12 V to 5 V / 1 A Buck Molecule (TPS54202)

@@ -1,9 +1,10 @@ # The process video: how it was made -The video on the [main page](https://wiki.adom.inc/john/buck-12v5v-molecule) tells this board's story start to finish: the prompt in Adom Hydrogen, the circuit, the three-engine simulation, the live layout in KiCad, the current and heat analysis and the rework it caused, the silkscreen, the part models and their wiki pages, the molecule on its scaffold, and what it cost. Every frame is real footage or a native render from this project.+The video on the [main page](https://wiki.adom.inc/john/buck-12v5v-molecule) tells this board's story start to finish: the prompt in Adom Hydrogen, the circuit, the three-engine simulation, the live layout in KiCad, the current and heat analysis and the rework it caused, the silkscreen, the part models, their pages on the Adom wiki, and what it cost. Every frame is real footage or a native render from this project. -- 3 min 25 s, 1080p, 30 fps, narrated, with subtitles burned in so it also works muted.-- [Download the 1080p copy](docs/video/buck-process-v2-1080p.mp4). The player on the main page is a 1600 px web copy.+- 3 min 28 s, 1080p, 30 fps, narrated from the first second to the last, with subtitles burned in so it also works muted.+- It opens and closes on the dark Adom logo sting from [adom/adom-video-brand](https://wiki.adom.inc/adom/adom-video-brand).+- [Download the 1080p copy](docs/video/buck-process-v3-1080p.mp4). The player on the main page is a 1600 px web copy.  ## Scenes and the footage behind them @@ -11,48 +12,49 @@ Each scene is seen through a slow, eased camera move, and long recordings are sp  | starts at | scene | footage | |---|---|---|-| 0:00 | The prompt | The prompt typed into a real Claude Code thread in Adom Hydrogen, filmed with Adom Bridge's window recorder. It opens on a full shot of Hydrogen, then pushes in on the composer. |-| 0:12 | Opening | A smooth orbit of the finished molecule, rendered frame by frame from its GLB (etched parts, green D1, rounded corners). |-| 0:24 | The circuit | The cleaned-up KiCad schematic, with the Adom-style TPS54202 symbol, explored by an eased camera move. |-| 0:39 | Simulation | Our own adom-spice dashboard run: ngspice, then LTspice, then PSpice for TI, ending on "3 engines agree on all 8 measurements". Idle time cut; vendor run times hidden (licence). |-| 1:02 | Placement | First run, placement clip: the AI placing 24 parts in KiCad 10, at 2.3x. |-| 1:15 | Routing and pours | Rework run: the routed traces with the pours stripped back, then the pours flooding back in. |-| 1:29 | Current and heat | First run, the Adom Fields current-density and heat walkthrough, at about 7x. |-| 1:44 | The rework | First run's routing rework, then the rework run's second routing visit. |-| 2:01 | Silkscreen, placed live | Rework run, the 16-minute live silkscreen session at about 88x. |-| 2:12 | Part models | Native KiCad 10 renders of the board before and after the part-model cleanup, then a smooth close-up of D1 from its etched side. |-| 2:28 | On the Adom wiki | Turntables of this board's seven parts as published on the Adom wiki, each labelled with its reference. |-| 2:43 | On the scaffold | The molecule on its LrgMed scaffold, wired to the control panel, rendered frame by frame. |-| 2:51 | What it cost | A cost card: tokens and model calls for the build and rework runs, their price at Claude API rates, and the practical cost on a 20x plan. |-| 3:10 | Close | A closing card over the finished board. |+| 0:00 | Logo sting | The dark Adom intro sting. The narration starts over it. |+| 0:04 | The prompt | The prompt typed into a real Claude Code thread in Adom Hydrogen, filmed with Adom Bridge's window recorder. It opens on a full shot of Hydrogen, then pushes in on the composer. |+| 0:14 | Opening | A smooth orbit of the finished molecule, rendered frame by frame from its GLB (etched parts, green D1, rounded corners). |+| 0:29 | The circuit | The cleaned-up KiCad schematic, with the Adom-style TPS54202 symbol, explored by an eased camera move. |+| 0:43 | Simulation | Our adom-spice dashboard run: ngspice in the container, then a second of the LTspice window and of PSpice for TI with the AI's cursor clicking Run, both driven through Adom Bridge, then the overlays agreeing. The two GUI shots come from the [adom-spice skillpack](https://wiki.adom.inc/adom/adom-spice-skillpack) recording of the same dashboard. Vendor run times hidden (licence). |+| 1:08 | Placement | First run, placement clip: the AI placing 24 parts in KiCad 10, at 2.3x. |+| 1:21 | Routing and pours | Rework run: the routed traces with the pours stripped back, then the pours flooding back in. |+| 1:35 | Current and heat | First run, the Adom Fields current-density and heat walkthrough, at about 7x. |+| 1:50 | The rework | First run's routing rework, then the rework run's second routing visit. |+| 2:07 | Silkscreen, placed live | Rework run, the 16-minute live silkscreen session at about 88x. |+| 2:18 | Part models | Native KiCad 10 renders of the board before and after the part-model cleanup, then a smooth close-up of D1 from its etched side. |+| 2:34 | On the Adom wiki | The live wiki pages of L1, C1, D1 and C2/C3, each scrolled from its 3D model down to its symbol and footprint (headless browser capture). |+| 2:48 | What it cost | A cost card: tokens and model calls for the board's build and rework runs, their price at Claude API rates, and the practical cost on a 20x plan. |+| 3:07 | Close | A closing card over the finished board. |+| 3:16 | Logo sting | The dark Adom outro sting, under the last line of narration. |  The step recordings are the ones on the [build clips](clips.md) and [rework clips](clips-rework.md) pages, taken from their raw 4K masters.  ## What it cost -Counted from this board's own Claude Code thread and its sub-agents, inside the two runs' clocks (the build, 2026-09-29 00:39 to 17:01 UTC, and the rework, 2026-09-30 01:08 to 11:33 UTC). The making of this video, and other threads open at the same time, are not counted.+Counted from this board's own Claude Code thread and its sub-agents, inside the two runs' clocks (the build, 2026-09-29 00:39 to 17:01 UTC, and the rework, 2026-09-30 01:08 to 11:33 UTC). Only the board is counted: the making of this video, other threads open at the same time, and side work that was not part of designing this board are left out.  | | tokens | |---|---|-| model calls (Claude Opus 5.5) | 1,458 |-| output | 892,123 |-| input (fresh) | 3,415 |-| cache reads | 583,232,019 |-| cache writes | 5,228,973 |+| model calls (Claude Opus 5.5) | 1,312 |+| output | 839,190 |+| input (fresh) | 3,123 |+| cache reads | 556,832,341 |+| cache writes | 4,936,353 | -At Claude API pricing for Opus 5.5 ($4 input, $20 output, $0.20 cache read and $8 one-hour cache write per million tokens) that is about **$176**. On a 20x subscription plan, divide by 20: about **$9**.+At Claude API pricing for Opus 5.5 ($4 input, $20 output, $0.20 cache read and $8 one-hour cache write per million tokens) that is about **$168**. On a 20x subscription plan, divide by 20: about **$8**.  ## The voice-over script  Spoken by adom-tts (the Andrew voice). Part numbers and units are written out the way they are spoken; the subtitles show the written form. -**The prompt.** It starts with one prompt: create a twelve volt to five volt, one amp buck converter, using TI's T P S five four two oh two, as an Adom molecule.+**The prompt.** It starts with one prompt, typed into Claude Code in Adom Hydrogen: create a twelve volt to five volt, one amp buck converter, using TI's T P S five four two oh two, as an Adom molecule. -**Opening.** This is a twelve volt to five volt, one amp buck converter. Claude designed it, laid it out, and documented it, start to finish, with Adom's tools. Here's how it came together.+**Opening.** From that one prompt, Claude did the rest: the circuit math, three simulators, the layout in KiCad, the analysis, the part models and the documentation, all with Adom's tools. Here's how it went.  **The circuit.** Claude worked the circuit out from the datasheet. Every value comes from its equations: a fifteen microhenry inductor, three twenty-two microfarad output capacitors, and a sixty-eight picofarad feed-forward capacitor that shapes the loop. -**Simulation.** Before any copper, the design was simulated in three engines at once, with the Adom SPICE dashboard. N G spice runs right in the container. L T spice, and TI's P spice, run on a Windows PC, driven through Adom Bridge. Start-up, both load steps, and the inductor ripple all overlay: three engines, eight measurements, all in agreement.+**Simulation.** Before any copper, the design was simulated in three engines at once, with the Adom SPICE dashboard. N G spice runs right in the container. L T spice, and TI's P spice, run on a Windows PC, their windows driven by the AI through Adom Bridge. Start-up, both load steps, and the inductor ripple all overlay: three engines, eight measurements, all in agreement.  **Placement.** Then the board. Adom AI Flow drives KiCad ten through the Adom KiCad Bridge, live. Twenty-four parts move onto a twenty-eight by twenty millimetre molecule, with the hot loop packed tight around the regulator. @@ -66,11 +68,9 @@ Spoken by adom-tts (the Andrew voice). Part numbers and units are written out th  **Part models.** Then every 3D model got the same attention. Each part number is laser-etched flat onto the part, in the part's own colours. The LED is tinted to its datasheet wavelength, with its marking on the side, so the window stays clear. And every height matches its datasheet. -**On the Adom wiki.** And every part on this board now has its model on the Adom wiki, for every Adom user: the inductor, the capacitors, the resistors and the LED, each with its etched part number, its footprint, its silkscreen and its pin names.+**On the Adom wiki.** Every part on this board now has its own page on the Adom wiki, for every Adom user: the inductor, the capacitors, the resistors and the LED, each with its 3D model, symbol and footprint. -**On the scaffold.** Finally, the molecule takes its place on a probing scaffold, wired to the control panel, ready for live measurements.--**What it cost.** What did it cost? Building the board took about nine hundred thousand output tokens, and five hundred eighty million tokens read back from the prompt cache. At Claude A P I pricing, that's about a hundred seventy-six dollars. On a twenty X plan, divide by twenty: about nine dollars.+**What it cost.** What did it cost? Building the board took about eight hundred forty thousand output tokens, and five hundred sixty million tokens read back from the prompt cache. At Claude A P I pricing, that's about a hundred sixty-eight dollars. On a twenty X plan, divide by twenty: about eight dollars.  **Close.** One measured run, from a prompt to a finished board. Zero design rule errors. Three simulators in agreement. And every part on it, marked and modelled. The whole story, with every clip, is on the Adom wiki.