---
type: case-study
slug: vainu
client: Vainu
clientUrl: 'https://www.vainu.com'
clientIndustry: B2B sales intelligence
title: Sharpening B2B agentic intelligence
summary: >-
  Vainu shipped research, enrichment, and discovery agents on top of 50 million
  pages of Nordic business data. We worked with their team to make the product
  carry those agents: components, UX flows, and the context behind the AI
  features.
tags:
  - Agentic UX
  - Product design
  - Context engineering
  - B2B data
  - Sales intelligence
year: 2025
status: ongoing
cover:
  src: /work/vainu/vainu-cover.jpg
  alt: Vainu case study cover
testimonials:
  - quote: >-
      When entering the unknown with AI, working with partners like Intentface
      is a great way to get fresh perspectives outside of your company's own
      legacy. It's almost like an insurance policy for your ideas.
    name: Mikko Honkanen
    title: 'Co-founder, Vainu'
    avatar: /work/vainu/mikko.webp
impact:
  - >-
    A set of reusable components and an extended visual language built for
    agentic use cases, so the next agent feature can be designed and shipped
    without reinventing the interface around it.
  - >-
    A more streamlined product UX that carries agentic experiences instead of
    working around them, AI features with better context behind them, and a
    sharper vision for where the product goes next.
featured: false
comingSoon: false
hidden: false
publishedAt: '2025-02-01'
updatedAt: '2026-09-14'
---

**The client**

Vainu is a Nordic B2B company data platform, bootstrapped since 2014. Its data engine processes more than 50 million pages of public business documents, turning filings, news, and registry changes into buying signals for sales teams.

**The challenge**

Vainu ships fast, and agentic features were already embedded across the platform. The missing piece was not capability but coherence: the agentic experience needed a rethink, so that everything flows more intuitively and lines up with where the product is heading.

We work alongside Vainu's product team on the agentic experience rather than on any single feature: the components the agents are built from, the flows around them, and the context the AI actually reasons over. The work runs upstream of the build as well, honing the product vision and pressure-testing what is worth building next. Strategy and design in the same conversation, not a spec handed over for implementation.

### Any column you can describe

You write the prompt. The agent works out which columns are needed to answer it and
fills them across the whole list, thousands of companies at a time. Scores, categories,
plain text, whatever the question calls for, drawn from the sources you choose.

Vainu's Enrichment Agent: a plain-language prompt, the columns it generated, and a preview of the filled results across a list of companies

### A prompt instead of a query

Semantic search instead of keyword matching, run across the documents nobody reads:
municipal meeting minutes, city budgets, annual reports, ESG statements. It surfaces
intent early, like a municipality planning an investment long before a tender appears.

Vainu's Discovery Agent running a one-sentence natural-language prompt across 5.2 million pages of public business documents

### An interface that carries agents

New components and reworked flows so agentic features feel native to the product instead of bolted onto it.

### Better context behind the AI

Context engineering on the existing AI features, so every answer draws on the right slice of Vainu's data.

### Ideas, early

A steady feed of what is actually working in agentic products, brought in time to shape the roadmap instead of react to it.

### Toward a main agent

Research, enrichment, and discovery each own one step. Next is the layer above them: an agent that decides on its own which to call and when, so a whole process runs end to end.

Podcast: [When Your Users Are Agents, Not People](/podcast/02-mikko-honkanen-vainu)