Amplifier Bundle

Becoming a Better AI Builder —
One Session at a Time

Metacognitive coaching for AI builders —
a system that evaluates the person who built it

Active

March 2026  ·  Chris Park  ·  github.com/cpark4x/amplifier-builder-coach

The Shift

Coding is solved. Now what?

AI can write the code. What changes next is how you choose what to build, how efficiently you direct it, whether you know when it’s good, how fast your ambition scales, and whether anyone else can see what you’re doing. Five dimensions mark the shift:

You can't improve what you can't see.
AI builders get feedback on what they ship. Never on how they build.
The Blind Spot

Session history is rich data,
sitting unused.

Every Amplifier session records what you built, which tools you used, how many iterations it took, what you abandoned. Hundreds of sessions, thousands of tool calls, all timestamped.

Nobody was reading it.

Plenty of tools tell you whether your code is good. Nothing tells you whether you’re getting better at building.

The Pipeline

Three steps to a coaching snapshot

1

Gather Evidence

Explorer scans session history within an adaptive window. Starts at 7 days. If fewer than 5 sessions are found, auto-expands: 7 → 14 → 28 → 90 days. Structures raw data into per-dimension observations.

2

Evaluate Against Framework

Coaching agent maps evidence to the five growth dimensions. Assigns qualitative levels — Low through Exceptional — calibrated to data volume. Every claim must cite a specific session or pattern.

3

Write Coaching Snapshot

Storyteller transforms the structured evaluation into a scannable coaching snapshot. 300-word ceiling. Second person. No platitudes, no jargon, no numeric scores. Stateless — each snapshot stands alone.

"Coach me" — that's the entire trigger.
The Output

A snapshot, not a report card.

Real output from the first coaching run — March 12, 2026

Your Snapshot

You’re building at an exceptional pace across multiple projects, and the work is genuinely novel — a self-evaluating pipeline, a consumer app under competitive pressure, review tooling used on real contributions. The gap is simple: nobody outside your system knows any of this exists.

What’s Working

Picking problems that don’t have names yet. You built a pipeline that evaluates your own building patterns — something nobody else has shipped.

Compounding your own leverage. Your read-to-edit ratio is 8:1 — you’re directing, not typing. And you used a tool you built to review someone else’s code.

What to Reconsider

Building in private indefinitely. One collaborator has found your work. No public writing, no announcements. Every week it stays unpublished is a week someone else might name it first.

What to Try Next

Write a 1,000-word post about what you learned building a system that watches you build. Not a tutorial — a reflection. Publish it where builders gather. One post, this week.

DimensionLevelSignal
Problem SelectionStrongProblems no one else has named yet
Leverage RatioStrong8:1 read-to-edit, parallel feature dispatch
TasteStrongTwo-hour audit on own shipped app
Ambition TrajectoryStrongFive meta-layers built in 85 days
VisibilityEmergingOne collaborator, no public writing

300 words max. Adaptive tone. No platitudes. Evidence or nothing.

Design Principles

Adaptive by design

Tone Calibration

Fewer than 10 sessions: tentative, curious. 10–100 sessions: observational, grounded. 100+ sessions: confident, direct. The system knows what it doesn't know.

Adaptive Evidence Window

Defaults to 7 days. If fewer than 5 sessions are found, expands automatically — 14, 28, then 90 days. Always evaluates with whatever is available. Never refuses to coach.

Composable

One line adds coaching to any Amplifier bundle. The behavior ships as a standalone YAML that pulls in agents and context. No code changes required.

include: builder-coach:behaviors/coaching

Evidence-Based, No Platitudes

Every observation cites a specific session or pattern. No numeric scores — qualitative levels only. Trajectory matters more than position. Generic advice is deleted before delivery.

The Journey

The cobbler's shoes

The coaching system couldn't coach its own builder.

“Coach me” is the trigger phrase. But when the author of Builder Coach said “Coach me” to their own system, nothing happened. The phrase wasn't in the trigger list. The namespace paths were broken. Competing delegation examples in the agent descriptions confused the routing.

Three root causes. All discovered by trying to use the thing you just built. The system designed to reflect your blind spots had blind spots of its own.

The format went through its own reckoning, too. The first version produced narrative essays — thoughtful, long, and heavy. Nobody wants a character study at 8 AM. Five design iterations compressed it to an assessment format: snapshot, strengths, gaps, action, scorecard. Under 300 words. The question users actually have is “Am I doing well?” — not “Tell me my story.”

The irony isn't a bug. It's the point. A tool that watches how you work and reflects it back will, inevitably, catch you in the act of not watching yourself.

First Evaluation

By the numbers

5,554
sessions analyzed
85
days of build history
5
growth dimensions scored
8:1
read-to-edit ratio detected
~2
minutes per evaluation
2
days to build

What the Coaching Found

The first real evaluation analyzed 5,554 sessions across 85 days. It flagged Visibility as the single biggest gap — “nobody outside your system knows any of this exists.” The coaching action: write and publish one reflection piece this week. This deck is part of closing that gap.

Source: data/reports/week-of-2026-03-12.md

Built in 2 Days — With Its Own Primitives

First commit March 11 at 3:51 PM. Public release March 12 at 10:56 PM. Built entirely from the same Amplifier primitives it evaluates — agents, recipes, behaviors, and context files. No custom infrastructure. The system that coaches builders was built the way builders should build.

Source: git log --all --format="%ai"

Architecture

Under the hood

2
Agents
coaching-agent (evaluator) + coaching-storyteller (snapshot writer)
3
Recipes
session-history-analyzer, weekly-retrospective, session-nudge
1
Composable behavior
behaviors/coaching.yaml
8
Python modules
discovery, parser, extractor, evidence, historical, nudge, chart, store

Built on amplifier-foundation + amplifier-bundle-recipes. No custom infrastructure — composes entirely from existing Amplifier primitives: agents, recipes, behaviors, and context files.

Get Started
“Coach me”

That's it. Two words. The pipeline handles the rest.

This deck exists because the first coaching run told its author to stop building in private. The system works.

Sources & Methodology

Research methodology

All claims in this deck are sourced from the public repository. Commands were run against the repo at the timestamp below. No external data or estimates were used.

Data as of: March 12, 2026, 23:20 UTC-7

More Amplifier Stories