📢 Changelog – Fresh Features & Fewer Bugs (Hopefully)
Ah, updates - like taxes and awkward Zoom calls, they’re inevitable. But at least ours are more fun, come with fewer surprises and (hopefully) more fixes. Here’s where you’ll find what’s new, what’s improved, and what we accidentally broke (but promptly fixed). So grab a coffee, take a deep breath, and dive into the wonderful world of feedback evolution - one update at a time.
Some visualizations don't fit a preset. Now you don't need one to fit — just describe the chart you want, and AI builds it: type, data, styling, all of it.
The sky's the limit — see how it works.
Speed matters when you're digging through feedback — the less time you spend waiting, the more time you spend finding the insight that matters. We've optimized our database layer, delivering 2x–5x faster performance across the platform. Expect snappier load times on Reports and the Insight Agent, especially on large projects with heavy data volumes.
We're giving you more room to experiment with Smart Column and Topic Assignment: more included runs, and cheaper overage on top. Here's what's new.
Included LLM runs per row are doubling across the board:
And if you do go over, it's a lot cheaper now: overage pricing drops from 0.25 to 0.1 credits per row, on every plan.
Same story here. Included runs go from 4 to 6 on Enterprise, Team, and Agency plans, and overage pricing falls from 0.5 to 0.2 credits per row across all plans.
Nothing to do on your end — these upgrades are already live on your account, and they apply to existing projects and Smart Columns too, not just new ones.
You can now import reviews directly from Kununu, the leading employer review platform in the DACH region.
Caplena pulls in employee, applicant, and trainee reviews for any company, including the overall rating, review text, category ratings (work atmosphere, work-life balance, career development, salary, leadership, communication, and more), reviewer department, review type, and employer responses.
To add a source, go to Projects → Import Data → Kununu and enter a company URL, e.g. https://www.kununu.com/de/deutsche-post (supported countries: de, at, ch).
Kununu is Datashake-backed and follows the standard 3-day sync cycle for review platforms.
You no longer have to explain to the Insight Agent what you want it to work on. A small magic-wand icon now sits next to the parts of your project where the Agent can help — click it, and the Agent opens with a ready-to-run prompt already filled in for that exact element. We're starting with the Topics view, and you'll see the wand appear next to more elements across Caplena over time.
Look for the ✨ icon next to these elements in your Topics view:
Each prompt is automatically filled with the right context — the category and topic you're looking at — so you can send it as-is or tweak it first. When you click the icon, the Agent panel opens automatically so you can see the prompt land and hit send.
The Insight Agent can already optimize topics, sharpen descriptions, and lift your AI quality score. The hard part was knowing where to start and how to phrase the ask. These shortcuts remove that step: the Agent now meets you exactly where the work is, with the context already in hand.
Give it a try in any Topics view — just look for the wand.
Enterprise customers can now purchase additional credits directly under Settings → Billing → Manage credits — no need to go through your account team.
Choose a credit amount, confirm, and credits are added instantly.
The Insight Agent can now inspect your topic collection and suggest ways to improve it.
It looks for problems that are easy to miss by hand — vague topic descriptions hurting AI score or leaving rows unassigned, gaps in coverage, redundant or overlapping topics, and conflicts with rows you've manually reviewed. When it finds something, it can act directly: tightening descriptions, adding new topics, or merging duplicates.
Before making a change, it can simulate the effect on a subset of rows first, so you can see the impact before committing — useful for answering questions like "why isn't topic X being assigned to rows containing Y?"
Every change the Agent makes is logged in the topic assignment history, so you always know what changed and why.
You can now connect your Azure Blob Storage account to Caplena and import data directly from your containers — no manual exports needed.
Once connected, select any blob container as a data source and Caplena will automatically pull in your files for analysis.
Getting started: Set up your Azure Blob Storage connection →
Getting started with realistic data just got a lot more flexible. You can now either pick from a curated list of pre-built demo projects — spanning different industries and research types — or generate your own from scratch by describing your use case and letting Caplena create a fully analysed project tailored to it.
Whether you're onboarding a new team, exploring a use case before committing real data, or just want to see what Caplena can do, demo projects are now a first-class way to get there.
Semi-Open mode just got significantly better for large tracking studies like brand trackers.
Import keywords directly — You can now import a keyword list into Semi-Open projects, making it much faster to set up and maintain large, structured topic collections.
Increased stability — We've improved how Semi-Open handles large volumes of short-text data, reducing inconsistencies in clustering results.
More configuration options in settings — New controls give you finer-grained tuning over how the algorithm groups and assigns topics, so you can match it to your specific data structure.
New to Semi-Open mode? Learn how it works →
Ask the Insight Agent a question about how Caplena works — it'll answer directly, no need to leave your project and dig through documentation.
You can now filter any column by blank — empty cells are no longer invisible to your filters.
Whether you're tracking down a missing date, a smart column that didn't populate, or a row with an identifier error, just select the "blank" filter and they'll surface instantly. No more hunting through your data manually.
