Skip to main content
Large-scale CX or brand trackers come with unique challenges around topic management. You’re often dealing with tens of thousands, hundreds of thousands, or even millions of rows per year — and you need to:
  • Develop and refine your topic collection quickly and iteratively
  • Detect new trends that emerge over time
  • Maintain an audit trail so any changes are deliberate, not accidental
Caplena recommends a DEV + PROD project setup to handle all three.

​
The setup

You maintain two projects:
  • DEV project — a representative sample of your full dataset (typically 1,000–20,000 rows). This is your test ground for developing and iterating on your topic collection. AI runs here are fast and cheap.
  • PROD project — your full dataset. Topics are only applied here once you’ve validated them in DEV.
Your CSM team can set up the DEV project for you and ensure it’s always a representative sample of your production data.

​
Initial setup

1

Build your topic collection in DEV

Use the DEV project to develop your initial topic collection with LLM support. Explore rare topics, refine descriptions, and customize until you’re happy with the structure.
2

Run a quality check

Apply the topics to the DEV project and scroll through a sample of responses to verify the assignments look right. Add or adjust topics as needed — this is the time to experiment.
3

Copy topics to PROD

Once satisfied, copy the topic collection from DEV to your PROD project. For large datasets (hundreds of thousands to millions of rows), this initial assignment may take anywhere from a few minutes to a few hours.
From this point, new rows coming into PROD will automatically be assigned using the same topic collection.

​
Ongoing maintenance: updating topics over time

Over time, new themes emerge in your data. Here’s the recommended workflow for adding or refining topics without disrupting your production data:
1

Spot new trends in PROD

Use the Topic Assistant in your PROD project to review AI-suggested new topics. When you find topics worth adding, add them directly to PROD — but don’t run a full AI update yet.
2

Sync the new topics to DEV

In your DEV project, set a learning relationship back to PROD and use Resync topics from source to pull in the newly added topics. DEV now reflects the latest state of PROD.
3

Iterate in DEV

Run AI updates in DEV to see how the new topics are assigned on your sample data. Experiment freely — merge topics, adjust descriptions, refine until you’re confident in the result. Since DEV is small, each update is fast and inexpensive.
4

Sync back to PROD and run one consolidated update

Once you’re happy, sync the finalized topics from DEV back to PROD using Resync topics from source. Then run a single consolidated AI update on PROD.This one update applies all your changes at once — instead of running multiple expensive updates on millions of rows every time you tweak something.

​
Why this approach

Efficiency — iterating on a sample of 5,000 rows instead of 1,000,000 means faster feedback and dramatically lower AI run costs. You only pay for a full production update once you’re confident in your changes. Quality — you validate topic assignments on real data before pushing anything to production. No surprises. Audit trail — all changes to the production project happen in one deliberate batch. Your topic assignment history stays clean and meaningful, making it easy to track what changed and when.
The DEV/PROD workflow is especially powerful for wave studies — after each new wave is uploaded to PROD, use the Topic Assistant to spot emerging themes, validate them in DEV, then push a single clean update to PROD before sharing results with stakeholders.
Last modified on June 8, 2026