Does This Task Actually Need an Agent?
Author(s): Rittika Jindal Originally published on Towards AI. Choosing between a script, RAG, a fixed workflow, and an AI agent using four requests to the same support team. Imagine you’re automating a billing-support inbox. Four customers send four different requests: Does this ttask actually need
Imagine you’re automating a billing-support inbox. Four customers send four different requests:
The article explains that whether you need an LLM, RAG, a fixed workflow, or an AI agent depends on separating message understanding from subsequent actions, and on what evidence is required versus how flexibly “next steps” must be chosen. It walks through four billing-support requests—invoice retrieval, refund policy questions, duplicate-charge resolution, and an account migration investigation—showing where simple scripts or fixed workflows work best, where retrieval helps when answers require documents, and where bounded agent behavior is useful when investigations require choosing different tool calls based on newly discovered evidence. The author emphasizes keeping investigation and high-risk execution (like refunds) separate, adding explicit stopping conditions, validating cited policy/version correctness and authorization rules, and benchmarking against a baseline with realistic test cases.
Finally, it advises starting with one request your current system can’t handle, identifying whether the gap is interpretation, evidence, or dynamic next-step selection, and building the smallest change that fixes it.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.