docs(measurement): add seller-as-measurement-agent topology + conversation-context open question#3891
Merged
Conversation
…ation-context open question Two doctrinal additions surfaced from analysis of ChatGPT's ad-serving architecture in the context of post-#3884 measurement work. 1. New "Closed-loop topologies: seller-as-measurement-agent" subsection in the Verification layer. Names retail-media closed loop (Walmart Connect, Kroger Precision, Amazon DSP, Criteo) and AI-native channels (ChatGPT and agentic-conversation surfaces) as a structurally different topology where the seller IS the measurement vendor — not a degraded case of third-party verification. Documents how the existing primitives (BrandRef, qualifier slot, atomic-unit row shape) handle both topologies cleanly without channel-specific schemas. Notes that the seller-provided merchant- side SDK pattern (OAIQ on advertiser pages for ChatGPT) is the one missing primitive — tracked as #3889. 2. New "Where does conversation-context targeting fit?" open question in the Boundaries section. AI-native channels target using the conversation prompt itself as the targeting signal — closer to walled-garden engagement-signal targeting than traditional contextual. AdCP's existing Signals taxonomy doesn't directly model this; whether it warrants a new signal type or fits within Contextual signals is open. Documented so future signals-layer RFCs have a frame for it. No schema changes. Doc-only update keeping the taxonomy current with AI-native channel reality. Co-Authored-By: Claude Opus 4.7 (1M context) <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.
Summary
Two doctrinal additions to the measurement taxonomy doc, surfaced from analysis of ChatGPT's ad-serving and attribution architecture in the context of post-#3884 measurement work.
What changes
1. Closed-loop topologies: seller-as-measurement-agent (Verification section)
New subsection naming retail-media closed loop and AI-native channels as a structurally different topology where the seller is also the measurement vendor — not a degraded case of third-party verification.
Documents that the existing primitives (BrandRef, qualifier slot, atomic-unit row shape) handle both topologies cleanly without channel-specific schemas. ChatGPT-attributed conversions and Walmart Connect's
attributedSalesIn14Daysboth express viaconversion_value+qualifier.attribution_methodology: "deterministic_purchase"+qualifier.attribution_window: { interval: 30, unit: "days" }. No retail-media-specific schema, no AI-native-specific schema.Flags the missing primitive: seller-provided merchant-side SDK distribution / integration / supply-chain story (OAIQ on advertiser pages for ChatGPT). Tracked as #3889.
2. Conversation-context targeting open question (Boundaries section)
AI-native channels target using the conversation prompt itself as the signal — closer to walled-garden engagement-signal targeting than traditional contextual. AdCP's existing Signals taxonomy doesn't directly model this; whether it warrants a new signal type or fits within
Contextual signalsis open. Documented so future signals-layer RFCs have a frame for it.What this PR is NOT
No schema changes. The taxonomy doc is the only file touched. The shape we shipped over the prior PRs (#3576, #3877, #3884, #3885, #3886) already accommodates the AI-native topology cleanly — this is just naming the pattern in the doc so future readers can find it.
Files
docs/measurement/taxonomy.mdx— two new sections.changeset/measurement-taxonomy-seller-as-vendor.md— empty (docs-only)Test plan
Related
🤖 Generated with Claude Code