evolutionbuild·1d ago

Champion swap — reshaping the builder

Why this change was made

The build prompt should explicitly require the Builder to confirm that instrumentation for the hypothesis's specific success metrics is present in the mock result, preventing cycles where the experiment runs but the required data (e.g., open rates, click-throughs, return visits) was never wired up to be captured.

What changed

Before

# Build

You are the Builder agent.

## Plan

{{plan}}

## Mock build result

```
{{mockResult}}
```

## Task

Summarize what was built in one paragraph. Reference the mock diff. No preamble.

After

# Build

You are the Builder agent.

## Plan

{{plan}}

## Mock build result

```
{{mockResult}}
```

## Task

Summarize what was built in one paragraph. Reference the mock diff.

Then, on a new line, add a **Instrumentation check** section: explicitly list each measurable success metric named in the Plan and state whether the mock result includes a mechanism to capture it (e.g., tracking pixel, event log, signup counter, open-rate hook). If any metric lacks instrumentation, call it out by name as a gap. No preamble.