Services
About
Portfolio
Careers
Blog
Get in touch
Data ManagementAI DevelopmentWeb Development

Generative AI meeting insights app built in 6 weeks

In 6 weeks we built a generative AI prototype that turns meeting transcripts into summaries, action items and sentiment, with a chatbot for questions.

Generative AI meeting insights web app

_>About

We built this generative AI prototype in six weeks. It transcribes meetings, analyses them and answers questions about them through a chatbot.

The aim is simple: get the key points, actions and sentiment of a meeting without attending it or reading every note.

Generative AI meeting insights web app - About - Image 1

>_Challenge

Users needed to browse notes generated from transcripts and ask questions about a recorded meeting, then get a detailed answer without digging through the notes themselves.

That raises two hard questions for any team building on LLMs: how do you know the answers are good, and how do you keep the cost of each answer under control?

Generative AI meeting insights web app - Challenge - Image 1

>>>Process

The prototype runs on large language models, including GPT-3.5 and GPT-4, with LangChain as the layer for querying them. On top of LangChain we built custom chains for multi-step work: summaries, action items and key points from each transcript, plus question answering.

We added sentiment analysis to read the emotional tone of a conversation, and tuned the chains with prompt engineering on our own dataset.

We measured quality in two ways: user ratings in the interface and automated evaluation. For each transcript the system generates questions, predicts answers with several configurations, and compares them by semantic similarity to find the best settings. We also assessed what SageMaker and Hugging Face would add in cost and benefit for later versions.

Generative AI meeting insights web app - Process - Image 1

__>Solution

The prototype summarises meetings, highlights their key points and lets users ask a chatbot for details in real time, so finding a decision or a clarification takes a question instead of a search through notes.

The part worth copying is the evaluation pipeline. Because every configuration is scored against the same transcripts, choosing between a cheaper and a stronger model becomes a decision backed by data, which is what a CTO needs before taking an LLM feature to production.

__> Technologies & Expertise

AI DevelopmentWeb Development

Related projects

_> Projects where we did this work

See all projects
Real-time AI voice avatar with ~1.5s perceived latency
Playing

Data Management · AI Development · Product Discovery

Real-time AI voice avatar with ~1.5s perceived latency

For a brand experience agency we built a voice AI avatar in three weeks: about 1s speech-to-text, 0.5s text-to-speech, ~1.5s perceived reply.

View project
Mobegí: RAG knowledge assistant for internal questions
Playing

Data Management · AI Development

Mobegí: RAG knowledge assistant for internal questions

Mobegí answers employee questions from company documentation inside Slack, with multi-pass anonymization for sensitive data. Prototype built in 12 weeks.

View project
Flairs: AI knowledge hub that maps a tech team's skills
Playing

Data Management · AI Development · Mobile Development

Flairs: AI knowledge hub that maps a tech team's skills

Flairs reads code in GitHub, Bitbucket and Slack and recognises 65k technologies, so tech leads can see team skills. We took it from idea to MVP.

View project

>>>Let's build something great_

If you are working on something similar, send us a short brief. A person on our team reads it and replies within one business day.

Apptension site footer

Taking new projects

Have a product to build, fix or scale?

Apptension is a senior-only software development company headquartered in Poznań, Poland. Since 2012 our engineers have shipped 360+ AI and SaaS products for startups, scale-ups and enterprises across the US, UK and EU: agentic MVPs, RAG and voice AI systems, multi-tenant SaaS and legacy modernization.

Projects shipped
360+
Founded
2012
Senior engineers
30+
Client CSAT
100%

Send a few lines about your product. A person from our team replies within one business day.

Start a projectScope it in Scope Studio
  • Emailcontact@apptension.com
  • Phone+48 533 352 052Poznań, Poland

  • Agentic MVP developmentNew
  • Agentic SDLC implementation
  • Product & SaaS development
  • Legacy modernization
  • Generative AI development
  • SaaS development company
  • Vibe-coded prototype to production
  • End-to-end software development
  • Senior engineering team extension
  • Product consulting & discovery
  • Tech due diligence for investors
  • All services

  • LLM application engineering
  • RAG & retrieval engineering
  • Voice AI agent development
  • MCP server development
  • LangGraph & LangChain agents
  • AI agent evaluation & observability
  • Node.js development company
  • Python & Django development
  • React & Next.js development
  • React Native app development
  • All expertise

  • Open-source SaaS Boilerplate
  • SaaS P&L model template
  • Walkthrough Studio
  • Agentic SDLC playbook
  • AI SDLC maturity assessment
  • Agentic SDLC ROI calculator
  • Founder resources
  • Events & exec dinners
  • Open source
  • Builder's Toolkit

  • Boutique vs large software house
  • Build vs buy vs partner
  • How to choose an AI & RAG partner
  • Team augmentation without chaos
  • Django vs Node.js for SaaS
  • React Native vs Flutter
  • AI in regulated industries
  • All guides

  • About Apptension
  • Case studies
  • Careers
  • Blog
  • Tech Radar
  • Agentic SDLC hub
  • Contact

Senior AI engineers shipping enterprise-grade AI and SaaS with startup speed.

Headquarters

Apptension sp. z o.o.23 Lutego 26
61-743 Poznań, Poland (opens Google Maps)

VAT-ID PL7831720203 · REGON 360404804
KRS 0000534235

Follow Apptension

Client reviews on Clutch

© 2012–2026 Apptension sp. z o.o. All rights reserved.

Privacy policySitemapllms.txt
  • 01Services
  • 02Portfolio
  • 03About
  • 04Careers
  • 05Blog

Services

All services

New · AI-native delivery

Senior engineers with AI coding agents

Ship a production MVP in weeks, or install agents into the team you already have.

Agentic MVPNewA production MVP your customers can rely on. Validate in 1–2 weeks, launch in 4–8, own all of it.Explore
  • Agentic SDLCAI coding agents installed into your delivery process in two weeks, with guardrails and metrics.
Agentic SDLC hub
>_ProductScope StudioFrom an idea to a shareable PRD_> Open_> Open
Emailcontact@apptension.comCall+48 533 352 052

HQ in Poznań, Poland

Start a project