnitude limits and the qualified process envelope for the part family.
- Policy engine before every write. Autonomy level, shift, part family, interlock state and operator presence are evaluated before a setpoint moves.
- Human-in-the-loop gates. Press-schedule changes, die changes and lot release wait for a named approver. Safety-critical press control stays guarded by PLC interlocks and engineer approval until qualification evidence supports more.
- Immutable audit log. Append-only and exportable. Every action records source evidence, the approved process envelope, confidence, estimated yield, scrap, die-life and energy impact, rollback path, approver and lot scope.
- Hard fallback. Loss of the edge node, the network or a model returns control to the furnace, press or die controller's last known-good state. Interlocks are never in Forgiron's path.
- Tenant and die-IP isolation. Die designs, part drawings, alloy recipes and quality records never cross a customer boundary. On-prem deployment is available for sensitive producers.
Compliance posture
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Planned, 6 to 12 months |
| SSO and RBAC | Console and approvals | QUEUED Planned, 6 to 12 months |
| AS9100 and NADCAP assurance packages | Disposition and genealogy evidence | QUEUED Planned, 6 to 12 months; not a certification claim |
| Standards-cited reasoning | AS9100, IATF 16949, NADCAP, ASTM documents | RUNNING In the design, every answer cites its source |
| Per-tenant and die-IP isolation | Recipes, die designs, models, memory | RUNNING In the design from day one |
| On-prem and plant-edge deployment | Sensitive producers | RUNNING Design option |
FAQ
Straight answers
The questions plant directors, forging engineers and quality engineers ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, inside the qualified process envelope, and only at the autonomy level your plant has set. Design partners start in shadow mode, where Forgiron writes nothing. Press-schedule changes stay supervised by a named forging engineer until the part family is qualified.
Control returns to the furnace, press or die controller's last known-good state. Forgiron is a supervisory layer on top of the PLCs and interlocks you already run, never a replacement for them, so an outage degrades the cell to its current way of running, not to a stop.
Advisory recommendations start from the physics-based twin and the part spec in the first weeks. Defect, die-wear and heating prediction improve as cell history and labelled outcomes accumulate per part family. The first training sets are sized at 2 million labelled frames and signals, 20,000 heat and press cycles and 10,000 die-life events per design-partner cohort, all design targets.
Only if you choose cloud training. Die designs, part drawings, recipes, process models and quality records are isolated per tenant and never used to train another customer's models. A fully on-prem deployment at the plant edge is available for sensitive producers, and federated learning across sites is planned and waits on data-rights agreements.
You are, the same as with any control strategy, which is why every write is policy-checked, bounded, logged and reversible, and why anything above your risk threshold waits for a named approver. The audit log records the request, the evidence, the envelope applied and the human decision.
A paid pilot of 90 to 180 days on one cell, scoped to a single wedge with a success metric written into the order form: defect-detection accuracy, scrap reduction, die-change reduction, energy reduction or first-pass-quality improvement. The first 30 to 60 days baseline scrap, die life, energy, inspection escapes and takt in shadow mode.
Get started
See the features on one cell
Start with one heating, press, die or inspection cell and one measurable baseline. A paid pilot on billet heating and press fill, die life or ultrasonic and MPI defect detection shows the number before you commit further.