liveBook · Manning

Task prioritization

As explained in Effective Conversational AI

Problem prioritization is the process of ranking problems according to their expected value, effect, frequency, cost, and effort to resolve.

When a chatbot misunderstands appointment types, users may abandon booking and contact agents. Task prioritization ranks problems by expected value, effect, frequency, resolution cost, and effort. section 3.4.2

Assess each problem by considering:

  • User and business effect, including workflow completion, containment, and user experience. section 3.4.2
  • Frequency and conversation volume affected. section 3.4.2
  • Resolution effort, implementation cost, complexity, and required departmental buy-in. section 3.4.2
  • Expected return, balancing benefits against costs. section 3.4.2

Appointment booking

A PharmaBot team gives highest priority to confusion about appointment types because it directly blocks booking, a core business objective. An effect-effort matrix can separate high-effect, low-effort fixes from high-effect, high-effort redesigns. section 3.4.2

How Effective Conversational AI covers it

How deep it goes
Explains comparative assessment using effect, frequency, value, cost, effort, complexity, and expected return.
Examples
Uses appointment-type confusion, escalation analysis, effect-effort matrices, prioritized fix tables, and categorized chatbot problems.
What you can do after
Evaluate and prioritize chatbot fixes by comparing user impact, conversation volume, expected benefits, implementation effort, and cost.
How it connects
Connects problem analysis with triage, cost-benefit analysis, effect-effort matrices, and chatbot improvement.

Also explained in

Compare how 5 books explain task prioritization →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Effective Conversational AI. The section links point to the parts of the book it draws on.