KIDO Events

Development notes

Measuring AI Accuracy

Prompt counts show how often a person intervened. They do not, by themselves, show whether the AI was right or wrong.

Posted June 9, 2026Updated July 17, 20268 min readData through July 17

Blog Build Report

The revised conclusion

There is no honest single-number “AI accuracy” score in this project yet.

The project has strong operational evidence: prompt history, source runs, ingest reports, record failures, duplicate checks, approvals, and verification notes. It does not have a labeled gold-standard dataset that can turn all of that into one accuracy percentage.

671 logged prompts are a history of work and intervention—not 671 AI mistakes.

What changed

The first measurement mixed unlike things

The original version of this post compared prompt volume with ingest output over the project’s first days. That was useful as an early pressure gauge. It was not an accuracy measure.

A prompt can request a new feature, correct listing data, tune a scraper, change the interface, document a reusable rule, verify completed work, or release code. Counting every one of those against published records made ordinary product development look like AI correction work.

The corrected efficiency measure now counts a prompt once only when it is tagged data_fix or source_ingest. Even that number measures human steering, not record-level error.

One prompt can repair hundreds of records. One record can require several prompts. Prompt-to-record ratios describe operational effort, not the probability that a record is correct.

Current snapshot

What the project can measure today

9,893current normalized events, camps, and programs
404sources represented in current normalized records
532recorded source runs in the current run history
97.0%successful source-run rate
506prompts tied to data changes
55.54data-change prompts per 1,000 published additions
520prompts with explicit verification recorded
25record failures captured across runs in the prompt window

Work classification

Most intervention has been data support

The prompt log now assigns each request one primary work type. Release work is separated first. Prompts that touch data_fix or source_ingest then count as data support. Remaining prompts fall into feature development, product quality, or workflow maintenance.

Primary work type

Mutually exclusive totals across 671 logged prompts.

Data support504 · 75.1%
Product quality92 · 13.7%
Feature development32 · 4.8%
Workflow & maintenance24 · 3.6%
Release & delivery19 · 2.8%

This also changes how code work should be read. Of 327 prompts that changed code, 252 supported data ingestion or repair, 39 supported product-quality fixes, and 26 supported feature development. A code_fix tag says code changed; it does not say the code contained a bug.

Definitions

Workflow tags are not accuracy categories

Source ingest

A source was scraped, normalized, rerun, or reviewed through the ingest pipeline. It is a data-support workflow.

Verification

Tests, API checks, browser checks, ingest reports, duplication reports, or other evidence were recorded. It shows checking, not correctness by itself.

Data fix

Stored or normalized listing, source, organization, venue, or review data changed.

Code fix

Application or pipeline code changed. Its purpose may be data support, feature development, quality, or release work.

Config fix

Source rules, mappings, URLs, categories, or runtime configuration changed.

QA correction

A person found that the result did not match the expected product or source evidence and directed a correction.

A better scorecard

Accuracy has to be measured at several boundaries

MeasureCurrent signalWhat it answersWhat it cannot prove
Pipeline reliability516 / 532 runsDid collection and normalization complete?A successful run can still contain a semantically wrong field.
Rule-check qualityIngest reportsAre dates, locations, links, types, ages, and required fields structurally usable?Passing rules does not prove every value matches its source.
Human steering load55.54 / 1,000How much data-focused intervention accompanied published growth?It is not a record error rate.
Verification coverage520 promptsWas explicit checking recorded with the work?The depth of each check varies.
Record-level accuracyNot yet scoredDoes each normalized field match authoritative source evidence?This requires sampled or comprehensive labeled truth and field-level comparison.

What the corrections taught us

Repeated misses should change the system

  • Stable platforms should use deterministic APIs, feeds, or paging. AI should classify new records or review exceptions, not replace reliable extraction.
  • Explicit source fields should beat inference for dates, ages, prices, schedules, links, and listing type.
  • Customer-facing fields must never contain parser caveats, uncertainty notes, or implementation commentary.
  • Publishing needs separate approval gates. A successful local ingest is not permission to publish locally or push production data.
  • When a correction repeats, it should become code, configuration, validation, or a focused test—not another reminder that must be remembered next time.

System design

AI works best inside a controlled pipeline

Source evidenceKeep the original payload and public URLs.
Deterministic extractionUse APIs, feeds, HTML rules, and stable mappings.
Bounded AIClassify or extract only the requested fields.
ValidationCheck contracts, required fields, failures, and duplicates.
Human approvalReview evidence before local publication.
Production gatePush only through a separately authorized release.

Instructions remain useful. They preserve judgment and explain edge cases. Code and tests provide enforcement. Reports preserve evidence. Approval gates control state. AI supplies language judgment where the input and output can be constrained.

The most useful accuracy question is not “How many prompts did the AI need?” It is “At each decision boundary, what evidence shows that the result is supported, valid, reviewed, and safe to publish?”

The live Data Quality Report tracks pipeline reliability, validation, field coverage, duplicate flags, and corrections over time. The next meaningful accuracy improvement would be a field-level audit sample tied back to authoritative source evidence.