§ rpiv-pi · blog

Field notes.

Updates, deep dives, and release notes for the rpiv-pi pipeline.

13 posts

rss

Bake the evidence into the prompt

juicesharp 7 min

Two probing turns at the start of every commit was the wrong default. rpiv-args 1.10 lets Pi skills inline shell output and runtime variables — the same primitive Claude Code ships, ported to Pi.

One morning of the loop

juicesharp 13 min

Issue #32 from a two-part feature request to a second approved review in three and a half hours. A walk-through of what driver-in-the-loop looks like when you can read every artifact along the way.

Release notes: v1.9.0

juicesharp 3 min

rpiv-advisor learns when to step back without disappearing, and ask-user-question stops hiding the bottom of its own dialog.

The self-verify trap

juicesharp 3 min

v1.8.2 shipped half its FRD. Here is what broke, why the design skill missed it, and which blueprint upgrade from this month would have caught it.

Release notes: v1.8.2

juicesharp 1 min

Pipeline artifacts move from thoughts/shared/ to .rpiv/artifacts/, and rpiv-site clears its W3C HTML/CSS validation errors.

Release notes: v1.8.0

juicesharp 4 min

rpiv-web-tools learns five new search engines, /web-search-config gets a friendlier picker, raw fetch refuses to talk to your localhost, and the web-search-researcher stops hiding in its own room.

Release notes: v1.7.0

juicesharp 3 min

rpiv-advisor learns to keep quiet around strong executor models, bundled agents move to a single global home, and the blog finally has a proper front door.

How we test skills at Codemasters

juicesharp 3 min

A small recipe for evaluating prompt changes against data instead of vibes: parallel arms, cheat-sheet answers, blinded LLM judges on a frozen rubric. The discover vs SAGE A/B is the worked example.

Release notes: v1.6.0 and v1.6.1

juicesharp 2 min

A sharper discover ships as v1.6.0, and v1.6.1 follows up with a fix so the advisor stops replaying stale history after Pi compacts a session.

discover holds against SAGE

juicesharp 2 min

Why the current discover skill is good, and what blind judges said when we A/B'd it against a SAGE-Agent adaptation.

A sharper discover

juicesharp 2 min

Architectural questions in the discover skill now name what they sacrifice, not just what they choose. Decisions arrive with a real rationale instead of agreement, and scope stays on the ask you actually made.

Release notes: v1.5.0

juicesharp 3 min

A redesigned voice equalizer, a sharper blueprint verifier, and a freshly minted blog, all in lockstep across the rpiv-pi family.

Hello, rpiv-pi

juicesharp 1 min

Introducing the blog — changelogs, deep dives, and release notes for the rpiv-pi pipeline.