Home: Cloudfic

Consulting client, B2C solar energy

Lead qualification and follow-up for a solar energy company

We audited and stabilized a B2C solar energy company's lead automation: the follow-up queue dropped from about 1,300 records to fewer than 40.

Leads from ads and forms go through AI qualification into a follow-up with idempotency guards, an async queue and the CRM.Ads, formslead captureQualificationconversational AIFollow-upidempotentCRMQueueasync
Leads from ads and forms go through AI qualification into a follow-up with idempotency guards, an async queue and the CRM.

Context

The client sells solar energy to consumers, with high lead volume from social ads and forms. It already had conversational AI qualification and scheduled follow-up, grown in layers with no documentation, no versioning and no instrumentation.

Problem

  • Duplicate leads re-entered the follow-up queue for lack of a concurrency guard.
  • A messaging channel was configured but sent nothing, and the team did not know.
  • A lead in follow-up who replied on their own never got an AI reply again.
  • Finished sequences kept being processed.

What we did

  • Freeze and critical fixes first: a full map of the system and removal of obsolete automations.
  • Idempotency and concurrency guards in the orchestration, with a state snapshot before every change.
  • Fixed the re-engagement flow so the AI replies again during follow-up.

Result

The follow-up queue dropped from about 1,300 duplicate or stuck records to fewer than 40 active ones, and we removed dozens of obsolete automations.

Facing a similar problem? Email us