Skip to content

PCA tags

Tags are how Post Call Analyzer labels a call. Some tags are simple flags (“greeting said”), some extract a value (“product mentioned”), and some combine other tags into a business rule (“compliant opening”).

You configure tags on the Call Analyzer project Tags page. They run in the analysis pipeline’s apply-tags step, after transcription.

QA scorecards and analytics need consistent inputs. If every reviewer invents their own labels, trends are meaningless. Tags give you a shared vocabulary:

  • Supervisors filter and coach from the same flags
  • QA questions can require specific tags
  • Analytics can show which tags fire most often

Configure tags before you rely on them in QA conditions.

Screenshot needed
Tag master page with add-tag form and list of existing tags.
Where: Call Analyzer project → Tags
Save as: src/assets/screenshots/46-pca-tags.png
TypeIdeaBest for
MetadataRules on call metadata / payload fieldsCampaign, team, duration bands, CRM flags already on the row
BoW (bag of words)Keyword or phrase presence in the transcriptScript phrases, product names, prohibited words
GenAIModel judges or extracts from the transcriptTone, nuance, open-ended extraction
DerivedCombines other tags with include / exclude logicComposite compliance rules
NoneGrouping only (no evaluation)Organize a hierarchy of parent labels

Metadata tags do not read the transcript. They look at fields that arrived with the call row (payload) or pipeline output.

Example: tag vip_customer when a payload field segment equals VIP.

You choose:

  • Source — payload, output, or either
  • Field and operator (equals, contains, …)
  • Logic — all conditions (AND) or any (OR)

Use metadata when the fact is already known before analysis. It is fast and cheap compared with GenAI.

BoW tags scan the transcript for keywords. Matching is whole-word oriented and supports Unicode (including languages such as Hindi).

Example: keywords pricing, EMI, ब्याज for a “rate discussion” flag.

BoW is predictable and easy to audit: you can see which keyword hit. It is weaker on paraphrase (“monthly installment” might miss EMI if you only listed that token).

Screenshot needed
Add tag form with BoW type and keywords field filled.
Where: Call Analyzer project → Tags → Add tag (BoW)
Save as: src/assets/screenshots/47-pca-tag-bow.png

GenAI tags send the transcript (and your instructions) to the project’s LLM provider.

Two modes:

ModeResultExample prompt idea
FlagYes / no style judgment“Was the agent rude or dismissive?”
ExtractA value pulled from the call“What product did the customer ask about?”

GenAI is flexible but depends on provider quality, cost, and clear prompts. Prefer BoW or metadata when a simple rule is enough; use GenAI when judgment or free-form extraction is required.

Screenshot needed
Add tag form with GenAI type, mode, and prompt instructions.
Where: Call Analyzer project → Tags → Add tag (GenAI)
Save as: src/assets/screenshots/48-pca-tag-genai.png

Derived tags do not read the transcript directly. They fire based on other tags:

  • Include when — require certain tag keys (all or any)
  • Exclude when — suppress the derived tag if other tags matched

Example: compliant_opening includes greeting_provided and disclosure_read, and excludes prohibited_phrase.

Build base tags first, then layer derived rules. Derived tags are ideal for scorecard-friendly composites.

  1. Open the Call Analyzer project → Tags.
  2. Enter a key (stable id, snake_case, for example greeting_provided) and a human label.
  3. Choose the type.
  4. Fill type-specific fields (keywords, prompt, conditions, or include/exclude rules).
  5. Save.

Keys should stay stable: QA and analytics refer to them. Renaming a key later is more disruptive than changing the label.

  • Each important behavior has a clear tag with the simplest type that works.
  • QA questions reference tags that actually fire on real calls.
  • Analyzed records show tag results that supervisors understand without reading the full transcript.
  • Analytics Top tags reflects the labels you care about coaching on.
SymptomLikely causeWhat to try
Tag never matchesWrong type or empty configConfirm keywords / conditions / prompt
BoW misses paraphrasesKeywords too narrowAdd variants or use GenAI flag
GenAI inconsistentVague promptAdd examples and a clear yes/no definition
Derived never trueBase tags inactive or keys mistypedMatch include keys exactly to base tag keys
QA cannot select a tagTag is extract-only or wrong type for flagsUse flag / BoW / derived for yes-no QA conditions
No tags on recordsIntake not run or apply-tags failedCheck Jobs / journey; confirm runtime is up

Tags classify. QA scores.

A tag might say “disclosure read = yes.” A QA question might award 5 points when that tag is present, inside a bundle with other opening questions. Configure tags first, then build the QA scorecard.