AccAnalysisAccAnalysis
Software & SaaS

Business cards to prioritised follow-up, without leaving the building

A software company needed to capture and work event and field leads on its own infrastructure. We built an on-premise lead-management system with card digitisation, interaction capture and prioritised follow-up.

At a glance
Status
Delivered
Region
Japan
Engagement model
Dedicated team

Status: Delivered. Described from our own delivery records. Client identity, brand and commercial terms are withheld. Figures, where given, cover the period stated and nothing beyond it.

The organisation

Context

A software company supplying post-sale systems to car resellers. Its pipeline comes substantially from trade events and field visits, where the artefacts are business cards and conversations.

Its data-handling position ruled out hosted lead-management tooling.

The brief

The problem

  • Leads captured at events arrived as a stack of cards and a set of memories.
  • Contact details were transcribed manually, days later, with the conversation context already fading.
  • There was no consistent way to distinguish a lead worth calling on Monday from one worth calling next quarter.
  • Follow-up campaigns were assembled by hand, so they happened late or not at all.
  • Hosted tools were not an option, which removed most of the market.
The work

What we built

An on-premise lead-management system

Running entirely on the company's own infrastructure.

Business-card digitisation

Using optical character recognition, so a card becomes a contact record without transcription.

Interaction capture with transcription and automatic field population

So the context of the conversation lands on the record while it is still accurate.

Priority tagging

So the follow-up list is ordered rather than chronological.

Bulk follow-up email campaigns

Driven from that ordering.

Method

How we delivered it

  1. 1

    Establish the infrastructure boundary

    And size the on-premise deployment.

  2. 2

    Build the contact and interaction model first

    The thing everything else writes into.

  3. 3

    Add card digitisation

    Tuned against real cards in the languages and layouts the company actually encounters.

  4. 4

    Add interaction capture and auto-fill

    With a review step before the record is committed.

  5. 5

    Add prioritisation and campaigns

    Tested on a real event's leads.

Sequence

How it was phased

PhaseDurationWhat happens
1Infrastructure & data model
2–3 wks

On-premise deployment, contact and interaction structures

2Card digitisation
3–4 wks

OCR, field extraction, real-card tuning

3Interaction capture
3–4 wks

Transcription, auto-fill, review step

4Prioritisation
2 wks

Tagging rules, ordered follow-up list

5Campaigns & pilot
2–3 wks

Bulk outreach, tested against one real event

Indicative phasing for work of this shape. Actual duration varies with data quality, access and decision speed.

Hand-over

What the client keeps

  • The system and its source
  • The on-premise deployment configuration
  • Extraction and tagging rules
  • Campaign templates
Stack
On-premise deploymentOCRTranscriptionPythonEmail automation
Keep reading

Related

Related case studies

Tell us what your current system can't do, and we'll tell you what it would take to change that.