> ## Documentation Index
> Fetch the complete documentation index at: https://cofounder.appeeky.com/llms.txt
> Use this file to discover all available pages before exploring further.

# A/B Test Memory

> Detects metadata changes you ship, automatically schedules a 14-day follow-up, and measures impressions / conversion / downloads before vs after.

When you change your app's metadata (subtitle, keywords, screenshots), the hardest part isn't shipping — it's remembering to measure whether it actually worked. A/B Test Memory does that for you.

## How it works

Each run:

1. Reads your current metadata from `user_apps` (web Supabase mirror of ASC).
2. Computes a **stable fingerprint** over title + subtitle + keywords + description + promotional text + what's new.
3. Compares against the previous snapshot in `cofounder_metadata_snapshots`.
4. If the fingerprint changed → records the diff and schedules a 14-day follow-up.
5. When the follow-up window has elapsed → measures impressions / conversion / downloads in the 14 days before vs after.

## What you see (fresh change)

```
## 🧪 Metadata Change Detected (3d ago, v3.2.1)
  • subtitle: "Take amazing screenshots" → "AI-powered screenshot stitching"
  • keywords: "screenshots,photos,export" → "screenshots,stitching,ai,photos"

(Scheduled 14-day follow-up to measure impact.)
```

## What you see (after 14 days)

```
## 🧪 Metadata Change Detected (14d ago, v3.2.1)
  • subtitle: "Take amazing screenshots" → "AI-powered screenshot stitching"
  • keywords: "screenshots,photos,export" → "screenshots,stitching,ai,photos"

Measured impact (14d window):
  Impressions/day: 547 → 891
  Conversion:      0.6% → 1.2%
  Downloads/day:   3 → 11
```

## In the structured report

The `abTestNotes` array gets one entry per detected change:

```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
{
  "changeDate": "2026-04-19",
  "field": "subtitle, keywords",
  "observedImpact": "Impressions +63%, conversion 0.6→1.2%, downloads 3→11/day.",
  "conclusion": "worked"
}
```

`conclusion` is one of: `worked` / `neutral` / `regressed` / `too_early`.

## Why this matters

The agent now reasons about **causality**:

* "Last time we shipped a subtitle change, conversion went 0.6 → 1.2%. This new draft might do similar."
* "Two months ago we tried 'AI' in the subtitle and it regressed downloads. Don't propose it again."

This is the foundation of the memory loop — without it, the agent would be amnesiac and re-suggest things that already failed.

## Edge cases

* **Multiple changes in a window** — only the most recent change is treated as the "experiment". Earlier ones are still recorded but the impact attribution fuzzes.
* **External factors** — the agent acknowledges seasonality / category shifts in its prose when the measured impact is suspicious.
* **Missing analytics** — if ASC analytics are absent, the impact field is `null` and the agent says so plainly instead of inventing numbers.