design: experiment phase — measured evidence for decisions - #1057
Merged
Conversation
Design log for a new pipeline phase beside research and discussion: controlled experiments designed before they are measured, feeding decisions through the topic's discussion. Settled in discussion 2026-08-30; prior art: the dex experiment system + the external pre-registration/ELN/experimentation record. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Aug 30, 2026
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…t, phase-symmetric Owner walk 2026-08-31: direct invocation retired (menu is the router, fresh context always), spawn = id + problem file + lock (design is the experiment phase's job — the laboratory model), per-experiment menu entries, research locks identically to discussion, one-at-a-time rule deleted. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…reads whole The model sections now state the corrected design end to end: an addendum tool used by research and discussion, context isolation as a scientific control, the spawn as the one door (id + problem file + lock), menu routing, per-experiment entries, sub-experiment splits, narrow remit, empowered execution. Amendments retained as the record; implementation plan replaced with the rebuild stack. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…n, sub-ids confirmed Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Aug 31, 2026
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Aug 31, 2026
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…e phase Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
… the shape is what's standard, never the verb Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Design log for the experiment phase: a new pipeline phase beside research and discussion in the Discovery stage (epic, feature, cross-cutting). Controlled experiments against real systems — a design (question, prediction with reason, decision rule, setup) written and confirmed before the first measurement, a series per topic, append-only reports, and results feeding decisions through the topic's discussion, which can override.
Settled in discussion 2026-08-30. Prior art studied: the dex experiment system (
dex/business/experiments/) and the external record (pre-registration / registered reports, ELN practice, ML experiment tracking, industry experimentation culture).Standalone design PR per the living-document rule — the implementation stack bases on main.
🤖 Generated with Claude Code