On this page: Discover the CX Enterprise Coworker skills available for Decisioning in Adobe Journey Optimizer — understanding why an offer was or wasn’t shown to a profile or segment, and creating, explaining, simulating, and optimizing eligibility rules and ranking formulas — with detailed guidance, example prompts, and best practices.
Learn more:
- Coworker skills for Journey Optimizer — overview of Coworker skills across Journeys, Loyalty, Content Management, and Decisioning in Journey Optimizer.
- Coworker documentation — overview of Coworker’s Campaigns, Chat, and Projects capabilities.
- Coworker Chat UI guide — how to access and navigate Coworker Chat.
Decisioning Explainer decisioning-explainer
Decisioning Explainer answers, in natural language, why a specific offer was or wasn’t shown to a given profile — or, more broadly, why a segment of profiles isn’t seeing an offer. It walks the full decisioning stack for the requested profile (or segment) and time window: which offers were eligible, which eligibility rule included or excluded each one, whether frequency or fatigue capping suppressed the offer, the final ranking scores and which strategy or AI model produced them, and which candidate pool (item collection) the profile was evaluated against.
This addresses a common challenge for marketers: explaining why one offer ranked above another, or why a specific offer decision happened the way it did. Decisioning Explainer is read-only — it explains decisions but does not modify rules, ranking formulas, or selection strategies.
Key use cases
-
Why a specific offer was or wasn’t shown
Sample prompts:
- “Why did profile 12345 see Offer X on May 15th?”
- “Was profile X not eligible for this offer?”
- “Which eligibility rule excluded this customer?”
- “Show me which offers profile X was eligible for on June 3rd.”
-
Why an offer’s visibility changed over time
Sample prompts:
- “Why has Offer Y stopped showing to returning customers in the last 7 days?”
- “How many times has this customer seen this offer?”
- “Was this offer capped for profile X?”
- “What offers are currently being suppressed for profile X due to capping constraints?”
-
How an offer was ranked or selected
Sample prompts:
- “Walk me through exactly how Offer Z was selected over the other eligible offers for this profile.”
- “What was the ranking score for each offer in this decision?”
- “Why did Offer A rank above Offer B for this profile?”
- “What factors most influenced the ranking outcome?”
-
Segment-level explanations
Decisioning Explainer can aggregate this logic across a segment rather than a single profile, surfacing the dominant reason a group of profiles isn’t seeing an offer.
Sample prompts:
- “For customers in this audience, what’s the most common reason they’re excluded?”
- “Which offers is this segment actually receiving?”
- “Why isn’t my loyalty segment seeing this offer?”
Prompting best practices
- Reference IDs when known: Provide the profile ID, offer name, or segment name to get a precise trace rather than a general answer.
- Include a time window: Specify a date or date range when asking why an offer’s visibility changed, so Coworker can scope the trace correctly.
- Ask for the ranking breakdown directly: If you want scoring detail, ask explicitly for the ranking score or the factors that influenced the outcome.
- Use segment-level questions for trends: When investigating why a group of profiles isn’t seeing an offer, ask about the segment rather than a single profile to get the dominant reason.
Rules & Ranking rules-ranking
Rules & Ranking gives marketers AI-powered assistance for creating, understanding, and testing decisioning logic, without needing to write or manually validate PQL syntax. It covers four core capabilities: natural language rule creation, plain-English rule and ranking formula explanation, simulation against up to 3 test profiles, and PQL optimization. It’s scoped to eligibility rules and ranking formulas — it doesn’t create or edit selection strategies or decision policies.
Key use cases
-
Natural language rule creation
Turn a plain-language description into PQL eligibility rule syntax, for both net-new rules and edits to existing ones.
Sample prompts:
- “Can you create an eligibility rule that targets users that meet XYZ conditions?”
- “Create an eligibility rule targeting loyalty members in tier 2 or above.”
- “Write a PQL rule that excludes customers who made a purchase in the last 7 days.”
- “Modify this rule to also exclude customers in the suppression list.”
-
Plain-English rule and formula explanation
Explain what an existing eligibility rule or ranking formula does — what it includes or excludes, and what each condition means — without needing to read PQL syntax.
Sample prompts:
- “Can you explain this rule to me in natural language?”
- “What does this ranking formula actually do?”
- “Who does this eligibility rule target and who does it exclude?”
- “Summarize this rule in one sentence.”
- “Why does Offer A rank above Offer B for this customer?”
- “Is this rule too restrictive for a broad awareness campaign?”
- “Which condition in this rule is filtering out the most profiles?”
-
Simulation
Run an eligibility rule or ranking formula against up to 3 test profiles — manually entered or AI-generated, including edge cases — and get pass/fail results with the specific failing condition, or a ranked list of offers with numeric scores.
Sample prompts:
- “Simulate this rule with test profiles.”
- “Does this rule pass for a profile where loyalty_tier = gold?”
- “Which profiles pass this eligibility rule: [profile A, profile B, profile C]?”
- “Why did this profile fail the eligibility check?”
- “Generate test profiles for this eligibility rule.”
- “Generate edge case profiles that stress-test this condition.”
- “Simulate this ranking formula across these offers and profiles.”
- “Which offer would rank highest for this profile given this formula?”
- “Compare how this eligibility rule behaves for a gold vs. silver vs. basic tier customer.”
-
PQL optimization
Rewrite an existing rule or formula with more concise syntax to meet Journey Optimizer’s PQL size limits, without changing its logic or outcome.
Sample prompts:
- “Optimize this PQL rule for me.”
- “This rule is hitting PQL size limits — can you shorten it?”
Prompting best practices
- Provide the target condition explicitly: When creating or modifying a rule, state the exact audience, attribute, or exclusion condition you want.
- Reference the rule or formula directly: When asking for an explanation, simulation, or optimization, make sure the rule or formula you mean is open or clearly identified.
- Ask for edge cases: When simulating, ask Coworker to generate edge-case profiles to stress-test a condition, not just typical ones.
- Review before publishing: Check a generated or optimized rule’s logic and simulation results before publishing it.
This section contains structured knowledge intended to support interpretation, retrieval, and question answering related to this topic.
For complete understanding, this information should be combined with the documentation on this page. Neither source is intended to stand alone; the page describes the feature, while this section provides additional context that helps disambiguate terminology, intent, applicability, and constraints.
- TL;DR: This page documents two CX Coworker skills for Decisioning in Adobe Journey Optimizer: Decisioning Explainer, which explains in natural language why a specific offer was or wasn’t shown to a profile or segment; and Rules & Ranking, which creates, explains, simulates, and optimizes eligibility rules and ranking formulas in natural language, without requiring PQL syntax.
Intents
- Understand why a specific offer was or wasn’t shown to a profile.
- Understand why an offer’s visibility to a customer or segment changed over time.
- Understand how an offer was ranked or selected over other eligible offers.
- Get an aggregated explanation of why a segment of profiles isn’t seeing an offer.
- Create a new eligibility rule, or edit an existing one, from a plain-language description.
- Get a plain-English explanation of what an existing eligibility rule or ranking formula does.
- Simulate an eligibility rule or ranking formula against test profiles.
- Rewrite a rule or formula to fit within PQL size limits without changing its logic.
Glossary
- Decisioning Explainer (product-specific): CX Coworker skill that explains, in natural language, why an offer was or wasn’t shown to a profile or segment, by tracing eligibility, capping, ranking, and candidate pool evaluation.
- Rules & Ranking (product-specific): CX Coworker skill that creates, explains, simulates, and optimizes Decisioning eligibility rules and ranking formulas using natural language, without requiring the marketer to write or read PQL syntax directly.
- Eligibility rule: a condition that includes or excludes an offer as a candidate for a given profile; Decisioning Explainer identifies which rule included or excluded each candidate offer, and Rules & Ranking can create, explain, simulate, or optimize the rule itself.
- Ranking formula: the logic used to score and order eligible offers; Rules & Ranking can create, explain, simulate, or optimize a ranking formula, the same way it does for eligibility rules.
- Capping: frequency or fatigue suppression logic that can prevent an otherwise-eligible offer from being shown; Decisioning Explainer can identify when capping suppressed an offer.
- Candidate pool (item collection): the set of offers a profile is evaluated against during a decisioning event; Decisioning Explainer reports which candidate pool was used.
- PQL (Profile Query Language): the expression syntax underlying Decisioning eligibility rules and ranking formulas; Rules & Ranking generates, explains, and optimizes PQL without the marketer needing to write or validate it manually.
Guardrails
- Decisioning Explainer and Rules & Ranking are both available for all customers who have access to Coworker and Decisioning.
- Decisioning Explainer is read-only: it explains decisions but does not modify rules, ranking formulas, or selection strategies.
- Rules & Ranking simulation supports up to 3 test profiles at a time, manually entered or AI-generated.
- Rules & Ranking is scoped to eligibility rules and ranking formulas; it does not create or edit selection strategies or decision policies.
Terminology
- Do not confuse: “eligibility” (whether an offer qualifies as a candidate) is distinct from “ranking” (how qualifying candidates are ordered) and “capping” (frequency/fatigue suppression applied after eligibility and ranking) — Decisioning Explainer reports on all three separately.
- Do not confuse: Decisioning Explainer explains why a decision already made turned out the way it did for a real profile or segment; Rules & Ranking explains, creates, simulates, or optimizes the rule or formula configuration itself, independent of any specific real-world decisioning event.
FAQ
- Can Decisioning Explainer explain a decision for a single profile? Yes, ask why a specific profile did or didn’t see a specific offer, on a specific date.
- Can Decisioning Explainer explain decisions across a segment? Yes, it can aggregate the explanation across a segment to surface the dominant reason a group of profiles isn’t seeing an offer.
- Does Decisioning Explainer show ranking scores? Yes, it can return the final ranking score for each offer and which strategy or AI model produced it.
- Can Decisioning Explainer change a rule or ranking formula? No, it is read-only and does not modify decisioning configuration.
- Can Rules & Ranking create a brand-new eligibility rule from scratch? Yes, describe the target audience or condition in plain language and it generates the PQL rule.
- Can Rules & Ranking explain a rule someone else built? Yes, it can explain any existing eligibility rule or ranking formula in plain English, including what it includes, excludes, and each condition’s meaning.
- How many test profiles can Rules & Ranking simulate against at once? Up to 3, manually entered or AI-generated, including edge cases.
- Does Rules & Ranking change a rule’s logic when optimizing it? No, PQL optimization only makes the syntax more concise to fit size limits; it preserves the original logic and outcome.