All ideasMore in Work

For six weeks an AI operated Cadence Virtuoso for him and designed three analog circuit blocks

Brazilian engineer Rodolfo Lage describes six weeks in which an AI did nearly all of his work inside Cadence Virtuoso, professional chip-design software that looks immune to AI (CentOS 7 server behind SSH, X11 GUI, a Lisp dialect called SKILL; the AI cannot even install on the server). Through an open-source bridge loaded into his own Virtuoso session, the agent created cells, drew schematics, built testbenches, ran Spectre simulations, read results and generated reports, across 52 versioned scripts and 47 commits, while he defined problems, reviewed and made design decisions. Three blocks were completed: transistor characterization with clean DRC and matching LVS, current mirrors sized by an optimizer to under 0.005% current error, and a common-source amplifier reaching 26.8 V/V gain and 109 MHz gain-bandwidth. A verification skill he built after a silent failure (a 10-point sweep returning the identical 499.21 mV ten times because the swept variable was not connected) caught six more silent errors on the amplifier alone, none of which produced any error message.

How it works

  1. Open an SSH master session and start Virtuoso
  2. Load the bridge daemon with one line in the console
  3. Agent works in the same live instance via SKILL commands returning JSON
  4. Per circuit: generate schematic/symbol/testbench script, run checks and screenshot
  5. Simulate DC/AC/transient via OCEAN on Spectre
  6. Sweep and compare against theory
  7. Record results in Markdown, figures, PDF report and a git commit
  8. A verification skill cross-checks every measurement before it is reported

Why it’s worth knowing

An agent operated 1990s-style EDA software it could not even be installed on, through a one-line bridge, and its most valuable skill became distrusting the tool's own success messages.

Where it’s from

Summarized from a public post on rodolfolage.substack.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.