Content Management
The Content Management category groups every setting that controls the structure your team applies to content as it flows through Sift - how it's labeled, evaluated, moderated, extended, captured, and organized. Inside you'll find six pages: Tag Groups for the workspace's tag library, Rubrics for AI quality scoring, Moderation Rules for spam and pattern detection, Custom Fields for extending Sift's data model with your own attributes, Forms for hosted submission forms and their branding, and Taxonomy for browsing the AI-generated topic hierarchy that powers Analytics. Together they define the vocabulary, scoring, and shape of every record in your workspace.
Tag Groups
The Tag Groups page is where admins manage every tag in the workspace. Tags categorize records, actions, and users - they show up in Analytics, in filters, on conversations, and as inputs to workflows - and they are organized into groups so related tags stay together in the picker (for example an Issue type group containing Bug, Feature request, and Billing).
The page is a single form covering every group at once, with an unsaved-changes banner that shows exactly what will change before you commit.
Editing groups and tags
Each group is rendered as an editable card with its name, an add tag action, and the list of tags inside it. For each tag, you can edit:
Value - The tag label that appears throughout the app.
Description - A short freeform description of what the tag means.
AI applicable - A toggle that controls whether Sift's AI is allowed to apply this tag automatically. Tags with AI off are admin-applied only.
Inside a group you can add new tags, rename existing ones, mark a group for deletion, and create new groups inline. Group names are searchable in tag pickers throughout the app.
Reviewing and saving changes
As soon as you make any edit, an amber Unsaved changes banner appears below the header summarizing the diff. Clicking the banner expands it into a structured breakdown - new groups, modified groups (with per-tag changes such as added, removed, renamed, AI enabled / disabled, and description changed), and deleted groups - so you can review the full impact before saving.
A Save now button inside the banner and a Save Changes button in the page header both commit the same diff.
Rubrics
The Rubrics page manages the custom evaluation rubrics Sift uses to grade customer-support interactions. A rubric is a structured scoring guide - a set of weighted criteria - that the AI applies to closed conversations to produce a quality score. Rubrics power the QA view in Analytics → Agents and feed CSAT prediction.
The rubrics table
A header introduces the page ("Create rubrics to grade customer support interactions. Rubrics help maintain consistency and quality across your team.") and is followed by a table of every rubric in the workspace.
Each row supports three actions:
Open - Click the row to open the rubric in its dedicated editor.
Duplicate - Clones the rubric so you can iterate without affecting the original.
Delete - Removes the rubric after a confirmation dialog.
Creating and editing a rubric
The Create button in the top-right opens a blank rubric editor at /app/settings/rubric/new where you define the rubric's name, description, scoring scale, and the list of criteria that make it up. Opening an existing rubric uses the same editor, pre-populated with its current configuration.
Moderation Rules
The Moderation Rules page configures how Sift catches spam, scams, and other unwanted content automatically. Detections from these rules feed the Analytics → AI Analytics → Moderation dashboard, and the rules can auto-close matching content so it never reaches your team.
The page contains three configurable cards: Stock Spam Detection, AI Spam Detection, and Pattern Moderation.
Stock Spam Detection
A built-in classifier that catches common spam patterns out of the box. The card has a status badge (Active / Inactive) and a single toggle to enable or disable it. When active, matched content is auto-closed; a View matches link jumps to the rule's detection log.
AI Spam Detection
An LLM-based classifier you tune to your workspace. The card has a top-level toggle plus several configuration fields:
Spam indicators - Free-text description of patterns the AI should treat as spam.
Safe indicators - Free-text description of patterns that look spammy but should be ignored.
Spam keywords - Comma-separated keywords that always count as spam.
Confidence threshold - A 0–100% input controlling how confident the AI must be before moderating. Lower values catch more spam at the cost of more false positives.
Discord Channels - Optional multi-select to scope detection to specific channels. Empty means "all".
A built-in Spam tester at the bottom of the card runs the classifier against a sample message and reports would moderate / would pass with a confidence percentage and reason - useful for tuning indicators before turning the rule on. View analytics and View matches links cross-link to the moderation analytics dashboard and the rule's detection log.
Pattern Moderation
A configurable card for rule-based moderation using regex or substring patterns. Use this for deterministic catches - specific phrases, URLs, or formats - that don't require AI judgment.
Custom Fields
The Custom Fields page extends Sift's data model with your own organization-specific fields - for example a CRM ID on a user, a region on an action, or an internal tier on an agent. Once defined, custom fields appear on the entity's detail page, become available as filters across the app, and are queryable via the API.
A header introduces the page ("Define and manage custom fields for actions, users, and agents across your organization.") and is followed by three tabs.
Three entity tabs
Custom fields are scoped to a single entity, so the page splits its work across three tabs:
Actions - Fields attached to actions.
Users - Fields attached to user records.
Agents - Fields attached to your team members.
Each tab shows the list of fields currently defined for that entity, with edit and delete actions per field, plus an Add field button that opens the create dialog.
Field types
The Add field dialog asks for a field name (snake_case identifier), an optional display name, and a type that determines how the value is captured and displayed:
Text
Short freeform strings.
Number
Integer or decimal numbers.
Date
Integer or decimal numbers.
Checkbox
A boolean value.
URL
Validated absolute URL.
URL (prefix-url)
Stores just the suffix; a configured prefix is prepended at display time (e.g. CRM record IDs that always live under the same base URL).
Multi-Value
A list of predefined values, configurable as Single-select or Multi-select.
Agent
A reference to a teammate.
Validation prevents reserved keywords, enforces snake_case, and caps field-name length at 50 characters. Fields can be edited, renamed, or deleted from the same dialog.
Taxonomy
The Taxonomy page is a read-only viewer for the AI-generated topic taxonomy that powers Analytics. It's the same hierarchy you see in Analytics → AI Analytics → Taxonomy, presented in a settings context so admins can browse exactly what their workspace is classifying conversations into. Taxonomies are generated and refreshed by Sift Admin → Taxonomy Pipeline; this page is for reading the result, not editing it.
Header and stats
The page header introduces the area ("Your topic hierarchy for organizing and understanding conversations across your channels."). In the top-right, two metadata lines report Built from N records and Updated <relative time> so you always know how recent the taxonomy is.
A row of stat chips below the header summarizes scale: Categories, Domains, Topics and Assignments.
Filtering
The taxonomy is three levels deep - Categories (L0) at the top (for example Complaint, Support, Bug, Feedback, Praise, Scam, Spam, Competitor, Industry, Brand, News, Noise), each with their own brand color, then Domains (L1) inside each category, and Topics (L2) at the leaves.
Two filter affordances narrow the view to a subset of categories:
A thin stacked overview bar shows each L0 as a colored segment proportional to its share of the topic count. Clicking a segment toggles its filter.
A row of filter pills below the bar — one per L0 plus an All pill — does the same. The active filter is highlighted with the L0's color and a subtle glow.
If no taxonomy has been built yet, the page shows the empty state: "No Taxonomy Available - A taxonomy will be generated automatically as Sift processes your organization's content."
Last updated