← Kevin Bartolome
Personal project Built on my own time Running daily since Aug 2026

I automated most of my own job and kept the quality bar.

Four screens and an AI that can see the work. I stayed in the loop for the two decisions that need a human, and handed it everything else.

800+ testsautomatically maintained, daily
Qualitykept via human in the loop
128 fixedcurrent best single day
4 minfastest, broken to fixed

What changed

Give it eyes. Then take everything off the human's desk that does not need a human.

My day job is keeping a test suite of 1,600 automated tests running against a large product that ships features fast. When the product changes, tests break, and someone works out why. The AI was good at the repair and blind to everything else, so I was the courier.

Before

One broken test. Ten hand-offs.

  1. Me, reading the failure on a dashboard
  2. Me, copying the error into a chat
  3. It guesses at a cause it cannot see
  4. Me, screenshotting so it can see
  5. It writes a fix
  6. Me, pasting the fix and running it
  7. Me, waiting, then copying the next error
  8. Repeat until it passes, or the day ends

After

One broken test. Two hand-offs.

  1. It reads the failure and the video itself
  2. It opens the product and confirms what changed
  3. It writes the fix and runs it twice to prove it
  4. It lands on a board, marked ready, with the reason
  5. Me, pasting and running
  6. Me, confirming it passed

Porting it

The same three jobs get automated every time. The same one stays yours.

Whatever the work is, the AI gathers the evidence, does the work and proves it. You keep the one step that is hard to undo. Only the words change.

the AI handles it end to end stays yours, on purpose
My test suite running today
diagnose write the fix prove it twice ship it

I read two items a day instead of thirty failures, and I never open a log again.

A code review queue
open the PR first-pass review nits fixed, tests run approve

Every PR reaches you already cleaned up, with the tests green. You spend your review on the design call, not on naming and formatting.

An AI eval loop
change the prompt run the evals score and diff vs last promote

Nothing ships on vibes. A prompt cannot be promoted until the scores are recorded against that exact version, and regressions surface before you look.

A support desk
reproduce it find the cause write and prove the patch release

Tickets land already reproduced with a proven fix attached. The ones that turn out to be user error never reach an engineer at all.

A hiring pipeline
collect the work samples draft the prep notes chase the scheduling every judgement call

You walk into each conversation already briefed, and the admin trail chases itself. No screening decision is ever made for you.

My own week building next
say what I want break it into steps chase and surface it actually do it

One screen that tells me what genuinely needs me today, and hides everything that does not. Same machinery, no testing in sight.

Every row above has the human gate in a different place, because that is a choice, not a limitation. Move it earlier if the work is risky, later once you trust it. I am building the personal one next.

The part that makes it trustworthy

The AI cannot mark its own homework

An AI will tell you the work is ready, because it believes that. So "ready" here is not an opinion. It is a gate, and the evidence has to already exist.

  • Two clean runs recorded on my machine
  • One clean run on the real test machines
  • All three against the same version of the code
  • The run id written onto the card, so I can check it
PROVENotherwise the card cannot move

The part that compounds

It files its own bugs and learns from its own mistakes

The system is not finished and was never meant to be. It gets a little better every day, and most of that improvement is not mine.

A tracker that fills itself

I can file a bug or an idea with one key. The interesting half is that the AI files them too, on its own, from whatever it ran into that day: a rough edge in the tooling, a gap it noticed, a bug in my own scripts.

Every row says who raised it, so I always know which are mine and which it brought to me. I keep, reprioritise or bin them. Nothing gets built without me saying so.

Tracker
◉ TRACKER                        6 open
────────────────────────────────────────
🐛 BUGS
  👤 Newest card sorts to the bottom   high
  🤖 Demo page could leak real names   high
🔧 CHANGES
  👤 Cap every panel at four rows      med
✨ FEATURES
  🤖 Shareable demo mode for the board med
  🤖 Re-queue runs that stall silently low
  👤 Live "what am I on right now"     high
────────────────────────────────────────
🤖 raised by the AI   👤 raised by me
When something goes wrong

It writes the lesson down

If I correct it, or it repeats a mistake, the rule goes into a permanent file that same day. Not a note for later. Part of how it works from then on.

Every evening

It runs its own retro

It re-reads the day, finds what it got wrong, and writes down anything the live capture missed. It also scores its own past predictions to see where it was overconfident.

Then it locks the door

It adds a test against itself

A lesson becomes an automated check, and the check has to fail on purpose first. If it cannot catch a planted mistake, it is not trusted.

The practical effect is that the same problem does not come back, and everything it learns about the product is written down where the next investigation will find it. The bigger the suite gets, the more that matters.

The four screens

Each one answers exactly one question

They sit open on a second monitor. The AI writes to them as it works. Real panels, names changed.

What needs me right now?

Headquarters

The only screen I have to look at. Everything else exists to keep this list short. On a good day it holds two items.

Headquarters
◉ HQ                              9:42 PM
────────────────────────────────────────
👉 YOUR MOVE (2)
  1 Paste 3 files, then run acc-07
  2 Re-run these 9. No fix needed
▶ RUNNING (1)
  bil-19   local run   3m 21s elapsed
✉ MESSAGES (0)
  nothing waiting
📌 TRACKER  3 bugs · 2 changes · 5 ideas

Where does every broken test stand?

The Mission Board

One card per test, ordered by how close it is to done. A card that has not moved in three hours turns red on its own.

Mission Board
◉ MISSION BOARD                  31 in this batch
────────────────────────────────────────
♻ PASSED ON RE-RUN just try it again
   chk-04        23m ago
🛰 PROVEN ON THE REAL MACHINES
  🛰 acc-07        41m ago
🔧 FIX READY waiting on you
  🔧 onb-05        31m ago
     why: the Continue button moved
🟡 STILL INVESTIGATING
  🟡 adm-03        1h 14m ago

What is running, and did it pass?

Flow Ops

Several tests run at once, in their own lanes. Before, they went one at a time, and most of the day was waiting.

Flow Ops
◉ FLOW OPS                       4 lanes open
────────────────────────────────────────
▶ RUNNING (2)
  bil-19    3m 21s  ████████░░░░
  srch-02   1m 04s  ███░░░░░░░░░
🏁 RESULTS newest first
   acc-07    passed   4m 02s
   log-06    passed   3m 48s
   adm-03    failed   2m 11s

What actually got done today?

The Workshop

The day's record, and arrow keys back through previous days. Every number on this page came off this screen.

Workshop
◉ WORKSHOP              Tuesday, Sep 1
────────────────────────────────────────
🏆 37 tests fixed and signed off
⏱ fastest today: 6 minutes
✅ WINS
  9:14p  crt-14 signed off      12m
  8:52p  prf-05 signed off      28m
  8:30p  chk-02 signed off      6m
  
🐛 1 sent back as a product bug

One real day

September 3rd, start to finish

Not a demonstration. One ordinary day, taken off the Workshop screen.

800+ tests investigated test suite comes in at 9am, green light within hours
32 at a timetests run in parallel lanes, not one by one
under a minutemy hands-on time per test
Me One link: the immediate results. Hundreds of tests failed. That is the whole hand-off.
AI Groups all by what actually went wrong instead of reading them one at a time.
AI Half were never broken. They failed because hundreds of tests hit the product at once. No fix needed, just a retry done for you automatically.
Me Retry those. Half pass. Not a line of code written for any of them.
AI Works the remainder in parallel. Opens the product, confirms what changed, writes the fix, runs it twice to prove it, lands it on the board with a one line reason.
Me Paste, run, confirm. Two keystrokes and a look, per test.
AI Automatically starts an end of day retro, which triggers self reflection (fixing mistakes and making sure they never happen again). The system is continuously improving and learning the product automatically. This makes maintaining the suite better over time, regardless of how big the test suite becomes.