Skip to main content

​
What It Does

  • Custom Ranking: Assign a rank to each row using plain-English logic—no code or SQL required
  • Optional “Why?”: Flip on reasoning to include concise rank explanations
  • Flexible Inputs: Rank by any column(s)—Mix and match GTM, firmographic, or behavioral data
  • Clean Output: Returns your original table + a RANK column (and optional REASON)

​
🏁 Getting Started

AI Ranker node configuration screenshot
1

Add the Node

Drag the AI Ranker node into your flow.
2

Select Columns

Pick the fields to use for ranking—like @Close Date, @Deal Size, or @Engagement Score.
3

Write Your Criteria

Define your logic in plain English (e.g. “Rank by soonest close date.”)
4

Enable Reasoning (Optional)

Turn on Include Reasoning to explain each rank.
5

Name the Output Column

Choose a name (default is RANK) to avoid naming conflicts.
6

Run the Node

Click Run—you’ll get RANK and optionally REASON added to each row.

​
Inputs

​
🛠️ Required Fields

  • Columns to Rank (✅)
    Select the fields that drive ranking—these values get sent to the model for logic evaluation.
  • Ranking Criteria (✅)
    Describe your rules in plain English.
    Example: “Rank by highest Engagement Score, then by newest Lead Source.”

​
🎯 Optional Fields

  • Include Reasoning (⚪️)
    Adds a second column (REASON) explaining why the rank was assigned.
    Adds 1 extra credit per row.
  • Output Column Name (⚪️)
    Defaults to RANK. Use a custom name like PriorityRank to avoid name collisions.

​
Output

  • RANK – Numerical value based on your rules (lower = higher priority)
  • REASON (optional) – Short explanation for each rank
AI Ranker output screenshot
The lower the number, the higher the priority. (1 = top-ranked)

​
🚀 Use Cases & Prompts

Use CaseExample Prompt
Pipeline Prioritization“Rank open opps by soonest Close Date, then highest Deal Size.”
Lead Scoring“Rank leads by engagement + firmographic fit.”
Account Segmentation“Rank accounts by ARR and likelihood to close this quarter.”
Inventory Optimization“Rank SKUs by highest margin, then by age.”

​
✨ Pro Tips

Keep your ranking criteria laser-specific—vague logic yields noisy ranks.
Limit to 2–3 high-signal columns like @Intent Score or @ACV—clearer signal = better ranks.
Fill missing values before ranking—blanks can skew outputs silently.
Use a custom output column name (@DealRank, @PriorityScore) to make downstream logic cleaner.

​
⚠️ Important Considerations

Ranking large datasets may take longer and use more credits.
Missing or malformed input values can throw off the model’s judgment.
If your rules are too broad, many rows may get tied ranks—tighten your logic.

​
🛠 Troubleshooting & Gotchas

SymptomLikely CauseQuick Fix
All ranks are the sameCriteria is too vagueAdd more specific thresholds or secondary conditions
Blank ranksNulls in input columnsFill or filter missing values ahead of this node
Flow stalls on large tablesToo many rows at oncePre-filter or chunk into smaller batches

​
📝 FAQ

Absolutely. Just reference them all in your criteria (e.g., “Rank by ARR and Close Date”).
Yes — score first with AI Scorer, then rank using that column.
The model may assign the same rank. Use more precise conditions to break ties.

​
💰 Pricing

ActionCredits / Row
Rank only1
With Reasoning2
Each row you rank consumes credits. Reasoning adds +1 credit per row.

Prioritize like a pro—drop AI Ranker into your flow and always know what to tackle first. 🚦📊