Case Study · aKube

aKube — a multimodal AI platform for technical presales.

Asquare designed and built aKube from the ground up: a custom, event-driven AI platform that reads engineering drawings and technical documents and generates customer-ready proposals, quotes, SOWs, and RFQ/RFP responses. Here's what it does — and how we built it.

60%
Reduction in proposal turnaround
8–12 hrs
Saved per Sales Engineer, every week
7+
Enterprise systems integrated
The brief

Turn technical drawings into customer-ready proposals — fast

Technical presales teams lose hours turning engineering drawings, RFQs, and scattered documents into accurate proposals, quotes, SOWs, and RFP responses. Asquare set out to automate that entire workflow with a platform that understands technical documents the way an engineer does.

  • Read the drawings — extract dimensions, tolerances, materials, and processes automatically.
  • Unify the knowledge — drawings, RFQs, meetings, CRM, and email in one searchable base.
  • Draft the documents — proposals, quotes, and SOWs generated with sources and versioning.
What aKube does

The functionality we built

Six capabilities that take a technical document from raw drawing to finished, accurate proposal.

Multimodal document understanding

Interprets engineering drawings, schematics, blueprints, PDFs, and CAD-derived files — extracting dimensions, tolerances, materials, part features, and manufacturing processes.

Custom AI agent

A bespoke agent harness (no LangChain/LangGraph) that runs long-lived sessions, calls tools, and streams results live — with all state persisted so work survives restarts.

Enterprise knowledge retrieval

Hybrid semantic + keyword search across drawings, RFQs, manuals, CRM records, emails, and historical proposals, with reranking and traceable source references.

Automated document generation

Drafts proposals, quotations, SOWs, RFQ/RFP responses, executive summaries, and technical docs via a prompt-driven templating engine with versioning and provenance.

Multimodal ingestion pipeline

Ingests video meetings (transcription + searchable keyframes), documents (with OCR), Teams chats, and email attachments into a unified knowledge base.

Human-in-the-loop governance

AI proposes structured edits gated behind human accept/reject, with session-scoped access control — built for enterprise trust and accuracy.

Architecture in brief

A distributed, event-driven system built to run for days

aKube is a distributed, event-driven system. Postgres change-data-capture (Debezium) streams into Kafka, and asyncio worker pools consume agent tasks with configurable concurrency, per-session queuing, retries with backoff, cancellation, and dead-letter topics.

Agent state — conversations, tool calls, results, token usage — lives in Postgres, so sessions can run for days and survive restarts, with responses fanned out to clients over WebSockets. On top of retrieval sits an LLM-driven templating engine where prompt-bearing placeholders are filled from the knowledge base, with source provenance, versioned snapshots, and per-user prompt customization.

Up to a 60% reduction in proposal turnaround and 8–12 hours saved per Sales Engineer each week — while improving consistency and preserving institutional knowledge.

— aKube platform impact
The impact

Faster proposals, without added headcount

  • Up to 60% faster proposal turnaround.
  • 8–12 hours saved per Sales Engineer, every week.
  • Greater consistency and preserved institutional knowledge.
  • Higher proposal throughput — with no increase in headcount.
  • Enterprise-grade multimodal AI, proving Asquare's ability to ship it.

Have a technical workflow to automate?

From multimodal AI to enterprise-grade platforms, Asquare designs and builds systems that ship. Let's talk about yours.