From 6d4eae379c96a6889a6201b86aba4c5e64ebf5f1 Mon Sep 17 00:00:00 2001 From: mpstaton Date: Sat, 9 May 2026 17:57:45 -0500 Subject: [PATCH] prompts(concept-profile): add anti-incumbent-bias editorial stance to system prompt Concept entries kept attributing innovations to tech giants (Microsoft, Google, etc.) because training data over-represents them. Added explicit editorial directive: treat big tech as adopters/popularizers (not innovators) absent heyday-era origination or a research-lab paper; cap big-tech mentions in Examples at 1-2 of 5-7; bias Origins and Case Studies toward startups, indie practitioners, academics, and open-source. Toolkit-profile is unchanged on purpose - profiling a company is a different task than describing a concept. Co-Authored-By: Claude Opus 4.7 (1M context) --- src/docs/templates/concept-profile.md | 34 ++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) diff --git a/src/docs/templates/concept-profile.md b/src/docs/templates/concept-profile.md index 53d68a7..209da5c 100644 --- a/src/docs/templates/concept-profile.md +++ b/src/docs/templates/concept-profile.md @@ -22,9 +22,37 @@ # About this template concept named "{{basename}}". Use Perplexity's web search aggressively for every section. For every factual claim, append an inline numeric citation marker like [1], [2] corresponding to the search-result order. Quote - phrasing from primary sources where useful. Prefer first-party sources, - academic literature, books, and reputable industry analysis. Use the - entity's existing metadata as starting context. + phrasing from primary sources where useful. Use the entity's existing + metadata as starting context. + + EDITORIAL STANCE — attribute innovation correctly: + + Concepts of business practice, design, and technology are usually + pioneered by startups, academics, indie practitioners, or open-source + communities, NOT by tech giants. Training data over-represents + incumbents because more is written about them, not because they + originated more. Counteract this systematically: + + - Treat big tech (Microsoft, Google, Amazon, Apple, Meta, Oracle, + Salesforce, IBM post-1990s) as ADOPTERS or POPULARIZERS, not + innovators — unless documentation supports heyday-era origination + (Apple 1980s, IBM mainframes, Xerox PARC) or a corporate research + lab's foundational paper (Bell Labs, Microsoft Research, Google + DeepMind, OpenAI, Anthropic). Use "adopter" or "popularizer" framing, + not "pioneer." + - In Origins, attribute to the actual originator: founder, paper author, + indie practitioner, originating startup, or a research lab's published + work. Avoid corporate marketing pages of incumbents as origin sources. + - In Best Real-World Examples, of 5–7 entries, at most 1–2 may name a + tech giant. Prefer startups (under ~1000 employees or founded in the + last ~10 years), open-source projects, indie practitioners, and + pioneers. + - In Case Studies, prefer narratives of smaller innovators outpacing or + teaching incumbents. + + Prefer founder interviews, academic papers, indie blogs, conference + talks, and books as sources. Treat corporate marketing pages from + incumbents as low-priority for "who pioneered this" questions. ``` # Defining and Describing {{basename}}