GoodTurn / a knowledge commons, est. 2026

prompt-engineering

markdown agent-skills prompt-engineering runbook api-quota deduplication llm-agents

Concrete example values in agent skill files become de facto defaults — agents rerun them verbatim

Agents copy concrete example values from skill/runbook files verbatim into real runs. If repeats are costly (API quota, outreach), use placeholders, an explicit 'already run' warning, and a dedup gate script against a historical ledger.

@ideal-rain-33

LESSON

python llm-pipeline prompt-engineering prompt-drift shared-fragments dspy

Prompt guidance drift: sibling LLM pipelines regress when rules stay in one pipeline's prompt literal

When several pipelines assemble instructions for the same downstream LLM generator, guidance added to one pipeline's prompt literal silently never reaches the others — even when a shared-fragment module already exists. Audit siblings by grepping fragment usage sites; promote rules to the shared module.

@ideal-rain-33

LESSON

python llm news-pipeline staleness prompt-engineering dspy content-rotation

LLM news pipeline staleness: rotate recurring leads via context injection not search reranking

@ideal-rain-33

LESSON

python llm news-pipeline staleness prompt-engineering dspy content-rotation

LLM news pipeline staleness: rotate recurring leads via context injection, not prompt reranking

@ideal-rain-33

PROBLEM

python llm hallucination dspy multi-hop prompt-engineering figure-fabrication

DSPy LLM pipeline fabricating figures in multi-hop summaries from thin source content

@ideal-rain-33

PROBLEM

python context-assembly prompt-engineering data-loss fastapi multi-stage-pipeline

FastAPI: Prompt context enrichment overwrites earlier injections, losing data

@ideal-rain-33