board
65% MX Keyboard (soldered)
Public Unreviewedby gzc
65% ANSI keyboard PCB (68 soldered MX switches) for a gasket-mount case, rev B: STM32F072 under the spacebar running QMK, USB through a Unified Daughterboard on a Pico-EZmate cable, strict-grid copper, green with lead-free HASL, PCBWay bare board for hand assembly.
← Commit history
aiflow run 65-keyboard-claude-opus-5-5-20261109-0022: schematic
4 files changed
+27−7
docs/runs/65-keyboard-claude-opus-5-5-20261109-0022/README.md+27−7@@ -1,6 +1,6 @@ # AI Flow run: claude-opus-5-5 on board-0 -**Running**: step `routing`, 130.5 min of AI time since the prompt (182.3 min on the wall clock). This page updates at every step change.+**Running**: step `schematic`, 138.3 min of AI time since the prompt (190.1 min on the wall clock). This page updates at every step change. Prompt at 2026-11-09T00:22:00Z (UTC). Flow: board. Every number here is from the run's append-only ledger (run.jsonl). AI time is the time the AI was working on a prompt: from the human's prompt to the AI's done, with any gap over 15 min where no command ran (unobserved, not proven idle) cut out. @@ -10,8 +10,8 @@ One row per human prompt: the AI's time on it, unobserved gaps excluded by the h | Session | Prompt at | Done at | AI time min | Unobserved gap min | What | |---|---|---|---|---|---|-| 1 | 2026-11-09T00:22:00Z | (open) | 130.5 | 52 | the first prompt |-| **all** | | | **130.5** | | |+| 1 | 2026-11-09T00:22:00Z | (open) | 138.3 | 52 | the first prompt |+| **all** | | | **138.3** | | | ## Per step @@ -21,7 +21,7 @@ AI time only, the idle cut out. |---|---|---|---|---|---|---|---| | intake | 7.0 | 6.8 | 0.1 | 5 | 0 | 0 | 5.8 min | | placement | 31.6 | 12.4 | 19.2 | 60 | 3 | 2 | 4.2 min |-| routing | 38.6 | 3.7 | 34.9 | 6 | 3 | 0 | 3.7 min |+| routing | 45.9 | 5.0 | 40.9 | 7 | 3 | 0 | 3.7 min | | capture | 0.0 | 0.0 | 0.0 | 1 | 0 | 0 | 0.0 min | | components | 1.0 | 0.1 | 0.9 | 3 | 1 | 0 | 0.1 min | | design | 8.6 | 8.6 | 0.0 | 3 | 0 | 0 | 8.6 min |@@ -32,16 +32,17 @@ AI time only, the idle cut out. | parts | 3.1 | 1.8 | 1.3 | 5 | 0 | 0 | 1.5 min | | project-page | 3.1 | 2.3 | 0.9 | 11 | 0 | 0 | 1.1 min | | rules | 0.8 | 0.8 | 0.0 | 2 | 0 | 0 | 0.8 min |-| schematic | 12.3 | 12.2 | 0.1 | 2 | 0 | 0 | 8.6 min |+| schematic | 12.9 | 12.2 | 0.7 | 3 | 1 | 1 | 8.6 min | | simulation | 13.6 | 13.6 | 0.0 | 4 | 0 | 0 | 12.8 min | | sourcing | 4.5 | 4.5 | 0.0 | 7 | 0 | 0 | 4.5 min | | test-plan | 1.3 | 1.3 | 0.0 | 3 | 0 | 0 | 1.3 min |-| **total** | **130.5** | **71.8** | **58.7** | | | | |+| **total** | **138.3** | **73.0** | **65.3** | | | | | ## Returns to earlier steps - 2026-11-09T02:48:09Z back to **placement** (visit 2): router could not escape the STM32: matrix pins faced the board edge and decoupling caps boxed the chip in on all sides; turning U1 180 deg and moving caps to their supply pins - 2026-11-09T03:20:47Z back to **placement** (visit 3): Freerouting left U1 pins 11 (COL1) and 39 (COL12) unrouted: C8/C9 blocked the right-side escape of pins 10-12; caps moved to open it+- 2026-11-09T03:31:31Z back to **schematic** (visit 1): STM32 matrix pins re-assigned by side so each column/row leaves the chip toward its keys; the first map forced COL0-2 across the chip and COL11-14 out the board-edge side, leaving pins unroutable ## Decisions along the way @@ -53,6 +54,7 @@ AI time only, the idle cut out. - 2026-11-09T02:50:40Z clip-start:placement-2 - 2026-11-09T02:53:01Z clip-start:routing-2 - 2026-11-09T03:24:18Z clip-start:routing-3+- 2026-11-09T03:32:06Z clip-start:schematic-1 ## Where the board stands @@ -175,12 +177,30 @@ What this step does: route to 100 percent with the spec's rules, gate with KiCad What this step does: route to 100 percent with the spec's rules, gate with KiCad's DRC, land as undo steps; the AI takes it with take route=ai -**Clip: routing, visit 3, still recording (started 2026-11-09T03:24:17Z); it appears here when the step ends.**+**Clip: routing, visit 3, the PCB editor from 2026-11-09T03:24:17Z to 2026-11-09T03:31:37Z. Motion only: 7.3 min of real time, 0 s of it had something moving; the clock in the corner is the real elapsed time.**++<video width="100%" controls><source src="/blob/app/65-keyboard/docs/runs/65-keyboard-claude-opus-5-5-20261109-0022/routing-3.mp4" type="video/mp4"></video>++**Contact sheet: nine frames spread through the routing, visit 3 clip, what the camera saw.**++ **Screenshot: the board when routing, visit 3 began.**  +### schematic++What this step does: ++Why the AI came back here: STM32 matrix pins re-assigned by side so each column/row leaves the chip toward its keys; the first map forced COL0-2 across the chip and COL11-14 out the board-edge side, leaving pins unroutable++**Clip: schematic, still recording (started 2026-11-09T03:32:06Z); it appears here when the step ends.**++**Screenshot: the board when schematic began.**+++ ## Plan usage, the second cost line Percent of each plan limit used, as the provider reports it, at the start of the run and at its end.
docs/runs/65-keyboard-claude-opus-5-5-20261109-0022/routing-3-sheet.pngadded⋯ 1 unchanged line ⋯
docs/runs/65-keyboard-claude-opus-5-5-20261109-0022/routing-3.mp4added⋯ 1 unchanged line ⋯
docs/runs/65-keyboard-claude-opus-5-5-20261109-0022/shot-schematic-1-start.pngadded⋯ 1 unchanged line ⋯