docs(plans): add content brief synthesis design doc#673
Open
arberx wants to merge 1 commit into
Open
Conversation
Design for two extensions to the existing content-target surface: a deterministic ownable/ceded winnability gate on content targets (reusing the discovery domain classifier) and a brief mode on the existing content explainer. Determinism decides which queries to target; the LLM only renders the brief. Docs-only, no code change. Co-Authored-By: Claude Opus 4.8 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Design doc (
plans/content-brief-synthesis.md) for two extensions to the existing content-target surface:surfaceClass(ownable vs ceded) on content targets, derived by reusing the discovery domain classifier (ota-aggregatorandeditorial-mediamap to ceded). No new LLM calls.briefmode on the existing content explainer (recommendation-explainer.ts) that synthesizes a structured brief, reusing the same provider plumbing, capability tier, and prompt-version cache, gated to ownable targets.Why
The content surface already finds opportunities deterministically and already has a narrow LLM explainer, but stops short of two judgments done by hand today: which queries are winnable with first-party content versus ceded to aggregators or editorial, and the brief itself (angle, why-winnable, schema hookup). The split keeps determinism deciding what to write for and the LLM deciding only how to write it, reusing two systems that already exist.
Docs-only. No code or behavior change.
🤖 Generated with Claude Code