TIM SCHROEDER
Home / How I build
AI-first development

How I build
with AI.

Claude Code writes the code. Everything around the code is mine: the problem, the decisions, the checks, and the call on whether it works.

The short answer

If AI writes the code, what do I do? Five things AI does not do for me:

  • Decide what is worth building, and what "done" means.
  • Choose the model, service and data rules for each job.
  • Demand the test or measurement that proves a change works.
  • Notice when something is wrong even though nothing reports an error.
  • Run it in production and answer for it.
The workflow

Ten steps, and who does each one.

This is the loop behind every project on this site. The AI does a lot of the typing. It does not own a single step on its own.

  1. Find the problem

    A real pain I or a business has, stated in one sentence.

    Me
  2. Define the outcome

    What a user can do afterwards, and how I will know it works.

    Me
  3. Research the options

    Existing tools, APIs and models, with their limits and costs.

    Me + AI
  4. Write the requirements

    Rules, edge cases, data access, what must never happen.

    Me
  5. Choose the approach

    Stack, hosting, which model does which job, what gets tested.

    Me decides · AI proposes
  6. Direct the build

    Claude Code writes the code, migrations and tests in small, reviewable pull requests.

    AI implements
  7. Review and test

    Tests, type checks, a real production build, and looking at the actual screen.

    Me + AI
  8. Investigate failures

    Read the logs and data, form a cause, then prove it with a measurement.

    Me + AI
  9. Refine

    Fix the cause, not the symptom, and add a test so it cannot come back quietly.

    Me decides · AI implements
  10. Deploy and operate

    Ship, check the live result, monitor, and keep it running.

    Me
A real example

One feature, start to finish.

PublishBench, July to August 2026. A routine model upgrade turned into a month of measured fixes. Every step below is in the git history. The quotes are from the actual commit messages.

  1. 29 Jul · Requirement

    Move to the newer model

    The goal was simple: move every AI generator to Claude Sonnet 5 and stop paying twice for the same prompt.

    9ea1b4c · "Move the default model to Sonnet 5, and stop paying twice for the same prompt"
  2. 29 Jul · Failure

    Every generator went offline

    The new model rejects two settings the old one silently ignored. For about four and a half hours, nothing generated. The fix switched every generator to a forced tool call, so the model must answer in a fixed shape.

    f058f10 · "Fix every Anthropic generator, which Sonnet 5 had taken offline"
  3. 31 Jul · Investigation

    A quieter failure underneath

    Replies now arrived, but often in the wrong shape: a list wrapped inside a string. The content was right; the encoding was wrong. Instead of guessing, I asked for a probe that measures how often it happens.

    7876f3a · "Add a probe for the rate at which the model malforms a tool argument"
  4. 31 Jul · Evaluation

    Test the obvious fixes, and reject them

    Four prompt changes looked plausible. Each was measured and each scored 0 out of 10. The one change that worked was a single sentence in the schema itself.

    2ee1a9b · "Tell the model in the schema that an array must arrive as an array"
  5. 11–14 Aug · Hardening

    Make the remaining failures harmless

    The repair step moved into its own tested module. A malformed reply now retries with its data intact, and a reply cut off at a token limit is no longer counted as a model failure.

    e86af13 · #124 · #139 "A cut-off reply is not a model that failed"
  6. 23 Aug · Final fix

    Rescue on the first attempt

    One prompt was still failing every time. The belief that rewording the query fixed it turned out to be luck: 15 of 15 runs were malformed, including the reworded control. A tolerant decoder now recovers the broken shapes.

    42c06bd · #178 "Rescue the pseudo-XML tool-argument spill that burned contentBrief jobs"

The measurement that decided it

Clean replies out of 10, before and after the one-sentence schema change. Source: commit 2ee1a9b.

PromptBeforeAfter
chapters010
summary39
replication brief39
thumbnail critique910
titles99
channel name56

Across the six main prompts: about 52% malformed before, 10% after. The control mattered: naming the property alone scored 1 of 15; adding "must be a JSON array, not a string containing one" scored 15 of 15.

From the commit message

git show 2ee1a9b · excerpt
# what was tried, and rejected
Each of the plausible prompt-side
explanations was tested and changed
nothing at all — 0/10 clean every time.

# what worked
What fixes it is one sentence in the
schema, and the control says which
part does the work.

# what it does not fix
It does not fix everything ... so the
repair layer stays.
My decisions
  • Measure the failure rate before changing anything.
  • Reject fixes that do not move the number, even plausible ones.
  • Stay on the new model rather than switch providers, because switching changes the product's writing voice and its cost model.
  • Repair broken replies for free instead of paying for retries.
  • Distrust a fix seen at 15 samples until it holds at 25.
What Claude Code did
  • Wrote the probe, replay and repair code, and their tests.
  • Ran each experiment and reported the counts.
  • Diagnosed the reply shapes it could and could not decode.
  • Wrote the commit messages that record what was tried.
RESULTOf 25 captured bad replies, 20 are now rescued on the first attempt (was 8). Live, 9 of 10 runs of a known-bad query succeeded. The 5 that still fail genuinely lack data, so retrying them is correct.
Judgement

Problems nothing reported.

The most valuable part of the job is noticing what is wrong when every log says fine. Four real examples:

Scheduled jobs that never ran

Property Station: the host registered none of three scheduled jobs, with no error anywhere. Found because the newest notification was a week old. Now one schedule, a run log, and a test that fails the build if it happens again.

Property Station →

Every signup refused

Thumbnail Bench: ads brought clicks but zero signups. Analytics showed no one ever reached the signup step, which traced to a security setting configured without its pair.

Thumbnail Bench →

A reviewer that never says no

PublishBench: a cheaper grading model looked fine on average, but it never rejected a single article, including one with a known flaw. The grader stayed on the stronger model.

PublishBench →

Audio at the wrong speed

Infinity Dictate: an independent multi-agent code review found that imported audio files were fed to the transcriber at the wrong sample rate. Fixed with 45 other findings from the same review.

Infinity Dictate →

Working rules

How I decide something works.

Rules I keep because breaking them cost me something.

  • Run the real build. Type checks and tests passing is not the same as the deploy's own build passing.
  • Look at the screen. Reading the page code is not verifying a user interface. I take a screenshot.
  • A green log line is not the outcome. Open the thing that was supposed to be produced.
  • A prompt change is a hypothesis. Measure it over several runs before calling it a fix.
  • Check the platform that serves users. Green CI does not mean the live deploy succeeded.
Toolkit

How the AI work is organised.

Claude Code

Custom skills
20+ reusable instruction sets for recurring jobs, from case-study builds to video pipelines.
Subagents
Parallel agents for research and review, each given its own files so they cannot overwrite each other.
MCP servers
Connections to email, browsers, hosting and data tools, with read-only limits where data is sensitive.

Safety rails

Pull requests + CI
Small changes, each with tests, type checks and a build before merge.
Read-only by default
Live business systems such as the real-estate MLS are only ever read, never changed.
Spending limits
Every paid AI call is costed, and products have switches to stop paid calls fast.

What I do not claim

Hand-written code
I do not write code by hand, and I do not pretend to. AI coding agents write it.
How I judge it instead
By evidence: tests, builds, measurements, independent reviews and the live result.

Let's talk about
what you need built.

Open to AI roles: full-time, contract or consulting. I build AI products, internal tools and automations with AI coding agents.