Each number in the text points here. Every entry states its confidence class in words and keeps its evidence one click away. How to read the labels.
Key to the badges
Confidence: Verified
A manufacturer or IntelliMake document says so, the project owner stated it as the design, or it was observed directly. It does not mean anyone measured it at S2.
Confidence: Inferred
Reasoned from Verified facts. The reasoning is printed with the record.
Confidence: Assumed
Plausible but untested. The record says how it would be checked.
Kind: Gap
Not known. No figure or answer is given in its place.
Kind: Contradiction
Sources disagree. Both sides are shown, and the site does not pick one silently.
Kind: Recommendation
Project advice drawn from the records it cites. Not a fact about the machine and not a confidence class, so the filter never hides it.
Awaiting cell access
Awaiting cell access: could be confirmed or corrected once the physical S2 cell can be observed.
This project's simulation and agent design, not the physical cellProject design, not the physical cell
This project's simulation and agent design, not the physical cell.
Filter records All shown
Plus 3 pieces of project advice, always shown: advice is not a confidence class.
S3, the Inbound Staging Table, provides temporary storage and buffering for incoming workpieces.
Evidence · 1 citation
Provides temporary storage/buffering for incoming workplaces.
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · S3 station description (the diagram prints 'workplaces'; read as workpieces)
S4, the Laser Engraver Conveyor, transfers workpieces through the laser processing area.
Evidence · 1 citation
Transfers workplaces through the laser processing area.
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · S4 station description (the diagram prints 'workplaces'; read as workpieces)
The factory's initial production scenario is personalized laser-engraved gifts; it is to expand in the future to additively manufactured (3D-printed) custom parts that are laser marked or engraved.
Evidence · 1 citation
Initial production scenario focuses on personalized laser-engraved gifts, expanding in the future to additively manufactured custom parts (laser marked/engraved).
The project specification places S2 at the first Cobot Handling step of IntelliMake's gift flow, between Receiving and Staging; the second Cobot Handling step, after laser engraving, is S6's. IntelliMake's layout draws the stations in the matching order (see observation).
Evidence · 3 citations
Where it sits in the Initial Personalized Gift Production Flow (Receiving → **Cobot Handling** → Staging → Laser Engraving → …)
The S1 conveyor can be seen as part of the cell's inventory supply: material from vendor partners arrives and is placed on the conveyor, and S2 takes the items from there.
Evidence · 1 citation
The conveyer can be sseen as part of inventory supply. Material from vendor partners arrives and is placed on the conveyer. S2 takes the items
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
S2 takes the items from S1 and arranges them logically on the S3 staging table. For business cards, cards of the same color are stacked in the same area.
Evidence · 1 citation
S2 takes the items and logically arranges it on S3 staging. Example, in case of business cards, stacking cards of the same color in the same area.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
S3 can serve two purposes: staging material in one area, and placing defects in another. That would be one point of quality assurance and quality control (QA/QC) in the cell.
Evidence · 1 citation
S3 can serve two purposes, staging material in one area, and placing defects in another. This would be one point of QAQC.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The planned outcome for the IntelliMake cell is a working autonomous production run: accepting orders, personalizing the parts, then sending them for shipping, all done by the agents interacting with each other.
Evidence · 2 citations
The goal is a working autonomous production run of the system accepting orders and printing then sending over for shipping, all done by the agents interacting with each other.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S47
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
The IntelliMake cell's planned outcome; 'printing' means personalising the part (engraving now, 3D printing later).
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S50, first answer (option text chosen)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The cell's initial orders are currently understood to be more geared to simple custom printed cards, where 'printed' means engraved by the cell's laser: there is no separate printing step. Depending upon progress, more complex orders could be taken on.
Evidence · 3 citations
initial orders are more geared to simple custom printed cards, however, depending upon progress, more complex orders could be entertained.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Laser-engraved
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S149 (2026-10-07), answer (3)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
"Printed" means engraved by the S4 laser; there is no separate printing step.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S149 (2026-10-07), the option answer (3) matches (the option's words)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
S5, the xTool F1 Ultra laser engraver, and the S4 conveyor are interconnected systems. The Phase 1 layout drawing has a box for S4 and none of its own for S5.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Evidence · 4 citations
S4 conveye and engraver are interconnected systems.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S97, first sentence (unchanged by S172; rule 7, the earlier citation kept)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Yes, it is S5
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S102, answer (2), to whether the engraver travelling along the S4 conveyor is the course's S5, the xTool F1 Ultra
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
S5 xTool F1 Ultra Laser Engraver
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · S5 station label
The S5 laser engraver stays in one place, and the S4 conveyor moves the product from one location to another.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Evidence · 2 citations
S4 engrave will remain stationary and the conveyer swill be the means of moving the product from one location to another.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S172 (2026-10-09), IntelliMake Notes
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Yes, it is S5
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S102, answer (2), to whether the engraver travelling along the S4 conveyor is the course's S5, the xTool F1 Ultra
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Reasoning:Verified as a statement of the design, on how the conveyor can run. No reversal of the belt has been observed or recorded. What commands the belt and chooses its direction is not known. 'mode' is read as 'move', the project's reading of a typing slip; the sentence answers whether the belt runs one way only.
Evidence · 1 citation
The conveyer can mode in either direction.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S176 (2026-10-11), on the order along the S4 conveyor
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Defects found on the xArm 6 side do not end up in S3's defects area at this time. The plan is to add another area for them ('another area or something'), which is to be determined (int-539).
Evidence · 4 citations
whether S154's first answer means the xArm 6 side's defects no longer go to S3's defects area
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S155 (2026-10-07), question (1) as given in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
xArm 6 defects does not end up in S3 at this time
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S155 (2026-10-07), first answer
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
we plan on adding another area or something
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S155 (2026-10-07), first answer, continued
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
sArm 6 does not reach s3, another area for defects has to be determined. It is currently unknown.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S154 (2026-10-07), first line of the answer
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The xArm 850 at S2 has a working camera of its own (confirmed after the station was set up on 2026-10-08), on the arm itself. It is not one of the cell's numbered cameras: the arm's camera and those cameras are not related.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Reasoning:Verified as a statement of the lab's state on the dates given: that the camera works, S172 (2026-10-09), after the station was set up on 2026-10-08; that it is on the arm itself and is not one of the Cx cameras, S181 (2026-10-12) and S183 (2026-10-13). No inspection is recorded here. S182's 'No cameras have been set up yet' (2026-10-12) was given to a question about 'Cx' and does not name this camera; whether it reaches this camera is a reading this record takes no position on (int-116).
Evidence · 6 citations
10/8 I set up the x850 station. I confirm that the x850 has working camera
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S172 (2026-10-09), item 2, after setting up the xArm 850's station
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
850 camera - there are multiple cameras, you are conflating the Cx cameras with the arm camera, they are not related. The 850 camera is on the arm itself.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S181 (2026-10-12), the line he numbered 3.3, answering §3.3 of the 10-09 decisions file ('Which camera is it, and where is it mounted'), which the message S181 replies to did not ask; 'the Cx cameras' are all of the cell's numbered cameras (S182, answer 4, cited below)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
'Cx': does that include a C3, or only C1 and C2?
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S182 (2026-10-12), question (4) as given in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Cx includes all of them.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S182 (2026-10-12), answer 4, first sentence; the topic mapping lists cameras C1 to C3 (int-036)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
I confirm that the Cx are for all the station cameras
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S183 (2026-10-13), second clause, its beginning
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
and not the x850 arm camera.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S183 (2026-10-13), second clause, its end; the words between this and its beginning, an example he gave and hedged, are not quoted
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The xArm 850 is to use its camera to select the correct material to fulfill an order, and possibly to check that material so that defective material is not used.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Evidence · 1 citation
The camera on the 850 allow sthe bot to select the correct material to fulfill the order as well as possible qaqc on the material to make sure that defective material will not be used.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S91 (unchanged by S172 and S181; rule 7, the earlier citation kept)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The cell uses two collaborative arms: the xArm 850 at S2 is the upstream arm that takes incoming material off receiving toward personalization, and the xArm 6 at S6 is the downstream arm that handles parts after processing.
Evidence · 2 citations
The xArm 850 at S2 is the **upstream** arm: it takes incoming material off receiving and hands it off toward personalization
The S4 conveyor is part of S4, so S6 picks up from S4, however the item's final placement is met.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Evidence · 1 citation
The Conveyer is part of S4 so S6 picks up from S4 regardless of how the item's final placement is met.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S119, to whether S6 still picks up at S4 or the conveyor carries the product to S6
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
With two arms, loading incoming material (S2) and unloading and routing finished parts (S6) can happen at the same time. With one arm, both handling steps for every part would run one after the other on the same arm. The two steps meet at S4, where both arms work (int-062); how the arms share S4 is not documented. How much two arms help throughput is unknown, because no cycle times are documented (int-033), and the laser step may be the real bottleneck.
Why we infer this:Verified: the gift flow has two separate Cobot Handling steps, one before staging and laser engraving and one after (int-028), assigned to S2 and S6 (int-029). One arm would have to perform both in series; two arms let them overlap. This shows the steps can overlap, not that one arm would be the bottleneck: that depends on cycle times, which no available source documents (int-033). Verified: both arms work at S4, one placing the material and the other picking up the finished product (int-062), so the two handling steps meet at one station; no source says how the arms share it (int-612).
None of the cell's numbered cameras had been set up as of 2026-10-12.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Reasoning:Stated twice, in answer to questions. Asked about the whole-cell view's S10, C1, C2 and S11 (S138, 2026-10-05): 'Camera placement is currently unknown and not set up in the lab.' Asked whether 'Cx' includes a C3 or only C1 and C2 (S182, 2026-10-12): 'Cx includes all of them. No cameras have been set up yet.' Whether 'No cameras' there means every camera or the Cx cameras only, the cell's numbered cameras are inside it, so this statement does not depend on that reading and takes no position on it. S183 (2026-10-13) says the Cx cameras are the station cameras and not the xArm 850's arm camera; it does not say which cameras 'No cameras' covered. The xArm 850's own camera is not this record's subject: int-114 stands on S172 and S181. S182's answer was given to a question about 'Cx' and does not name the arm's camera; whether its 'No cameras' reaches that camera is the reading this record takes no position on. Verified as a statement of the lab's state on the dates given; no inspection is recorded here.
Evidence · 5 citations
'Cx': does that include a C3, or only C1 and C2?
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S182 (2026-10-12), question (4) as given in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Cx includes all of them. No cameras have been set up yet.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S182 (2026-10-12), answer 4
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Camera placement is currently unknown and not set up in the lab.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S138 (2026-10-05), answer 10a, to a question about the whole-cell view's S10, C1, C2 and S11
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
I confirm that the Cx are for all the station cameras
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S183 (2026-10-13), second clause, its beginning
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
and not the x850 arm camera.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S183 (2026-10-13), second clause, its end; the words between this and its beginning, an example he gave and hedged, are not quoted
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Confidence: VerifiedThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-015
The record says
In this project's S2 design, S2 moves buffered workpieces from S3 to S4 once S4 gives its 'all clear and ready' signal. The concept holds on both substrates; the physical I/O may differ.
Evidence · 2 citations
S2 goes back and moves from S3 to S4 when S4 is busy and needs to provide an 'all clear and ready' signal.
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21
Project copy; not published on this site.
Confidence: VerifiedThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-020
The record says
In this project's S2 design, S2 communicates its own state as well as receiving other stations' state. What it publishes is not yet defined (see int-047).
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21
Project copy; not published on this site.
Confidence: VerifiedThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-095
The record says
Each arm's agent is designed to run the order and report problems. On the order's normal path it moves the arm itself, with no person approving each move. Anything off that path, it pauses and reports with a recommendation, and a person decides. This project names that design level 5E. The same level and the same report-don't-correct rule apply to both arms' agents: the xArm 850's at S2 and the xArm 6's at S6.
Evidence · 5 citations
Runs the order, reports problems
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), answer (1)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
On the normal path the agent moves the arm by itself, with no person approving each move. Anything off the path: it pauses and reports with a recommendation, and a person decides.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the option answer (1) chose (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
(This is our current design, called 5E.)
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the same option's name for the design (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Both arms
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), answer (2)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
The same level and the same report-don't-correct rule for both agents.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the option answer (2) chose (the option's words)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Confidence: VerifiedThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-091
The record says
While an arm works an order, its agent watches that the steps it is supposed to do are completed. Anything that falls outside the order's processing paths, it reports instead of correcting: if an issue arises, it pauses and alerts the person working with the cell, giving the issue and recommended actions. The same rule applies to both arms' agents.
Evidence · 4 citations
the agent is monitoring the arm and making sure the skills that are supposed to be done are being completed, if an issue arises, the agent will pause and alert the human collaborator with the issue and recommended actions.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
the agent observes and reports any deltas that falls outside of the order processing paths and reports the issue, instead of taking direct corrective actions.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (1)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Both arms
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), answer (2)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
The same level and the same report-don't-correct rule for both agents.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the option answer (2) chose (the option's words)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Kind: RecommendationThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-053
Project advice
Until S11's safety function is documented and verified, neither learners nor the S2 agent should treat S11 or the cameras as a safeguard. The S2 agent must not rely on them to stop motion or to protect people.
This is advice from this project, based on: int-024 Verifiedint-050 Gap, awaiting cell access
Why:S11 is described only as monitoring that includes safety (int-024). Nothing establishes a safety rating, stop authority or response time (int-050). Treating an unrated monitoring system as a safeguard is the failure the Q3 disposition warns against: an Assumed safeguard mistaken for a confirmed one.
S7, a Prusa 3D printer, is a future production extension that produces customized 3D-printed parts and supports a future hybrid additive-plus-laser workflow.
In IntelliMake's future 3D-printed flow, S6 handles parts coming from S7 (3D printing) and passes them to laser engraving or marking, so S6 serves both production flows.
Evidence · 1 citation
S7 3D Printing → S6 Robot Handling → S4/55 Laser Engraving or Marking
The factory cameras, including C1, feed the S11 IntelliAware monitoring layer.
Why we infer this:The mapping table groups cameras C1–C3 with S11 under AI vision for safety, and the layout draws dotted connectors from the camera icons to S11. The data path itself (protocol, what is sent) is not documented.
Evidence · 1 citation
AI Vision – Safety | Cameras C1–C3 + S11 IntelliAware
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · HW2 SME topic mapping table
Confidence: VerifiedThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-016
The record says
In this project's S2 design, when S3 and S4 are both unavailable, S2 monitors S4 and, once S4 is available, dispatches a workpiece from S3 to S4. The freed S3 space then lets S2 take material from S1 again.
Evidence · 1 citation
If both S3 and S4 are unavailable, S2 monitors s4 for availablilty then dispatches from s3 to make that available again, which then allows for material from S1 as well.
IntelliMake automation level 3 is 'Flexible': the conveyor action is 'Selects predefined modes', and the primary decision maker is the automation system.
IntelliMake automation level 4 is 'Intelligent/Adaptive': the conveyor action is 'Algorithm-driven adjustments', and the primary decision maker is the algorithm.
IntelliMake automation level 5 is 'Agentic/Autonomous': the conveyor action is 'Objective-driven execution', and the primary decision maker is the AI agent.
Evidence · 1 citation
Level 5 | Agentic/Autonomous | Objective-driven execution | AI Agent
The Progression Cheat Sheet: 6 stages of manufacturing automation · IntelliMake.org · Level 5 row
IntelliMake sub-level 5B, 'Understand & Determine': it interprets information, forming an interpretation of the operating situation from observed data.
Evidence · 1 citation
Forms an interpretation of the operating situation based on observed data.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5B
IntelliMake sub-level 5C, 'Recommend': it advises the human operator, determining an appropriate action and recommending it while the human keeps decision authority (human in the loop).
Evidence · 1 citation
Determine an appropriate action and recommend it, but human retains decision authority.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5C
IntelliMake sub-level 5D, 'Act with Human Approval': it authorizes machine action: the machine can act, but only after specific authorization, and the human keeps final authority.
Evidence · 1 citation
The machine can act, but only after specific authorization.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5D
IntelliMake sub-level 5E, 'Limited Autonomous Control': it operates within guardrails, with permission to make certain decisions independently within established safety and process limits and then monitor the outcome (human on the loop: supervision and exception handling).
Evidence · 1 citation
Permission to make certain decisions independently within established safety and process limits.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5E
IntelliMake sub-level 5F, 'Full Autonomy': it achieves objectives: given objectives rather than instructions, it perceives, understands, decides, acts, observes the result, learns and adapts, and replans.
Evidence · 1 citation
Given objectives, not instructions.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5F
IntelliMake frames the shift to agentic automation as follows: traditional automation tells the machine what to do and how, while agentic automation gives it a goal, situational awareness, reasoning capability, tools and the authority to determine what should be done.
Evidence · 1 citation
Agentic automation gives the machine a goal, situational awareness, reasoning capability, tools, and authority to determine what should be done.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel 'The fundamental shift'
IntelliMake's two-dimensional digital twin framework classifies a digital representation along two axes: its physical-digital coupling, which is how deeply the digital and the physical interact, and the scope of the physical world it represents.
Evidence · 3 citations
Classifying digital representations by their connection strength and physical scope.
The Two-Dimensional Digital Twin Framework (class slide) · IntelliMake.org · The slide's subtitle
On its coupling axis the framework names five levels, from the least coupled to the most: Digital Image, Digital Model, Digital Monitor, Digital Guide and Digital Twin.
Evidence · 1 citation
DIGITAL TWIN DIGITAL GUIDE DIGITAL MONITOR DIGITAL MODEL DIGITAL IMAGE
The Two-Dimensional Digital Twin Framework (class slide) · IntelliMake.org · The left column, top to bottom, beside the 'Increasing Coupling' arrow
In the framework, a Digital Twin, the highest level of coupling, has synchronized interaction both ways, from the physical to the digital and from the digital to the physical. Its verb is 'Optimize'.
Evidence · 1 citation
DIGITAL TWIN Optimize Synchronized interaction. Physical ⇄ Digital.
The Two-Dimensional Digital Twin Framework (class slide) · IntelliMake.org · The left column, the Digital Twin row
On its scope axis the framework names three scopes: a part or product (parts, subassemblies, assemblies and products); a machine, cell or line, the production-system level (machines, cells and production lines); and a facility, enterprise or ecosystem (large-scale systems).
Evidence · 3 citations
PART / PRODUCT At the smallest scale: Parts, Subassemblies, Assemblies, Products
The Two-Dimensional Digital Twin Framework (class slide) · IntelliMake.org · Under the horizontal axis, the first scope
Confidence: InferredThis project's simulation and agent design, not the physical cellProject design, not the physical celllvl-025
The record says
On IntelliMake's framework, this site's simulator (Practice in the Simulator) is a simplified Digital Model: its bench page is a machine-level one, and each station page a cell-level one. It simulates the arm's motion against the scene's limits, and no data flows between it and a real arm in either direction.
Why we infer this:Verified: a Digital Model is geometry, physics and simulation (lvl-019), and each level of coupling above it adds a flow of data: from the physical to the digital for a Digital Monitor (lvl-020), from the digital to the physical for a Digital Guide (lvl-021), and both ways for a Digital Twin (lvl-022). That the simulator has had no such flow since it went live on 2026-10-12 (the gate's pushed head, commit e2bd438) is the repository's state, not something a cited source says (corpus/README.md, Records About This Project's Own Simulation, rule 2): the bench and station pages load their scene from the site's own file (the site's learn/_app/operate/operate.js:45), the whole-cell view likewise (whole.js:14); every request these pages make is for one of the site's own files, the scene and the arm's 3D model (learn/_app/3d/arm.js:179, cellview.js:45), and operate.js's header says nothing in it talks to a machine or a server; by this project's design no web page can command real hardware (docs/specs/operate-twin-design-brief.md §2.4). Each page labels its model simplified. So the simulator sits at the Digital Model level: machine scope for the bench, one arm on a table, and cell scope for a station page, the arm at its station among the cell's cabinets and conveyors (lvl-023). This is the project's own reading of where its pages sit; the framework does not name them.
Evidence · 2 citations
DIGITAL MODEL Understand Geometry, physics & simulation (CAD, FEA).
The Two-Dimensional Digital Twin Framework (class slide) · IntelliMake.org · The left column, the Digital Model row
Incoming orders will carry the parameters of the cards. This was given as the answer to where an incoming card's color comes from.
Evidence · 2 citations
where an incoming card's colour comes from
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S154 (2026-10-07), the list of questions in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Card color - incoming orders will have the parameters of the cards.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S154 (2026-10-07), second line of the answer
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
To arrange cards on S3 as the cell's route requires, S2 has to know each card's color, which area of S3 holds that color's stack, and how full that stack is against a stack limit; the limit is not documented. To send a card to the defects area instead, it needs a way to judge the card defective, and S2's camera may possibly check material for that.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Why we infer this:Verified: S2 arranges cards on S3 with same-color cards stacked in the same area (int-080, int-084), and defective parts reach S3's defects area from S2 (int-107). Placing a card on the right stack needs the card's color and where that color's stack is; a stack on a table cannot grow without bound, so S2 also needs its height against a limit, which no source gives (int-094). Sending a card to the defects area needs a judgment that it is defective; the only stated means is the camera's possible check of material (int-115). Where a card's color comes from is stated: incoming orders will carry the parameters of the cards (int-109). No source says those parameters reach S2, or names any of these as S2's inputs; that S2 needs them follows from the tasks.
Evidence · 3 citations
stacking cards of the same color in the same area
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
On top of each other
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (3)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
The camera on the 850 allow sthe bot to select the correct material to fulfill the order as well as possible qaqc on the material to make sure that defective material will not be used.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S91
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The current assumption for the IntelliMake agents is that they do not talk to each other directly: they exchange information, and may collaborate, through a central shared knowledge space (a hub). IntelliMake leadership has not finalized this.
How this would be checked:IntelliMake team leadership's design for the shared knowledge space: its protocol, schema and hosting (open question Q9).
Evidence · 1 citation
The agents will not talk directly to each other, rather will exchange information in a central hub and possibly colloborate in that space. That has not been fully fleshed out by the iIntelliMake team leadership.
Camera C1's field of view covers the S1 receiving area that S2 picks from, so C1 could confirm material presence and state for S2.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
How this would be checked:Observe C1's physical mounting and field of view at the cell, and whether its output is available to S2 through S11 or the shared hub.
Evidence · 1 citation
Camera C1 – Receiving
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · Camera C1 icon placement
In a Phase 1 layout drawing, S2, S4, S6 and S8 stand in one row, in that order, so S4 lies between the two arms' stations. S3 is beside S2 and S7 beside S6, on the same side of the row; S1 is beside S2 on the other side.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Evidence · 7 citations
S2
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S4
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S6
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S8
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S3
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S1
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The drawing's labels
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S7 Repurposed Defect Table - Proposed location for Phase 1. Known as S7 3D Printer
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow · The box drawn above S6
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Both arms work at S4 (int-062), but the stations only one arm serves lie on opposite sides of it: receiving and staging (S1 and S3), served by S2, and the stations after S6, such as S8, where S6 sends parts for shipping by default. So a single arm probably could not reach both receiving and staging and the stations after S6.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
How this would be checked:Measure the as-built positions of S1, S3, S4, S6 and S8 relative to each arm's base and compare them with the published reach of each arm.
Evidence · 5 citations
S2 UFactory xArm 850 Cobot
IntelliMake Phase 1 Factory: Autonomous Production Demonstrator (infographic) · IntelliMake.org · S2 station label
UFACTORY publishes a longer reach for the 850 (850 mm, maximum payload 5 kg) than for its xArm 5/6/7 line (700 mm, with payloads from 3 kg to 5 kg across the line). No xArm 6-specific figure is cited here, and no source says whether reach decided which arm went to S2.
IntelliMake distinguishes intelligence (does the machine know what should be done?), authority (is the machine allowed to do it?) and autonomy (can it keep operating and adapting without repeated human intervention?), and holds that true autonomous manufacturing needs the right combination of all three.
Evidence · 1 citation
True autonomous manufacturing requires the appropriate combination of all three.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel 'Understanding the differences'
A placement policy that fixed rules alone could carry out would sit at IntelliMake levels 1–3, not level 5. S2's level 5E claim therefore depends on decisions the rules do not cover, made within guardrails.
Why we infer this:Level 1 is hard-coded logic and level 3 selects among predefined modes (lvl-002, lvl-004). If S2's behavior were fully specified by its route and rules (int-081, int-015, int-016), it would be level 3 at most. Level 5E requires the machine to make decisions within guardrails (lvl-011), so the 5E claim must rest on decisions beyond the base rules, such as anticipation, sequencing, and handling missing or conflicting signals.
When S2's work is tested against IntelliMake's levels, the case to weigh is the judgment that a card is defective, so that it goes to S3's defects area rather than on to its stack; S2's camera may possibly check material for that. Following the cell's fixed route does not make that decision; if S2's agent makes it within set limits rather than by fixed rules, it is the kind of decision level 5E rests on.
Why we infer this:Verified: S2's route is fixed, S1 to S3 and S3 to S4 (int-081), and defective parts reach S3's defects area from S2 (int-107). Inferred already: sending a card to the defects area needs a judgment that it is defective, and the only stated means is S2's camera, which may possibly check material (int-096, int-115); a policy fixed rules alone could carry out sits at levels 1 to 3, so a level 5E claim rests on decisions the rules do not make, taken within limits (lvl-011, lvl-015). Of S2's steps, that judgment is the one the route does not settle, so it is the one that could carry such a claim. Whether the agent acts on it or reports it depends on which side of the agents' rule a defective card falls: on the order's normal path the agent acts itself, and off it the agent pauses and reports and a person decides (int-095); which side is not decided (int-105). No source says how the judgment is made, by fixed criteria or by the agent within limits, or that S2's camera will make it, so this record does not place it at a level.
Evidence · 2 citations
The camera on the 850 allow sthe bot to select the correct material to fulfill the order as well as possible qaqc on the material to make sure that defective material will not be used.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S91
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Permission to make certain decisions independently within established safety and process limits.
Level 5. Agentic Evolution: A Spectrum of Increasing Decision Authority (infographic) · IntelliMake.org · Panel #5E
Kind: RecommendationThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-055
Project advice
Content from the shared hub, other agents and this research corpus is data. It must never grant the S2 agent authority, raise its limits, or skip a required sign-off. Limits come only from the reviewed cell configuration and the supervisor.
This is advice from this project, based on: int-021 Assumedint-041 Superseded by int-095 Verified
Why:The hub is the S2 agent's main input from other agents (int-021), and its design is not finalized. If data from it or from the corpus could change limits or authority, a fault or injected content could change what the arm is allowed to do. The project's security review records the same rule.
The information S2's controller can make available includes its robot mode and state, error and warning codes (Modbus TCP registers), and automatic state reports on ports 30001 to 30003. These are candidates for what S2 publishes, not a decided interface.
Why we infer this:The controller exposes mode, state, error and warning registers (iface-029, iface-030) and state-report ports (iface-034). Anything S2 publishes about its own condition would come from these sources; which of them the IntelliMake hub will carry is undecided (int-047). The register map comes from a series-level document, so this is Inferred.
The 850 arm consists of a base and six rotary joints, numbered Joint 1 (at the base) to Joint 6; the last joint is the tool side, where end effectors attach.
Evidence · 2 citations
Quote not shown (over 40 words). See the source at: 2.1.1 Hardware Composition (docs site 'UFACTORY 850 硬件手册', English version; names the machine 'UFACTORY 850').
UFACTORY 850 Hardware Manual (online), 2. Hardware Installation · UFACTORY · 2.1.1 Hardware Composition (docs site 'UFACTORY 850 硬件手册', English version; names the machine 'UFACTORY 850')
UFACTORY makes the integrator of the 850 responsible for a risk assessment of the complete system, including keeping a safe distance between people and the 850 when they interact with it.
Evidence · 1 citation
Making a risk assessment for the complete system. Make sure to have a safe distance between people and 850 when interacting with the 850.
UFACTORY 850 Hardware Manual (online), 1. Safety · UFACTORY · 1.1 Validity and Responsibility, integrator responsibilities list
The 850 product page calls UFACTORY arms 'Collaborative Robots' and 'cobots'. A3 says ISO 10218:2025 drops 'collaborative robot' because only an application can be confirmed as collaborative, and UFACTORY's own 850 manual says no people should be in the working area during operation. The marketing label does not establish that S2 is a collaborative application.
“Collaborative application” is used instead, as only the actual use of the robot can be designed, tested, and confirmed as a collaborative application.
Updated ISO 10218: Answers to Frequently Asked Questions (FAQs) (A3 blog, 03/20/2025; Wayback Machine snapshot 2025-10-06) · Association for Advancing Automation (A3) · FAQ 6
UFACTORY's 850 page, under 'Flexible Deployment With Safe Feature', cites hand teaching, a space-saving footprint and easy re-deployment to multiple applications without changing the production layout, and says collision detection is available for all its cobots.
Evidence · 2 citations
Hand teaching, space-saving and easy to re-deploy to multiple applications without changing your production layout. Perfectly for recurrent tasks.
No fetched UFACTORY document calls the 850's collision detection, safety boundary or reduced mode safety-rated, or gives them a performance level.
Why we infer this:Verified: collision detection is a model-based current comparison that UFACTORY says can false-trigger with wrong settings and can be disabled (level 0, Advanced Settings toggle, a documented default password); safety boundary and reduced mode are software settings exposed in Studio and the SDK. UFACTORY distinguishes safety signals (EI/SI, redundant pairs) from non-safety devices. Inferred: no fetched UFACTORY source assigns a PL, Category or safety rating to these software functions (see the gap on performance level); this is a statement about the documents fetched, not proof that no rating exists.
Evidence · 3 citations
By comparing the theoretical current and actual current of each joint, the system determines whether a collision has occurred.
Collision Detection in UFACTORY Robotic Arms: Current and Dynamic Model-based Feature (UFACTORY support article) · UFACTORY · Section 1
Never connect a safety signal to a non-safety PLC.Failure to follow this warning may result in serious injury or death due to an invalid safety stop function.
Kind: RecommendationThis project's simulation and agent design, not the physical cellProject design, not the physical cellsafety-140
Project advice
Treat the 850's collision detection, safety boundary and reduced mode as configurable controller functions, not as validated safeguards: they must not replace the risk-assessed protective devices wired to the EI and SI inputs.
This is advice from this project, based on: safety-087 Inferredsafety-062 Verifiedsafety-067 Verifiedsafety-073 Verifiedsafety-074 Verifiedsafety-057 Verified
Why:No fetched UFACTORY document gives these functions a safety rating or performance level (safety-087). Collision detection is a current-model comparison that can false-trigger and can be switched off (safety-062, safety-067); safety boundary and reduced mode are software settings (safety-073, safety-074). UFACTORY keeps safety signals separate from non-safety devices (safety-057). A function with no documented rating cannot stand in for a rated protective device.
The future 3D-printed flow in the IntelliMake diagram has no S2 step (printed parts go from S7 straight to S6), but S2's stated role includes handling material for 3D printing in the future. What S2 does in the future flow is unresolved: IntelliMake says it could be S3, S4 or S7, that this is subject to change, and that the cell is not locked into any configuration.
The layout draws unlabeled return paths from the laser and S6 region back toward S1 and S2. Whether reworked parts re-enter through S1 or S2, and what S2 does in rework, is not documented.
IntelliMake's reason for putting the 850 at S2 and the xArm 6 at S6 is not documented. IntelliMake says only that the cell uses several arms for task-specific work and could add more (int-057).
The project specification describes S6 as the downstream arm that handles parts after processing, but IntelliMake's future 3D-printed flow has S6 handling parts before laser engraving (S7 → S6 → S4/S5). S6's role is therefore not simply 'after processing' in the future flow.
What S2 publishes to the other agents or the hub is not defined: placement confirmations, S3 slot updates, faults and error codes, its own ready or busy state, and whether any work-order or traceability data passes through S2. IntelliMake says this will be developed as the simulation is created.
Whether S11 IntelliAware has any authority to stop or slow S2, whether it is a safety-rated protective device, and who owns S11 are not documented, and IntelliMake does not yet know. The diagram calls S11 'monitoring of ... safety', which does not make it a safeguard.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
S97 says the cabinet sizes are all the same, while the measurements table gives the S4 cabinet as 32.5 in high and 50 in long, against 32.25 in high and 25.5 in long for S2, S3, S6 and S8. The height difference is settled by int-099: S4 was 32.5 in high when the table was taken, and every station's height is adjustable. The length difference is not settled by any statement: the project reads S97 as covering the 25.5 in cabinets (S2, S3, S6, S7 and S8), and that reading is unconfirmed.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
IntelliMake's written answer (Batch 01, Question 2) and the project's earlier statements have S2 place a part on S4, or on S3 when S4 is busy or the part does not fit there, so that parts need not pass through staging; this project's simulation was specified from that reading, moving cards from one conveyor to another (int-013, int-014, int-051). The project's later statement S146, answering which is right now, gives the route as S1 to S3, and S3 to S4: S2 arranges parts on S3 first, then later moves them from S3 to S4 (int-081). The later statement is the current reading; the earlier records are kept as history, marked as superseded.
Related: int-014 Superseded by int-081 Verifiedint-051 Superseded by int-081 Verifiedint-060 Superseded by int-081 Verifiedint-081 Verifiedint-013 Superseded by int-081 Verified
Evidence · 5 citations
S2 can place either on s3 or s4 depending upon availablitity or fit could even pause if neither are available.
xArm 850 S2 Project: Open Questions for IntelliMake, Batch 01 responses · IntelliMake.org · Question 2, Answer column
The project's earlier statement says S2 'can not simply stack' workpieces (int-017), which this project's S2 design read as one card per place on S3. Asked whether same-color cards are placed on top of each other or side by side, the later statement S146 answers 'On top of each other': real stacks on S3 (int-084). The later statement is the current reading for S3, and int-017 is kept as history, marked as superseded. Whether the rest of the earlier rule, not breaking the space the system allocates, still holds is not stated.
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21
Project copy; not published on this site.
Our safety rules today forbid stacking: one card per spot on S3. Do you mean cards placed on top of each other, or side by side in the same area?
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), question (3) as asked
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
On top of each other
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (3)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Kind: ContradictionThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-092
Sources disagree
The earlier target for the S2 agent is level 5E, limited autonomous control, with the goal of not needing human approval (int-041). A later statement says the agent operates the real arm in fulfilling orders but is not expected to work semi-autonomously: it reports deviations instead of correcting them (int-090, int-091). That answer took none of the options on whether 5E stays the goal. The later statement S148 settles it: 'Runs the order, reports problems', for 'Both arms'. On the order's normal path the agent moves the arm with no person approving each move; anything off the path, it pauses and reports with a recommendation, and a person decides; the option chosen names this the current design, 5E (int-095). So 5E stays the design for both arms' agents, the goal of not needing human approval holds on the normal path, and int-041 is kept as history, marked as superseded.
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21
Project copy; not published on this site.
the agent is not expected to work semiautonomous
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (1)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Runs the order, reports problems
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), answer (1)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
On the normal path the agent moves the arm by itself, with no person approving each move. Anything off the path: it pauses and reports with a recommendation, and a person decides.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the option answer (1) chose (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
(This is our current design, called 5E.)
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), the same option's name for the design (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Both arms
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S148 (2026-10-07), answer (2)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
How S3 is divided between its staging and defects areas, how many colour areas staging holds, and how many cards a stack may hold are not documented. Whether S3 can hold both kinds of material is itself open: a separate defects station could be added if it cannot (int-087).
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
S3 can serve two purposes, staging material in one area, and placing defects in another.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S145 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
On top of each other
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (3)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Kind: GapThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-097
Not known
Which decisions on the order's normal path remain the agent's own is not stated. The parts' route is fixed, S1 to S3 and S3 to S4 (int-081), and a defective part takes its own move, to the defects area on S3 (int-107), so the choice between S4 and S3 that the earlier design gave S2 no longer arises, while level 5E rests on decisions within limits that fixed rules do not make (lvl-011, lvl-015).
Kind: GapThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-098
Not known
How this project's simulation keeps to the cell's route is not fully settled. Since its configuration's schema 0.5.0 (2026-10-07), the simulation is configured to take each card from S1 to S3, then from S3 to S4 (int-081), and S3 has a staging area and a defects area whose stacks each hold up to 10 cards, a labelled placeholder (int-104; one card until 2026-10-18). Since 2026-10-09 the simulation's motion process refuses to place a card anywhere its route does not take it from the place it was picked, and refuses any pick or place in the defects area, which a person must decide (the way for a person to decide is not yet built). Keeping one colour to each stack, and which stack a card goes to, are designed but not enforced: they rest on labels the simulation cannot check. Before 0.5.0 the simulation placed each card on S4, or on S3 when S4 was busy (int-014).
The measurements table does not say what its 'Height' column is measured from. The cabinets' heights (32.25 and 32.5 in) and the S1 conveyor's (32 in) read as heights above the floor, and the S4 engraver conveyor's (3.5 in) and the S2 and S6 mount plates' (1 in) as each item's own height; this project's Operate scenes draw them that way (the agent's simulation configurations keep placeholder surfaces), and that reading is unconfirmed.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
How this would be checked:Measuring at the cell from the floor to the top of each cabinet, conveyor and mount plate would settle it.
Phase 1 measurements table, sent by Derek with the layout drawing (2026-09-30) · Derek Stringfellow · Table, header row
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S1 Conveyer 32 18.5 51.5
Phase 1 measurements table, sent by Derek with the layout drawing (2026-09-30) · Derek Stringfellow · Table, 'S1 Conveyer' row (Height, Width, length)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S4 Engraver conveyer 3.5 38.5
Phase 1 measurements table, sent by Derek with the layout drawing (2026-09-30) · Derek Stringfellow · Table, 'S4 Engraver conveyer' row (Height, then length)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
S2 Mount Plate 1
Phase 1 measurements table, sent by Derek with the layout drawing (2026-09-30) · Derek Stringfellow · Table, 'S2 Mount Plate' row (Height)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30
Project copy; not published on this site.
Kind: GapThis project's simulation and agent design, not the physical cellProject design, not the physical cellint-105
Not known
Whether a card a camera judges defective is on the order's normal path, so that the agent sends it to a defects area itself (for S2, S3's defects area, int-107; where the xArm 6 side's defects go is not known, int-539), or off it, so that the agent pauses and a person decides, is not decided. Until it is, the simulation is designed to pause and report; that behavior is not yet built.
When a camera judges a card defective (S2's checking incoming material, or S6's after the engraver), what should the agent do?
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S152 (2026-10-07), the question as asked
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Not decided yet
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S152 (2026-10-07)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Leave it open; the simulation pauses and reports until you decide.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S152 (2026-10-07), the option chosen (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The earlier statement S146 says defective parts reach S3's defects area from S2 and from the xArm 6 side, including defects found after the engraver or the printer (int-086), and the option chosen in S149 repeats that defects go to S3 (int-535). Asked whether S154's first answer means the xArm 6 side's defects no longer go to S3's defects area, the later statement S155 answers that they do not end up in S3 at this time. The later statements are the current reading for the xArm 6 side (int-538); where those defects go instead is a gap (int-539). S154 and S155 leave S2's half of int-086 and int-535's rework half unchanged: int-107 and int-540 carry them, keeping the earlier citations (S146, S149), which the later statements do not restate. int-086 and int-535 are kept as history, marked as superseded.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), answer (4)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Defects found after the engraver or printer also end up in S3's defects area.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S146 (2026-10-07), the option answer (4) matches (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Rework is its own flow; defects go to S3.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S149 (2026-10-07), the option answer (2) chose (the option's words, not his)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
whether S154's first answer means the xArm 6 side's defects no longer go to S3's defects area
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S155 (2026-10-07), question (1) as given in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
xArm 6 defects does not end up in S3 at this time
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S155 (2026-10-07), first answer
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S154 (2026-10-07), the list of questions in the bracket
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Defects area - management of area is currently unknown.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S154 (2026-10-07), third line of the answer
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The earlier statement S97 says the engraver can travel along the length of the S4 conveyor (int-068). The later statement S172 says the engraver will remain stationary and the conveyor will move the product from one location to another (int-111). This project reads S172 as replacing S97, and int-111 as the current reading: S97 says what the engraver can do, a capability, and S172 how the cell will run, the plan, so the cell is described as running with a fixed engraver. Whether the two statements conflict at all, or the engraver can still travel and will not be used that way, is not settled: only the person who made both statements can settle it. S97's other half, that the engraver and the conveyor are interconnected systems, is unchanged; int-112 carries it with S97's citation. int-068 is kept as history, marked as superseded.
Reasoning:This project's reading, not one either statement gives: S97's "can travel" names a capability of the engraver; S172's "will remain stationary" names the plan for the cell. A plan stated later is taken for how the cell runs, which is what the lessons and the agents' configurations describe.
What the xArm 850's payload setting of 0.61 kg (int-552) stands for is not stated. The figure equals the weight UFACTORY lists for its Vacuum Gripper (AS1200), 610 g (comp-070), and the payload of UFACTORY Studio's preset named 'Vacuum Gripper', 0.61 kg (ops-092). The figures match; the match does not show which tool the arm carries (int-034).
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
UFACTORY Studio's Device Info page for the xArm 850, screenshot (2026-10-16) · Derek Stringfellow · Device Info page (Settings, My Device, Device Info), status panel under the 3D view, 'Payload' line; 'Real' selected, not 'Sim'; the colon is full-width (U+FF1A) on screen, read by eye
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-16
Project copy; not published on this site.
Weight 610g
UFACTORY 850 Hardware Manual (online), 8. Technical Specifications · UFACTORY · Vacuum Gripper(AS1200) table (docs site 'UFACTORY 850 硬件手册', English version; names the machine 'UFACTORY 850')
Not stated for S4: what the engraver carriage's 465 mm height is measured from (the belt, the table or the floor; int-611); the engraver's width across the belt, and whether any of it reaches past the belt's sides; where the unit stands in the cell; whether and how it would be interlocked; whether the conveyor may move while an arm places or picks at S4; and how the two arms share S4: whether both may work there at the same time, and if not, in what order and on whose signal. The carriage area's extent along the conveyor and its height were given on 2026-10-22 (S222, S224, S226; int-611), final for the engraver but not for the station.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
Reasoning:What the earlier gap on S4 (named in related) left unstated and the 2026-10-22 figures do not answer, with the one new question no record answers: how the two arms share S4 in time (int-011, int-062). This record keeps that gap's citations (rule 7). It replaces that gap when the run of s2-agent/tools/set_carriage_area.py marks it superseded; until then both stand, and the earlier gap's "Not stated" on the carriage's height is answered in part by int-611: a figure, 465 mm, with no datum.
Quote not shown (over 40 words). See the source at: Statement S194 (2026-10-14, about 10:50), the S4 conveyor's areas.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S194 (2026-10-14, about 10:50), the S4 conveyor's areas
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
S4 engrave will remain stationary and the conveyer swill be the means of moving the product from one location to another.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S172 (2026-10-09), IntelliMake Notes
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
We have not determined what functionality will be used since the conveyer is an attachment to the engraver and the conveyer may be the only location to location movement for the product. So this is TBD for now.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S118, answer (2), to whether the engraver travelling along S4 enters the arms' place and pick zones and is interlocked
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
The engrave actually can travel along the length of the conveer.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S97
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
Yes, it is S5
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S102, answer (2), to whether the engraver travelling along the S4 conveyor is the course's S5, the xTool F1 Ultra
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
both arms work at S4. one places the material to perform the work, the other picks up the finished product
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S84, answering Q55(1)
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
The statements of 2026-10-22 disagree on where the engraver stood that day. S222, item 1, about the xArm 850, says "It is mounted on station cabinet, like x6, engraver and 3d printer, as expressed previousilly." S226, later the same day, says "The engraver is on a different table and n ot sittng on the final station cabinent yet." S226 is taken as current for where the engraver stood on 2026-10-22, because it is later and specific; that is the project's reading, and item 1 may restate the design ("as expressed previousilly"). It is asked (Question 7 of the carriage design note). Either way the engraver's place in the cell stays a placeholder.
Awaiting cell access: this could be confirmed or corrected once the physical S2 cell can be observed.
1. It is mounted on station cabinet, like x6, engraver and 3d printer, as expressed previousilly.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S222 (2026-10-22, from the lab), item 1, on how the xArm 850 is mounted
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
Project copy; not published on this site.
engraver was measured from the 850 end. THese are final measurements for the engraver but not the station. The engraver is on a different table and n ot sittng on the final station cabinent yet.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow · Statement S226 (2026-10-22, from the lab, after S225), answering which end of the belt the carriage area was measured from and whether the figures are final
Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04
CODE_SESSION 01 — xArm 850 Interactive Learning Platform (project specification) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21 · cited by 3 records here · Project copy; not published on this site.
Owner statements from 2026-09-24 onward (verbatim; S40 and later) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-04 · cited by 41 records here · Project copy; not published on this site.
Owner statements, 2026-09-21 (verbatim) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-21 · cited by 10 records here · Project copy; not published on this site.
Phase 1 layout drawing, sent by Derek (2026-09-30) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30 · cited by 3 records here · Project copy; not published on this site.
Phase 1 measurements table, sent by Derek with the layout drawing (2026-09-30) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-09-30 · cited by 2 records here · Project copy; not published on this site.
UFACTORY Studio's Device Info page for the xArm 850, screenshot (2026-10-16) · Derek Stringfellow (project owner) Derek Stringfellow, project record · Project-internal record · retrieved 2026-10-16 · cited by 1 record here · Project copy; not published on this site.
This site keeps what the courses need to work in this browser: the tier you chose, the questions you answered correctly, whether you have visited before, and your filter and display settings. It stays on this device, and nothing you choose here changes it.
This site uses no third-party analytics. No analytics script, tracking pixel or tracker from another company loads by itself on any page, so there is nothing here to allow or refuse. A lesson video loads from YouTube only when you press Play, as its note says. If analytics is ever added, it will be named here, and it will load only after you allow it.
What each one records
Who
What
When
This site
The tier you chose, the questions you answered correctly, whether you have visited before, your filter and display settings
Always, in this browser only
You can change this at any time from “Analytics choices” at the foot of every page.