INFO 5315

Conversation Engineering

Course Description

Course information provided by the 2026-2027 Catalog.

Conversational agents have become a primary interface to computing, but the practice of designing their behavior has not kept pace with their deployment. This course covers the specification, implementation, and evaluation of conversational agents. Topics include the structure of human conversation (turn-taking, grounding, repair, and cultural and linguistic variation); archetypes of conversation from clinical intake to customer support, each with its own goals and success criteria; the lineage of dialog systems; the system prompt as an executable behavioral specification; guardrails and the duties that attach to agent conduct; runtime concerns including retrieval, tool use, context management, and voice; and evaluation through simulated users, LLM as a judge, benchmarks, and audits of deployed systems. In a semester-long project, students specify, build, and evaluate an agent for a chosen conversation type.

Enrollment Information Enrollment limited to: Cornell Tech students.

Last 4 Terms Offered (None)

Learning Outcomes

• Analyze transcripts of human and human–machine conversation using conversation-analytic concepts such as turn-taking, sequence, and repair, and translate that analysis into a behavioral specification for a conversational agent.
• Implement a working conversational agent from a behavioral specification, selecting and configuring the runtime components the specification requires, including prompts, guardrails, tools, and memory.
• Design and calibrate instruments for evaluating conversational behavior, including simulated users and rubric-based automated judges, and iteratively improve the agent from the resulting evidence.

View Enrollment Information