Hashlogics
Case study · SaaS / Productivity · Global (38+ countries)

Broollie

Every meeting ends with a decision you can track.

AI meeting management and workflow automation SaaS.

Key takeaways

4 things that decide this

  1. 01Hashlogics built Broollie, an AI meeting platform that drafts agendas, writes minutes, and tracks action items for teams in 38+ countries.
  2. 02Broollie turns a finished call into minutes and action items in about five minutes, then sends reminders by voice, WhatsApp, and SMS.
  3. 03The platform runs as multi-tenant SaaS on Bubble, with GPT-4o-mini for agendas, MeetGeek for transcription, Twilio for alerts, and Stripe for billing.
  4. 04Universities, enterprises, government, healthcare, and professional services teams use it to keep decisions from getting lost.
Client
Go Broollie LLC
Industry
SaaS / Productivity
Region
Global (38+ countries)
Engagement
B2B SaaS · AI SaaS web application
Overview

Broollie turns scattered meetings into tracked outcomes. It drafts agendas with AI and assists live during the call. It writes the minutes and follows up on every action item, so decisions never get lost. Built for universities, enterprises, government, healthcare, and professional services teams across 38+ countries.

The challenge

The problem we set out to solve.

01

Meetings ran without clear agendas or objectives.

02

Manual note-taking meant insights got missed.

03

Action items were never tracked or enforced.

04

Communication was split across too many separate tools.

05

Leaders had no visibility into what meetings actually produced.

06

No central record of decisions for onboarding or compliance.

What success needed to look like

  • Every meeting ends with a documented agenda, minutes, and owned action items — not scattered notes.
  • Leaders get visibility into whether meetings are actually driving outcomes.
  • Teams stay connected across channels (voice, WhatsApp, SMS), so nothing gets missed.
  • The platform scales from small teams to enterprise, government, and healthcare without breaking.
Our approach

How we delivered it.

  1. 01

    Diagnose

    Mapped the meeting lifecycle before, during, and after the call. Found where agendas, notes, and follow-through were falling through the cracks.

  2. 02

    Design

    Designed the AI agenda-to-minutes-to-action-item pipeline together with the team. The notification model covers Zoom and Webex meeting flows and role-based access.

  3. 03

    Build

    Built the platform on Bubble as multi-tenant SaaS. GPT-4o-mini drives agenda drafts and live meeting help. Twilio sends voice, WhatsApp, and SMS alerts, MeetGeek transcribes, and Stripe bills subscriptions.

  4. 04

    Launch

    The hard part was security, not the AI. One Bubble app serves university, government, and healthcare tenants side by side, so a weak boundary could leak across clients. We rolled out through continuous security testing (SAST, DAST, dependency scanning) and staged every release before production.

  5. 05

    Run

    Ran two-week agile sprints. We kept refining the AI assistant, minutes, and dashboards as usage grew across universities, enterprises, and healthcare.

The solution

What we built.

We built a platform for the full meeting lifecycle. Before the call, AI drafts the agenda. During it, the Max AI assistant helps keep the discussion on track. After, the system writes minutes and action items in about five minutes — down from the hours it used to take one person. It then sends reminders by voice, WhatsApp, and SMS so the whole team gets them. Leaders see every outcome in one analytics dashboard, from a single meeting to the whole quarter.

The meeting lifecycle Broollie automatesLive
  1. ScheduleSynced from Zoom or Webex.
  2. DraftGPT-4o-mini writes the agenda before the call starts.
  3. AssistMax AI keeps the live discussion on track.
  4. CaptureMeetGeek transcribes; the system writes minutes in about five minutes.
  5. AssignAction items get an owner, not just a note.
  6. ChaseTwilio sends reminders by voice, WhatsApp, and SMS until it's done.

Most meeting tools stop at the transcript. Broollie's fifth and sixth stations are the ones that make a decision actually happen.

AI agenda builder for every meeting
Real-time AI assistant (Max AI) during the call
Automated minutes generated within about five minutes
Action-item tracking with follow-up
Multi-channel notifications: voice, WhatsApp, and SMS via Twilio
Meeting scheduling with Zoom and Webex
MeetGeek AI bot integration
Analytics and reporting dashboards for leadership
AI-powered search across meeting records
Stripe subscription management and Zendesk support
Role-based access control
Broollie marketing homepage and account settings with meeting preferences
Broollie meetings list and analytics export dashboard
Under the hood

Tech stack

  • Bubble.io (multi-tenant)
  • OpenAI GPT-4o / GPT-4o-mini
  • OAuth 2.0
  • AES-256 storage
  • TLS 1.2/1.3

Integrations

  • Zoom API
  • Webex API
  • MeetGeek
  • Twilio (voice / WhatsApp / SMS)
  • Stripe (billing)
  • SendGrid (email)
  • Zendesk (support)

Security

  • OAuth authentication with role-based access control
  • AES-256 encryption; TLS 1.2/1.3 in transit
  • SAST, DAST, and penetration testing
  • GDPR-aware data handling
More from the build
Broollie dashboard and mobile app shown on a laptop
Broollie secure sign-in screen
The takeaway

Your meetings only create value if what happens in them gets captured and acted on. We built the lifecycle that makes that automatic.

By Abdul Basit, CEO, HashlogicsUpdated
Start

Let’s deploy working AI into your business.

We build AI agents and automation, ship them into the tools you already run, then stay on under an agreed service level. A senior engineer reads every brief, and your call gets scheduled within 24 hours.

What happens next

  1. 01

    You send a brief or book a call

    Two minutes, whichever you prefer.

  2. 02

    A senior engineer replies within 24 hours

    Not a sales rep.

  3. 03

    Honest scoping, in writing

    And if we’re not the right fit, we say so.

Abdul Basit, CEO of Hashlogics

“I started Hashlogics because too many teams ship a demo, get paid, and disappear. We build to a standard we’d run ourselves — and we stay to keep it running.”

Abdul Basit · CEO · a direct line

Not ready to talk? Take the checklist.

12 questions to ask any AI agency before you sign. They separate a demo shop from a team that ships to production.

Get the checklist

Free · no newsletter