Industry & AI · Agentic engineering

Where coding agents
break, measured.

I build software entirely with AI agents, and measure where they break and need a human. Then I turn each break into a check or an automatic fix.

Industry research at AI companies · Applied AI · Data science · QuantOn the 2026–27 job market, open nowRequires U.S. visa sponsorship

Up to 10

coding lanes in parallel, each with its own subagents

3,700+

tasks live or merged to main since August 22, 2026, one person directing

18%

of 1,366 tasks were sent back by an independent AI reviewer before landing. Three in four passed after repair.

91%

of changes now land on main within 4 hours of first commit, up from 65% three weeks earlier

01 · How I work

01

Build only through agents

I set the goal, rank the work and judge the result. The agents write and ship all of the code.

02

Find where they break

Work that stalls, output that looks finished but is not, checks that block work for no reason: I log each point where a human had to step in.

03

Measure and automate

Each break becomes a metric, a check or an automatic fix, so the fleet keeps running without someone watching it.

02 · What the measurement shows

Faster, and so far no more fragile.

Over three weeks, more changes reached main within 4 hours, and rollbacks fell from 5 a week to none. The trend is thin: 7 rollbacks in 1,555 changes. I can't yet separate the effect of my checks from other things that changed in the same weeks, like model updates and the mix of tasks.

Landed within 4 hours of first commit

Share of changes merged to main, by week

0% 50% 100% 65% Oct 19–25 86% Oct 26 – Nov 1 91% Nov 2–6
Data
WeekLandingsWithin 4 h
Oct 19–2546665%
Oct 26 – Nov 159386%
Nov 2–6, partial week47091%

Rollbacks per 100 changes

Changes on main that had to be reverted, by week

0 0.5 1.0 1.07 Oct 19–25 0.34 Oct 26 – Nov 1 0 Nov 2–6
Data
WeekLandingsRolled backPer 100
Oct 19–2546651.07
Oct 26 – Nov 159320.34
Nov 2–6, partial week47000.00

A failure, caught at night

Nov 1, 2026. Times in ET.

  1. A change lands on main that makes the phone and the server write a one-round score differently ("1 round" vs "1 rounds").

  2. The full test run on main fails. A watcher agent traces the failure to that change in 14 seconds.

  3. The revert lands on main. No human involved, and saved scores were never affected.

Weeks run Monday to Sunday, from the first full week after the landing queue started on Oct 18, 2026. The first week includes a backlog of older work. Rollback counts are small: 7 of 1,555 landings in total.

03 · Case studies

Case study 1 · The test bed

An AI-driven training app

An athlete-facing, multi-user training app for iOS and web: AI workout planning, timed execution and completion, equipment and injury constraints, and a persistent training history. Native iOS and web clients on a Rust backend, both shipped by agents through the same task board.

  • Built byOne person directing parallel AI coding agents
  • Where it breaksAI workouts that look right but miss a detail, and features that look present but do not work
  • How it is measuredA rubric-based AI judge scores saved cases, calibrated by hand, and AI failures are counted over time. A separate referee agent scores generated workouts against established coaching rules for workout design, so the generator never grades itself.
Training app: today's workout with warm-up, strength and for-time blocks Training app: an AMRAP timer running, with the round's movements
Case study 2 · The method

Running a fleet of coding agents

A scheduler assigns ranked backlog work to parallel coding lanes; independent agents review changes, a serialized landing queue integrates them, and separate nightly automation attempts production releases. A phone dashboard shows each lane, work that is stuck, and whether the task board matches what actually shipped.

  • Where it breaksWork left behind between stages, and stalls that need a human nudge
  • What I builtStuck work shown as one clear action with a one-tap fix, and sync checks that compare the board against what actually merged instead of trusting agent reports
  • How it is measuredTime from first commit to merged, how often reviewers send work back, and how often a landed change has to be rolled back

04 · The stack

Build

Claude Code in parallel lanes

Parallel coding lanes run on an always-on workstation, with Claude Code as the implementer in each lane. Independent agents review every change before a single landing queue merges it to main.

Specialize

A fleet of specialist agents

Role-specific assistants instead of one generic chat: product build, fleet operations, reliability and research. Each has one job and a written list of what it must not do; builder, designer and judge are separate agents.

Research & writing

Long research sessions

Long-running research and writing sessions with handoffs between agents, kept apart from the coding lanes and the product release path.

Machines

Always on, no babysitting

An NVIDIA DGX Spark for heavy agent work, a Mac mini for iOS builds and local gates, and a laptop for direction. Work keeps running without anyone at either machine.

05 · Research that carries over

Credit risk and consumer behavior, with causal inference

I study how people borrow and how lenders decide, on Finnish loan-marketplace data linked to credit-registry records, including 730,000 applications in my NBER paper. My job market paper finds applicants who would default above the lender's break-even rate, yet look like everyone else on credit score, income and debt-to-income. The same methods answer product questions: what a change really causes, and for whom.

See the research →

06 · Experience

2021 – 2027

PhD in Finance, Hanken · Visiting Scholar, UNC

Consumer credit research on register data, with causal inference and machine learning.

2020 – 2021

Data Scientist, Silicon Labs

Forecasting and reporting on SQL-backed transactional data with AWS ML tools and Tableau, at a NASDAQ-listed semiconductor company.

2010 – 2020

Founder and co-founder, several startups

Built and divested two startups. Raised €3M+ from angel and VC investors.

2011 – 2013

Senior Sales Manager, Estlander & Partners

One of Scandinavia's early algorithm-based hedge funds.

07 · Skills

Data and modeling

Causal inferenceEconometricsPanel dataPredictionMachine learning

Engineering

PythonSQLGitData pipelinesRelease operations

Agentic engineering

Parallel coding agentsAI output evaluationFailure metricsHuman checkpoints

On the 2026–27 job market, open now.
Industry research, applied AI, data science, quant.

Download resume