I asked the AI coding agent I work with every day to describe how it pictures
me, as a prompt for an image model. It refused to invent a face, so the figure
is seen from behind. Everything else in the prompt is real work we did together.
I pasted the prompt, unchanged, into ChatGPT and Gemini.
Prompt
A cinematic wide-angle digital illustration of an image-algorithms engineer andtechnical lead working late at night, seen from behind at a sleek desk, so theface is not visible. The person wears a dark hoodie and over-ear headphones witha violet accent, rim-lit by cyan and violet neon light. Three glass-likemonitors curve around the desk. Left monitor: a dark live monitoring dashboardwith four glowing line charts in cyan, violet, green and amber, a GPUutilization bar near 100%. Center monitor: a before/after face-restorationcomparison, the left half blurry with ringing artifacts, the right half sharpand clean with a green "aligned" checkmark. Right monitor: a black terminalshowing a CI pipeline where build, benchmark and verify stages are green and adeploy step is running. On the wall, a translucent glass whiteboard with ahand-drawn architecture sketch: three boxes labeled proxy, framework and engineconnected by arrows, and a dashed CI flow "tag → build → verify → deploy test".A yellow sticky note reads "Heading home. Keep working after verify. Fix yourown mistakes. I'll check in the morning." To the right, a small server rack withfive glowing units: several Linux servers with blinking green status LEDs and aMac mini, one unit marked "2× GPU". On the desk: a mechanical keyboard with acyan underglow, an iPhone showing a long stitched screenshot, a steaming coffeemug, and a compact camera. Futuristic glassmorphism style, dark navy backgroundwith a subtle cyan grid, soft volumetric glow, neon accents in cyan (#22d3ee)and violet (#7c3aed), clean vector-like shading, high detail, 16:9, 4k.
ChatGPT. Photoreal. Text is nearly perfect. Added a skyline, slogans, textbooks and dashboard metrics nobody asked for.Gemini. Flat vector. Nothing added, nothing missing. Dashboard labels came out garbled.
ChatGPT
Gemini
Style
Photoreal
Flat illustration
Text
Exact
Mostly exact, small labels garbled
Extras
Many
None
ChatGPT treats a prompt as a brief to improve on. Gemini builds what you
specified.
What is in the prompt
Almost none of it is decoration. The agent picked each detail from something we
had actually done.
Seen from behind. It did not know my face and would not invent one.
Three monitors. A live monitoring dashboard, a face-restoration
before/after, a CI terminal. The three things we spent the most time on.
“aligned” checkmark. A real bug: restored faces came back misaligned.
We fixed it together.
proxy → framework → engine. The actual shape of our inference service,
with the internal names removed.
tag → build → verify → deploy test. Our release flow. A git tag kicks it
off; nothing goes to production without a manual step.
The sticky note. A message I left the agent one evening, word for word.
It kept working overnight.
“2× GPU”. I keep asking it to use both cards. It remembered.
Long stitched screenshot. I send it phone screenshots stitched together
so it can read a whole chat at once.
Compact camera. From the expo photos elsewhere on this site.
Cyan and violet, glass, grid. This site’s default theme.
Hoodie and headphones. Invented. The only guess in the whole prompt.
Neither picture is what I look like. Both are what my work looks like from
inside an AI agent.