Fetching from the wire…
01
02
03
04
05
06
07
08
Skills2026-06-28 · source-backed
Add a PromptFoo eval suite that runs every prompt change against fixed test cases across multiple models and fails the build on regression (Lakera). Prompt edits become reviewable diffs instead of blind tweaking. Exactly like unit tests, because that's what they should be.
Each link below shares sources, entities, or timing with this story.
OpenAI acquired PromptFoo / Shared entity: Promptfoo / Shared topic / What happened next / Tension
Linked by a graph relationship (OpenAI acquired PromptFoo); both cover Promptfoo; overlapping topics (against, code, eval).
OpenAI acquired PromptFoo / Shared entity: Treat / Shared topic / What happened next
Linked by a graph relationship (OpenAI acquired PromptFoo); both cover Treat; overlapping topics (code, exactly).
Linked by a graph relationship (OpenAI acquired PromptFoo); both cover Treat; overlapping topics (eval, model).
OpenAI acquired PromptFoo / Shared entity: Promptfoo / Shared topic / What happened next
Linked by a graph relationship (OpenAI acquired PromptFoo); both cover Promptfoo; overlapping topics (eval, prompt).
OpenAI acquired PromptFoo / Shared topic / Tension
Linked by a graph relationship (OpenAI acquired PromptFoo); overlapping topics (against, change, code, eval); pushes against this story (against).
OpenAI acquired PromptFoo / Shared entity: Treat / Earlier coverage / Tension
Linked by a graph relationship (OpenAI acquired PromptFoo); both cover Treat; earlier Treat coverage from 2026-06-23.
OpenAI acquired PromptFoo / Shared topic / Tension
Linked by a graph relationship (OpenAI acquired PromptFoo); overlapping topics (against, change, code); pushes against this story (against).
Linked by a graph relationship (OpenAI acquired PromptFoo); overlapping topics (against, code, model); pushes against this story (against).