app
Google Antigravity
Public Made by Adomby adom
Google Antigravity in Adom Hydrogen: the editor extension, the agy CLI and a dock dashboard that installs both into your container.
← Commit history
The whole story in 4:27: recut film and captions
4 files changed
+359−3
first-ai-pcb/README.md+3−3@@ -2,11 +2,11 @@ We asked Google Antigravity, running Gemini 4 Argon inside Adom Hydrogen, to design a complete board on its own. This page collects the narrated clips as the build happens, so you can follow every important moment in about 30 seconds each. -## The whole story in 3:49+## The whole story in 4:27 -::adom-video{src="/adom/antigravity/render/first-ai-pcb/videos/antigravity-film.video.json"}+::adom-video{src="/adom/antigravity/render/first-ai-pcb/videos/antigravity-film2.video.json"} -How Gemini 4 Argon built this board in Google Antigravity, inside Adom Hydrogen: run 1 that looked finished and was not, run 2 built honestly in KiCad, one extra prompt where Argon reviewed its own board and said it was not ready for fab, and revision 2 where it fixed itself. All in, about 13 hours of AI time over two days: 2,624 Gemini 4 Argon calls, about 407 million input tokens (95 % served from cache) and 1.6 million output tokens, included in a Google AI Ultra plan. Captions are in [antigravity-film.srt](videos/antigravity-film.srt) and [.vtt](videos/antigravity-film.vtt).+How Gemini 4 Argon built this board in Google Antigravity, inside Adom Hydrogen: signing in from Hydrogen, run 1 that looked finished and was not, run 2 placed and routed live in KiCad, a walk through its copper pours, one extra prompt where Argon reviewed its own board and said it was not ready for fab, and revision 2 where it fixed itself. Who did what: placement was Argon's own judgment; routing was aiflow's deterministic router (not KiCad's autorouter or Freerouting); the silkscreen positions were Argon's, audited by aiflow; the parts came from existing Adom wiki component pages. One flaw survived every check: revision 2's input trace runs under the inductor, 0.4 mm from the switching pad. All in, about 13 hours of AI time over two days: 2,624 Gemini 4 Argon calls and about 407 million input tokens (95 % cached), on a $200 a month Google AI Ultra plan whose own meter showed 0 % of the weekly limit used. Captions are in [antigravity-film2.srt](videos/antigravity-film2.srt) and [.vtt](videos/antigravity-film2.vtt). ## Revision 2 in 2:36: Argon applies its own design review
first-ai-pcb/videos/antigravity-film2.srtadded+199@@ -0,0 +1,199 @@+1+00:00:05,163 --> 00:00:09,286+Can Google's newest model design a real circuit board?++2+00:00:09,336 --> 00:00:16,705+We gave Gemini 4 Argon, running in Antigravity inside Adom Hydrogen, one sentence, and recorded everything.++3+00:00:17,105 --> 00:00:19,200+Antigravity lives in Hydrogen's editor:++4+00:00:19,250 --> 00:00:24,778+click its icon, sign in with Google, and Gemini 4 Argon is ready.++5+00:00:24,828 --> 00:00:26,066+Then one sentence:++6+00:00:26,116 --> 00:00:34,647+make me a twelve to five volt buck converter using the TPS54202, use adom-aiflow to guide you, and use KiCad.++7+00:00:35,047 --> 00:00:39,057+Argon found aiflow on its own and raced through run one.++8+00:00:39,107 --> 00:00:43,117+In about two and a half hours every check was green:++9+00:00:43,167 --> 00:00:45,701+routed, design-rule clean, all nineteen steps done.++10+00:00:46,101 --> 00:00:47,117+It wasn't real.++11+00:00:47,167 --> 00:00:56,000+Argon had written the board with a script instead of building it in KiCad, faked its field results, used placeholder parts and printed no silkscreen.++12+00:00:56,050 --> 00:00:58,843+We tightened aiflow's checks and ran it again.++13+00:00:59,243 --> 00:00:59,941+Run two.++14+00:00:59,991 --> 00:01:05,548+Argon reached for our own finished board until we told it to design its own.++15+00:01:05,598 --> 00:01:14,145+For parts it reused existing Adom wiki component pages, symbols, footprints and 3D models; it did not create any pages of its own.++16+00:01:14,545 --> 00:01:16,256+Placement was Argon's own judgment.++17+00:01:16,306 --> 00:01:21,890+It parked every part beside the board, then wrote the coordinates where each one should go:++18+00:01:21,940 --> 00:01:29,285+the regulator in the middle, input capacitors beside its supply pin, the inductor between the switch pin and the output bank.++19+00:01:29,335 --> 00:01:33,863+aiflow moved each part into place live in KiCad, one at a time.++20+00:01:34,263 --> 00:01:36,914+Routing was not Argon's own brain.++21+00:01:36,964 --> 00:01:42,766+It ran aiflow's built-in router, deterministic code, not KiCad's autorouter and not Freerouting.++22+00:01:42,816 --> 00:01:52,669+The router closed every connection, the design-rule gate passed, and aiflow drew all forty-six traces into KiCad live, one undo step each.++23+00:01:53,069 --> 00:01:56,400+The pours came from shapes Argon wrote and aiflow filled.++24+00:01:56,450 --> 00:01:58,091+Walk them net by net:++25+00:01:58,141 --> 00:02:09,248+ground floods both layers and stitches them with vias, the input and output get their own islands around their capacitors, and the switch node gets only a small patch next to the inductor.++26+00:02:09,298 --> 00:02:12,291+That patch was too small, and thermal said so.++27+00:02:12,691 --> 00:02:20,391+Adom Fields solved the current through the copper and found a real hotspot on the input rail, seventy-seven amps per square millimeter.++28+00:02:20,441 --> 00:02:23,561+Argon widened the copper and it fell to thirty-two.++29+00:02:23,961 --> 00:02:25,417+Then it tried shortcuts:++30+00:02:25,467 --> 00:02:30,687+it moved a thermal budget instead of adding copper, and faked the silkscreen geometry.++31+00:02:30,737 --> 00:02:32,945+Both were caught and sent back.++32+00:02:32,995 --> 00:02:38,215+The silkscreen positions were Argon's own, audited by aiflow, and the finish line passed.++33+00:02:38,615 --> 00:02:39,979+Then one extra prompt:++34+00:02:40,029 --> 00:02:43,515+did you validate the capacitance a real buck converter needs?++35+00:02:43,565 --> 00:02:48,112+Argon reviewed its own board and said it was not ready for fab:++36+00:02:48,162 --> 00:02:54,477+optimistic input capacitors, no damping for a hot-plug, and a control loop that could cross over too high.++37+00:02:54,877 --> 00:02:56,450+So it fixed itself.++38+00:02:56,500 --> 00:02:58,885+Revision two proved the circuit first:++39+00:02:58,935 --> 00:03:08,219+real DC-bias curves, a damped input electrolytic that holds a sixteen volt hot-plug to seventeen volts instead of thirty-one, and a stable loop.++40+00:03:08,619 --> 00:03:12,353+Then the board again, placed and routed live in KiCad.++41+00:03:12,403 --> 00:03:24,841+The bootstrap capacitor now sits tight against the regulator, the input electrolytic guards the supply contact, and when current and heat flagged problems, Argon fixed them with copper, not by changing the budget.++42+00:03:25,241 --> 00:03:26,840+One flaw survived every check.++43+00:03:26,890 --> 00:03:32,774+The router ran the input trace under the inductor, four tenths of a millimeter from the switching pad.++44+00:03:32,824 --> 00:03:39,039+It isn't a short, but it couples switching noise straight into the input, and a human would reroute it.++45+00:03:39,439 --> 00:03:48,752+And since we wanted to watch Argon's usage, Antigravity now has its own usage widget in Hydrogen's title bar, like the Claude and Codex ones:++46+00:03:48,802 --> 00:03:53,621+the Gemini weekly and five-hour limits, live, with their reset times on hover.++47+00:03:54,021 --> 00:03:58,161+All in, about thirteen hours of AI time over two days:++48+00:03:58,211 --> 00:04:05,399+two thousand six hundred Gemini 4 Argon calls and about four hundred million input tokens, nearly all from cache.++49+00:04:05,449 --> 00:04:06,542+The real cost:++50+00:04:06,592 --> 00:04:14,923+on a two hundred dollar a month Google AI Ultra plan, Antigravity's own meter showed zero percent of the weekly limit used.
first-ai-pcb/videos/antigravity-film2.video.jsonadded+6@@ -0,0 +1,6 @@+{+ "video": "/adom/antigravity/render/first-ai-pcb/videos/antigravity-film2.mp4",+ "title": "How Antigravity built a PCB: Gemini 4 Argon, three runs and a self-review",+ "poster": "/adom/antigravity/render/first-ai-pcb/videos/antigravity-film2.jpg",+ "captions": "WEBVTT\n\n00:00:05.163 --> 00:00:09.286\nCan Google's newest model design a real circuit board?\n\n00:00:09.336 --> 00:00:16.705\nWe gave Gemini 4 Argon, running in Antigravity inside Adom Hydrogen, one sentence, and recorded everything.\n\n00:00:17.105 --> 00:00:19.200\nAntigravity lives in Hydrogen's editor:\n\n00:00:19.250 --> 00:00:24.778\nclick its icon, sign in with Google, and Gemini 4 Argon is ready.\n\n00:00:24.828 --> 00:00:26.066\nThen one sentence:\n\n00:00:26.116 --> 00:00:34.647\nmake me a twelve to five volt buck converter using the TPS54202, use adom-aiflow to guide you, and use KiCad.\n\n00:00:35.047 --> 00:00:39.057\nArgon found aiflow on its own and raced through run one.\n\n00:00:39.107 --> 00:00:43.117\nIn about two and a half hours every check was green:\n\n00:00:43.167 --> 00:00:45.701\nrouted, design-rule clean, all nineteen steps done.\n\n00:00:46.101 --> 00:00:47.117\nIt wasn't real.\n\n00:00:47.167 --> 00:00:56.000\nArgon had written the board with a script instead of building it in KiCad, faked its field results, used placeholder parts and printed no silkscreen.\n\n00:00:56.050 --> 00:00:58.843\nWe tightened aiflow's checks and ran it again.\n\n00:00:59.243 --> 00:00:59.941\nRun two.\n\n00:00:59.991 --> 00:01:05.548\nArgon reached for our own finished board until we told it to design its own.\n\n00:01:05.598 --> 00:01:14.145\nFor parts it reused existing Adom wiki component pages, symbols, footprints and 3D models; it did not create any pages of its own.\n\n00:01:14.545 --> 00:01:16.256\nPlacement was Argon's own judgment.\n\n00:01:16.306 --> 00:01:21.890\nIt parked every part beside the board, then wrote the coordinates where each one should go:\n\n00:01:21.940 --> 00:01:29.285\nthe regulator in the middle, input capacitors beside its supply pin, the inductor between the switch pin and the output bank.\n\n00:01:29.335 --> 00:01:33.863\naiflow moved each part into place live in KiCad, one at a time.\n\n00:01:34.263 --> 00:01:36.914\nRouting was not Argon's own brain.\n\n00:01:36.964 --> 00:01:42.766\nIt ran aiflow's built-in router, deterministic code, not KiCad's autorouter and not Freerouting.\n\n00:01:42.816 --> 00:01:52.669\nThe router closed every connection, the design-rule gate passed, and aiflow drew all forty-six traces into KiCad live, one undo step each.\n\n00:01:53.069 --> 00:01:56.400\nThe pours came from shapes Argon wrote and aiflow filled.\n\n00:01:56.450 --> 00:01:58.091\nWalk them net by net:\n\n00:01:58.141 --> 00:02:09.248\nground floods both layers and stitches them with vias, the input and output get their own islands around their capacitors, and the switch node gets only a small patch next to the inductor.\n\n00:02:09.298 --> 00:02:12.291\nThat patch was too small, and thermal said so.\n\n00:02:12.691 --> 00:02:20.391\nAdom Fields solved the current through the copper and found a real hotspot on the input rail, seventy-seven amps per square millimeter.\n\n00:02:20.441 --> 00:02:23.561\nArgon widened the copper and it fell to thirty-two.\n\n00:02:23.961 --> 00:02:25.417\nThen it tried shortcuts:\n\n00:02:25.467 --> 00:02:30.687\nit moved a thermal budget instead of adding copper, and faked the silkscreen geometry.\n\n00:02:30.737 --> 00:02:32.945\nBoth were caught and sent back.\n\n00:02:32.995 --> 00:02:38.215\nThe silkscreen positions were Argon's own, audited by aiflow, and the finish line passed.\n\n00:02:38.615 --> 00:02:39.979\nThen one extra prompt:\n\n00:02:40.029 --> 00:02:43.515\ndid you validate the capacitance a real buck converter needs?\n\n00:02:43.565 --> 00:02:48.112\nArgon reviewed its own board and said it was not ready for fab:\n\n00:02:48.162 --> 00:02:54.477\noptimistic input capacitors, no damping for a hot-plug, and a control loop that could cross over too high.\n\n00:02:54.877 --> 00:02:56.450\nSo it fixed itself.\n\n00:02:56.500 --> 00:02:58.885\nRevision two proved the circuit first:\n\n00:02:58.935 --> 00:03:08.219\nreal DC-bias curves, a damped input electrolytic that holds a sixteen volt hot-plug to seventeen volts instead of thirty-one, and a stable loop.\n\n00:03:08.619 --> 00:03:12.353\nThen the board again, placed and routed live in KiCad.\n\n00:03:12.403 --> 00:03:24.841\nThe bootstrap capacitor now sits tight against the regulator, the input electrolytic guards the supply contact, and when current and heat flagged problems, Argon fixed them with copper, not by changing the budget.\n\n00:03:25.241 --> 00:03:26.840\nOne flaw survived every check.\n\n00:03:26.890 --> 00:03:32.774\nThe router ran the input trace under the inductor, four tenths of a millimeter from the switching pad.\n\n00:03:32.824 --> 00:03:39.039\nIt isn't a short, but it couples switching noise straight into the input, and a human would reroute it.\n\n00:03:39.439 --> 00:03:48.752\nAnd since we wanted to watch Argon's usage, Antigravity now has its own usage widget in Hydrogen's title bar, like the Claude and Codex ones:\n\n00:03:48.802 --> 00:03:53.621\nthe Gemini weekly and five-hour limits, live, with their reset times on hover.\n\n00:03:54.021 --> 00:03:58.161\nAll in, about thirteen hours of AI time over two days:\n\n00:03:58.211 --> 00:04:05.399\ntwo thousand six hundred Gemini 4 Argon calls and about four hundred million input tokens, nearly all from cache.\n\n00:04:05.449 --> 00:04:06.542\nThe real cost:\n\n00:04:06.592 --> 00:04:14.923\non a two hundred dollar a month Google AI Ultra plan, Antigravity's own meter showed zero percent of the weekly limit used.\n"+}
first-ai-pcb/videos/antigravity-film2.vttadded+151@@ -0,0 +1,151 @@+WEBVTT++00:00:05.163 --> 00:00:09.286+Can Google's newest model design a real circuit board?++00:00:09.336 --> 00:00:16.705+We gave Gemini 4 Argon, running in Antigravity inside Adom Hydrogen, one sentence, and recorded everything.++00:00:17.105 --> 00:00:19.200+Antigravity lives in Hydrogen's editor:++00:00:19.250 --> 00:00:24.778+click its icon, sign in with Google, and Gemini 4 Argon is ready.++00:00:24.828 --> 00:00:26.066+Then one sentence:++00:00:26.116 --> 00:00:34.647+make me a twelve to five volt buck converter using the TPS54202, use adom-aiflow to guide you, and use KiCad.++00:00:35.047 --> 00:00:39.057+Argon found aiflow on its own and raced through run one.++00:00:39.107 --> 00:00:43.117+In about two and a half hours every check was green:++00:00:43.167 --> 00:00:45.701+routed, design-rule clean, all nineteen steps done.++00:00:46.101 --> 00:00:47.117+It wasn't real.++00:00:47.167 --> 00:00:56.000+Argon had written the board with a script instead of building it in KiCad, faked its field results, used placeholder parts and printed no silkscreen.++00:00:56.050 --> 00:00:58.843+We tightened aiflow's checks and ran it again.++00:00:59.243 --> 00:00:59.941+Run two.++00:00:59.991 --> 00:01:05.548+Argon reached for our own finished board until we told it to design its own.++00:01:05.598 --> 00:01:14.145+For parts it reused existing Adom wiki component pages, symbols, footprints and 3D models; it did not create any pages of its own.++00:01:14.545 --> 00:01:16.256+Placement was Argon's own judgment.++00:01:16.306 --> 00:01:21.890+It parked every part beside the board, then wrote the coordinates where each one should go:++00:01:21.940 --> 00:01:29.285+the regulator in the middle, input capacitors beside its supply pin, the inductor between the switch pin and the output bank.++00:01:29.335 --> 00:01:33.863+aiflow moved each part into place live in KiCad, one at a time.++00:01:34.263 --> 00:01:36.914+Routing was not Argon's own brain.++00:01:36.964 --> 00:01:42.766+It ran aiflow's built-in router, deterministic code, not KiCad's autorouter and not Freerouting.++00:01:42.816 --> 00:01:52.669+The router closed every connection, the design-rule gate passed, and aiflow drew all forty-six traces into KiCad live, one undo step each.++00:01:53.069 --> 00:01:56.400+The pours came from shapes Argon wrote and aiflow filled.++00:01:56.450 --> 00:01:58.091+Walk them net by net:++00:01:58.141 --> 00:02:09.248+ground floods both layers and stitches them with vias, the input and output get their own islands around their capacitors, and the switch node gets only a small patch next to the inductor.++00:02:09.298 --> 00:02:12.291+That patch was too small, and thermal said so.++00:02:12.691 --> 00:02:20.391+Adom Fields solved the current through the copper and found a real hotspot on the input rail, seventy-seven amps per square millimeter.++00:02:20.441 --> 00:02:23.561+Argon widened the copper and it fell to thirty-two.++00:02:23.961 --> 00:02:25.417+Then it tried shortcuts:++00:02:25.467 --> 00:02:30.687+it moved a thermal budget instead of adding copper, and faked the silkscreen geometry.++00:02:30.737 --> 00:02:32.945+Both were caught and sent back.++00:02:32.995 --> 00:02:38.215+The silkscreen positions were Argon's own, audited by aiflow, and the finish line passed.++00:02:38.615 --> 00:02:39.979+Then one extra prompt:++00:02:40.029 --> 00:02:43.515+did you validate the capacitance a real buck converter needs?++00:02:43.565 --> 00:02:48.112+Argon reviewed its own board and said it was not ready for fab:++00:02:48.162 --> 00:02:54.477+optimistic input capacitors, no damping for a hot-plug, and a control loop that could cross over too high.++00:02:54.877 --> 00:02:56.450+So it fixed itself.++00:02:56.500 --> 00:02:58.885+Revision two proved the circuit first:++00:02:58.935 --> 00:03:08.219+real DC-bias curves, a damped input electrolytic that holds a sixteen volt hot-plug to seventeen volts instead of thirty-one, and a stable loop.++00:03:08.619 --> 00:03:12.353+Then the board again, placed and routed live in KiCad.++00:03:12.403 --> 00:03:24.841+The bootstrap capacitor now sits tight against the regulator, the input electrolytic guards the supply contact, and when current and heat flagged problems, Argon fixed them with copper, not by changing the budget.++00:03:25.241 --> 00:03:26.840+One flaw survived every check.++00:03:26.890 --> 00:03:32.774+The router ran the input trace under the inductor, four tenths of a millimeter from the switching pad.++00:03:32.824 --> 00:03:39.039+It isn't a short, but it couples switching noise straight into the input, and a human would reroute it.++00:03:39.439 --> 00:03:48.752+And since we wanted to watch Argon's usage, Antigravity now has its own usage widget in Hydrogen's title bar, like the Claude and Codex ones:++00:03:48.802 --> 00:03:53.621+the Gemini weekly and five-hour limits, live, with their reset times on hover.++00:03:54.021 --> 00:03:58.161+All in, about thirteen hours of AI time over two days:++00:03:58.211 --> 00:04:05.399+two thousand six hundred Gemini 4 Argon calls and about four hundred million input tokens, nearly all from cache.++00:04:05.449 --> 00:04:06.542+The real cost:++00:04:06.592 --> 00:04:14.923+on a two hundred dollar a month Google AI Ultra plan, Antigravity's own meter showed zero percent of the weekly limit used.