An Amplifier Case Study
185 lines of markdown, zero code
anderlpz/amplifier-bundle-design-intelligence-enhanced
The Design Intelligence Enhanced bundle faithfully gathered what's happening in design. But "what's out there" is only the informed half — taste is the judgment half, and it was missing.
First, the proof that the informed half already worked.
A weekly research recipe fetched RSS feeds into a dated archive, generated a trend summary, and updated a 30-day rolling index. The collection engine was real and running.
Yet all that collecting hit a ceiling.
More feeds meant more data, not better judgment. The agents had no memory of your taste and no loop connecting accumulated trends to your personal preferences.
The obvious instinct is to build a feature. It was the wrong instinct.
Taste turned out to be an instruction problem, not a code problem. Instead of engineering new machinery, the answer was to teach the existing agents how to reason about preference.
Here's the instruction that carried the judgment.
context/taste-awareness-instructions.md loads and merges your user-global and per-project taste profiles, then reasons in a three-mode protocol. No code — just prose.
And it does more than decide once — it learns.
On at least 2 occurrences of a signal, it proposes a profile update, escalating confidence Low → Medium → High. That's the loop from data to remembered taste the bundle never had.
All of it shipped as markdown, in a single day.
Registered by one line in bundle.md and six-line frontmatter edits per agent, taste-awareness reached 7 advisory agents plus research-analyst. Across all 5 commits: only markdown and yaml — 0 code files.
The reframe was right — so what's the pattern?
Look for judgment problems disguised as engineering problems. Sometimes the capability you're about to build is one you can simply write down.
Teaching taste took prose, not a platform.
Data as of: repo history 2025-12-23 → 2026-05-20 (49 commits)
Case-study subject: anderlpz/amplifier-bundle-design-intelligence-enhanced (author Alex Lopez), an enhanced fork of microsoft/amplifier-bundle-design-intelligence.
Research performed:
git show bbd8291 --stat; git log --format='%h %ad %s' --date=short 7985ed8 bbd8291 0988128 5da94e2 22100ccgrep -rln taste-awareness agents/; git show --numstat 5da94e2 22100ccgit show --name-only $c | grep -E '\.(py|js|ts|go|rs|sh|c|cpp)$' | wc -l → 0 (10 .md + 1 .yaml)head -20 recipes/weekly-design-research.yaml; git log --reverse | grep -iE 'research|learning' (0d9c1c3, 67838ab @ 2026-01-13)grep -niE 'Decide|Flag|Recommend Evolution|Confidence|at least 2' context/taste-awareness-instructions.mdgrep -n 'taste-awareness' bundle.md (line 13)Notes: The 185-line figure is the file size at introduction (commit bbd8291); it has since grown to 204 lines. Primary contributor: Alex Lopez (all 5 taste-awareness commits).