loteck.ai
last run 28 jul 2026 · 01:58 utc
fig. 01 — operating principle

Simplify.
Standardize.
Automate.

Don't pay an LLM to do an if-statement.

Most of what looks like an AI problem is a process problem wearing a costume. The machinery here is deterministic by default — plain code, plain tests, plain logs — and a model only gets called at the point where judgment is genuinely required. That boundary is the whole design.

IF THEN TRIGGER AI deterministic by default · model on demand
fig. 02 — register
Systems built and maintained here.
SystemWhat it doesEvidenceState
flagstat.us Knows when U.S. flags fly at half-staff, and why. Official proclamations parsed, cross-checked against a second source, and served over an API. Model classification sits behind deterministic gates, because the failure mode is telling a state its governor ordered something he didn't. 940 tests
rev 00120
production
loteck-evals Scores a model against versioned case suites so model choice is a measurement, not a preference. Four scorers, and the LLM judge is the last resort: eleven of the fourteen cases are graded by executing the generated code or validating its schema. Open source. 4 scorers
14 cases
public
mission harness Runs a queue of jobs overnight against local models. A job only counts as done when it turns a failing test green, and the test is sealed before work starts — a pass earned by editing the test is a trust violation, not a fix. Anything it can't finish inside its budget comes back to me with its working shown. 52 missions
since 29 jun
running
fig. 03 — run log
26
verified
15
proposed
12
escalated
1
already settled
Most recent entries from the mission ledger.
DateJobOutcomeResult
28 jul make app/tests/test_poller_pa_boilerplate.py pass by editing ONLY app/services/poller.py, keeping… qwen3-coder-next proposed
28 jul make app/tests/test_end_date_review_persist.py pass by wiring the end_date_review signal end-to-end. (1)… qwen3-coder-next proposed
27 jul enrol every installed model for evaluation, not just the hand-listed ones qwen3-coder-next
2 attempts
verified
22 jul correct honoree boundary parsing in proclamation text qwen3-coder-next
1 attempt
verified
22 jul internal project — counted in the tallies above, not named here qwen3-coder-next
5 attempts
proposed

Twelve runs stopped short and handed the job back — every one of them because it hit its own time or attempt budget, which is the cap doing exactly what it's for. Each came back with its receipt attached, so I could see what it had tried. Every job behind those escalations has since shipped — several on a second pass with a longer leash. The count stays on this sheet on purpose: a machine that never hands anything back isn't checking its work, it's just asserting.