Profile and context features for Personalized optimization models
Personalized optimization AI models can score decision items using up to 50 profile attributes and 20 context attributes; limited to select organizations.
Entries on this page are generated by AI from vendor sources. How AI is used
Selecting offers or content items from a catalog with eligibility and ranking.
| Month | Changes |
|---|---|
| 2026-01 | 2 |
| 2026-02 | 8 |
| 2026-03 | 1 |
| 2026-04 | 3 |
| 2026-05 | 4 |
| 2026-06 | 4 |
| 2026-07 | 5 |
| 2026-08 | 2 |
| 2026-09 | 10 |
| 2026-10 | 7 |
| 2026-11 | 1 |
Select a month to view the whole-record timeline. This clears timeline filters.
Platforms with at least one feature state classified in this capability (primary or secondary, minor updates included), in the site's fixed order. Select one to filter the timeline. Counts are not shown side by side: they reflect how finely each vendor documents, not how much it offers.
Filters apply to the timeline. The chart and platform totals describe the whole record. Selecting a chart month clears timeline filters to show that same whole-record scope.
Matches the Release Matrix evidence: latest state reached in the selected period, entries under review excluded, primary and secondary capabilities included.
No recorded changes match these filters.
Within each period: major updates as cards, then notable ones as rows; newest first in each group. Minor updates below.
Personalized optimization AI models can score decision items using up to 50 profile attributes and 20 context attributes; limited to select organizations.
A no-code Channel Builder lets admins add any outbound HTTP-based channel (e.g. WeChat, Kakao Talk, Messenger) with full native capabilities; now generally available to all environments after limited availability.
Coworker will answer natural-language audit questions about Decisioning objects, including inventories, relationships and edit history.
Coworker will let marketers create and populate Decisioning offers using natural-language prompts instead of manual field entry.
Fills empty recommendation slots with popular or alternate items when the primary recommendation returns too few.
Decisioning now works in the Web channel, letting decision policies serve relevant offers via the web visual editor.
A Coworker skill explains, in natural language, why a specific offer was or wasn't shown to a profile or segment, tracing the decision.
A Coworker skill lets you create, explain, simulate, and optimize Decisioning eligibility rules and ranking formulas in natural language.
Journey Simulation now models Decisioning: content decision nodes, Optimize targeting, decisioned actions, and offer ranking policies.
Test a Recommendation previews Basic and Advanced recommendation model results for a chosen user, random sample, or item, with live filter adjustments and zero-result troubleshooting.
Now GA (2 Oct 2026). Current summary: A no-code Channel Builder lets admins add any outbound HTTP-based channel (e.g. WeChat, Kakao Talk, Messenger) with full native capabilities; now generally available to all environments after limited availability.
Decisioning rules and ranking formulas can now be simulated with manual or AI-generated test variants before deployment, in Limited Availability.
Marketers can describe a Decisioning rule in plain language in the rule builder and let AI generate it; available to a set of organizations with Adobe AI capabilities (Limited Availability).
Decision item custom attributes can now be personalized at delivery time from profile, contextual, and audience data.
APIs to programmatically create, update, and list Offerings, also exposed as tools within the MoEngage MCP server.
AEM content fragments can now be mapped to decision items and used in decision policies, generally available after an earlier limited release.
Recommendations becomes one cross-channel tool with UI-configurable dynamic filters, position pinning, multi-rule block lists and rule previews.
Direct Mail journeys and campaigns can now use Decision policies, including batch decisioning to export offer items per profile.
Simulator that runs a Decision Policy against a chosen or anonymous user to preview selected, eligible, and capped offerings, including score calculations.
Now GA (18 Jun 2026). Current summary: AEM content fragments can now be mapped to decision items and used in decision policies, generally available after an earlier limited release.
Adds a Custom Formula ranking strategy combining fixed org-level goals with dynamic user-level signals to rank offers with real-time recalculated scores.
AI now flags Decisioning rules and ranking formulas that can be simplified and suggests an equivalent optimized version.
Email content can now be personalized and optimized via Decisioning using Priority Scores, Formulas, or AI Models, now GA with mirror page support.
Fragments can now be attached to decision items for use in code-based experiences and email campaigns via decision policies.
A Content decision activity integrates personalized offers into journeys, usable in conditions, custom actions, and other activities.
SMS content can now be personalized and optimized via Decisioning using Priority Scores, Formulas, or AI Models.
Upgrades Offer Decisioning with conversion goal tracking, five-variation testing, global/local control groups, down-funnel revenue analytics, and drafts.
Recommendation models can now filter results by multi-value product attributes such as tags, genres, promotions and regions.
New APIs let organizations programmatically migrate Decision Management entities to Decisioning, with rollback and reports.
AEP data in Decisioning now supports edge inbound use cases, beyond email and journey custom actions, in Limited Availability.
Push notification content can now be personalized and optimized via Decisioning, requiring a specific Mobile SDK version.
Lets marketers showcase products from a catalog directly within messages.