Insight Agent

Nobody can watch every signal, every day. So Caplena now actively scans your reports and flags what's worth your attention — like a radar —  Risks to fix, and opportunities to scale. That means less digging through reports to find what changed. You see it and can act instantly.

Where you'll see them

• In your report — a collapsible side rail on the right, shows insights next to the insight element they came from.
• On the insights board — a global page collecting every insight across all your reports & views.
• On the insights detail page — a page that shows a specific insight, the linked insight element and linked tasks users can act on.

An insights' life-cycle

1. Discovery — On a regular interval, the Insight Agent scans your report views. If it finds something worth flagging, a card appears in the rail. If not, nothing shows — no noise

2. Updates — Live insights are rechecked on the same schedule, so the numbers stay current for as long as the finding remains relevant-

3. Retirement — Once an insight stops being relevant, it's retired and removed from the view. A new one can appear later if the data shifts again.

This new feature is in private bata, currently enabled across selected organizations. Want to give it a try? Contact support@caplena.com.

Read our documentation to get more details on the new insights feature.

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.

What's new

Look for the ✨ icon next to these elements in your Topics view:

• AI quality score → "Optimize the AI quality score"
• Add topic → "Suggest more topics for category {CATEGORY}"
• Edit topic → "Analyze and improve assignment of topic {TOPIC} in category {CATEGORY}"
• Topic description → "Improve description for topic {TOPIC} in category {CATEGORY}"

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.

Why it matters

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.

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.

What it can do ✨

• Tune topic descriptions to reduce unassigned rows and improve AI score
• Suggest and add new topics to close coverage gaps
• Simulate changes on a sample of rows before applying them
• Remove or merge redundant/overlapping topics
• Flag conflicts with manually reviewed rows

Not yet supported (coming soon👷🏼‍♀️) 

• Sentiment support
• Simulating brand-new topics

Ask the Insight Agent a question about how Caplena works — it'll answer directly, no need to leave your project and dig through documentation.

Automating your workflow just got much easier. You can now schedule alerts, notifications, and recurring tasks directly through the Insight Agent using a natural conversation.

Instead of navigating through multiple settings, simply tell the Insight Agent what you need, and it will set up the recurring task for you.

What’s New:

• Conversational Scheduling: Just ask the Insight Agent to schedule an alert or recurring task. For example, simply type: "Send me a week-on-week KPI summary each Monday at 08:00" and the agent handles the rest.
• Auto-Optimized Prompts: The Insight Agent automatically translates your quick request into an optimized prompt to ensure you get the best possible data summary in your inbox.
• Customizable Delivery: Open any scheduled alert to modify its frequency (One-off, Weekly, Monthly, Quarterly), adjust the time, or change the recipient to yourself or another team member.
• Centralized Alerts Dashboard: Keep track of all your active recurring tasks, agent prompts, and notifications in a dedicated "Alerts" overview page.

How to use it:

Open the Insight Agent inside any project and type your scheduling request. Once the agent confirms, your new alert will appear in the Agent Alerts section on the left-hand panel. You can click on it at any time to edit the details or trigger a test alert to see exactly what the notification will look like.

To get the most accurate answers from Caplena’s Insight Agent—especially when querying your data via Slack, Microsoft Teams, or ChatGPT, the AI needs to understand the blueprint of your project.

We’ve rolled out a few structural updates to reduce AI guesswork and make the Insight Agent even more powerful:

• 10x More Project Context: We’ve increased the character limit for your Project Context from 500 to 5,000 characters. You now have the space to thoroughly brief the AI on the specific nuances, background, and goals of your dataset.
• Default Date & Score Columns: You can now explicitly define which columns represent your primary timeline (e.g., Review Date) and primary metric (e.g., Rating). By setting these defaults once, the AI immediately knows how to accurately track trends and weigh sentiment without needing extra prompting.

Where to find it:
You can update these anytime in the Data View, or simply confirm them when setting your project to Live to connect with everyday tools like Slack, Microsoft Teams, or ChatGPT.

Powerful for Experts, Effortless for Everyone — now where work happens. Insight Agent is now available in Slack, Microsoft Teams, Copilot, and ChatGPT (MCP), so anyone can ask questions and get reliable insights without leaving their daily tools.

This is a big step toward democratizing insights across your organization: experts move faster with on-demand analysis, while non-research teams self-serve clear, actionable answers — no dashboards, training, or back-and-forth required. Less chasing data. More turning feedback into decisions. 💪

How it works

• Create a shared channel (e.g., #customer-feedback-insights)
• Ask questions by tagging the agent with @Caplena in 1:1 messages or public channels
• Here is an example question: @Caplena What topics had the biggest impact on the NPS change in the last 4 weeks?

Advantages

• Help teams discover what the bot can do (and copy great prompts)
• Learn from each other’s use cases over time
• Discuss insights together — and jump in if you disagree
• Keep decisions and learnings accessible for everyone

👉 Set up the integration in your Integrations Settings and get started.

Insights are most powerful when they show up at the right moment — in the tools you already use. With these new integrations, Caplena fits seamlessly into your daily workflows, helping teams move from feedback to action with less friction.

Simply select the projects you want to connect and query your insights directly from your go-to tool.

💬 Slack & Microsoft Teams

Share project updates, alerts, and insight summaries in the channels your organization already relies on — keeping everyone aligned without switching tools.

🤖 MCP Integration

Connect Caplena to MCP-enabled AI workflows to build custom automations and intelligent insight pipelines — tailored exactly to how your teams work.

The response to our Insight Agent has been incredible! This surge in usage recently pushed our LLM providers to their limits, occasionally leading to resource constraint errors or timeouts.

We’ve been working around the clock to build a more resilient and contineously improving system for you. We are excited to announce a major infrastructure upgrade: advanced multi-region datacenter load balancing (that’s just fancy dev-speak for: "the Agent is now much harder to break, even when it’s busy" 🤓).

• What this means: The Insight Agent now intelligently routes requests to the most available datacenter, bypassing provider bottlenecks and ensuring stable performance even during peak hours.
• Performance: You'll notice significantly fewer errors and smoother analysis for large datasets.
• Compliance: Most importantly, our EU-only data residency remains unchanged. All data processing and storage continue to stay strictly within the European Union.
• Continuous Learning: A quick reminder that your Thumbs Up/Down ratings help the Agent refine its logic to better suit your specific tasks, project goals, and needs. We appreciate the feedback!

Ask questions with your voice — faster, hands-free insights.

You can now speak your questions directly into Caplena and get instant answers from your data.

What’s new:

• Voice input: Ask Insight Agent anything using your microphone
• Faster workflows: Perfect when you’re multitasking or on the go
• Multilingual support: Works across the languages Caplena understands

Give it a try next time you open Insight Agent — just tap the microphone and start speaking.