Skip to content
Condictor Studio
Automation
Automation

Automating enquiry handling

How to break enquiry handling into automatable stages, where to keep a human boundary, and what to measure to know whether it helped.

About 2 min readby
Six modules on a service track, with the fifth routed along a separate path through a coral decision point

Break enquiry handling into stages and automate only decisions that are repeatable, measurable, and safe. Receiving a case, enriching its data, or preparing a draft can be good candidates; the safe level of classification and sending depends on data quality and the cost of an error.

Six stages of enquiry handling

StageWhat happensTypical owner
1. Intakea case arrives from email, form, chat, or phoneautomation
2. Classificationtype, urgency, and right team are identifiedautomation with AI layer
3. Enrichmentcustomer, history, or order data is addedautomation
4. Draft responsea draft is prepared from a knowledge baseAI layer
5. Resolutiona non-standard decision is madehuman
6. Closure and measurementthe case closes and becomes learning dataautomation
Six enquiry-handling stages in one track; at the fifth stage the track branches to a separate highlighted decision block
Six service stages: give the machine stages where the decision is repeatable.

Start with classification and data, not a robot reply

Classification is a good first step when it is frequent, has a clear correctness criterion, mistakes are reversible, and historical cases form a representative test set. A low-confidence result, missing data, or a high-risk category should route to a person.

For response drafting, the company knowledge must be controlled and current. Otherwise the system can produce a polite but false answer. Start with a suggestion that a person approves; move to automated sending only in narrow, tested categories with a complete log.

Keep a human boundary

Escalate cases involving legal or costly consequences, empathy or de-escalation, low confidence, absent source evidence, or an explicit request for a person. The customer should have a simple route to human contact. Any AI interaction disclosure required by the applicable rules should be assessed for the actual interface and use case.

Measure quality as well as speed

Compare time to first response, time to resolution, share of cases handled without a person, classification accuracy, and the rate of cases that return. A faster response is not an improvement if it creates more repeat work.

Indicative August 2026 ranges: 2,000–8,000 PLN net for a focused intake/classification/enrichment automation; 8,000–25,000 PLN net for a fuller AI-assisted flow; and 8,000–30,000 PLN net for an end-to-end case agent. Start with the First Automated Process.

Maciej Szukalski

Author

Maciej Szukalski

Founder of Condictor · systems architect · research and development

He has designed and built digital products since 2014. He specialises in architecture, research, and applications with automation and intelligence layers.

Have a problem to solve?

Let’s find the right first step

Describe your situation in a few sentences. We’ll return with questions or a concrete proposal for what comes next.

Describe your topic

See also

← All articles