On a 4-layer board, 27 pads got a fan-out via drilled into a locked via that was already there, with KiCad hole-to-hole check at 0.000 mm on 12 of them, even though every one of those pads was already joined to its plane. The fan-out step only counted other pads as a way to the plane, not the net existing locked wiring.
Recurring agent failure issue in WeaveEngine (c28ba)
What engineers report
A recurring agent failure problem in WeaveEngine (c28ba) that mostly hits the electrical engineer.
Failure pattern: validation / failure
Analyst note
From the Grok pain-radar digests, Nov 8-9 2026 (Nov 8 8:41 AM ET through Nov 9 6:41 AM ET digests plus the Haitch editions). Verified live 2026-11-09: issue/PR read; title and state confirmed.
What it costs a team
Modeled annual cost
$30,000
For a team of 5
Prototype delay
3 days
Modeled schedule slip per occurrence
Time lost
240 min
Per engineer per month, about 1 incidents
How the cost is modeled
240 min/month × 5 engineers × 12 months = 240 hours × $125/hour = $30,000
A modeled estimate with medium confidence. Swap in your own team size and loaded rate to size it for your team.
Engineering tools that address it
No engineering tool profile lists this error yet. Browse tools that connect to WeaveEngine (c28ba).
Evidence
More recurring errors in WeaveEngine (c28ba)
- The DSN reader only knew the keepout spelling, so vias landed in no-via areas on a 4-layer board because KiCad also writes via_keepout and wire_keepout.ECAD · impact 74
- The natural command for a 4-layer board dropped inner layers and hid the planes: pours went from +3V3, +5V and GND on inner layers plus GND outer to the two outer GND pours only, and vias still went through inner layers whose locked copper had been thrown away. Same contributor as PR #3, each time the tool read only part of the board and routed confidently into the rest.ECAD · impact 74
Sourced from public community reports. Costs and delays are modeled estimates, not measurements. Know a better source or a fix? Tell us at hello@productflo.io.