Plan your literature review
Organize your approach to reviewing academic sources before you start reading.
Claude turns a research question into a review plan — search terms, inclusion criteria, the themes to code for, and a screening workflow — so the review is systematic instead of ad hoc.
Single model call (rung 2 of 6). Generate, extract, summarize, classify or translate. One request, one answer.
Not an agent: the sequence of steps is fixed in advance, so the whole path can be tested end to end.
- Autonomy: T0 · Suggest
- Surfaces information, ranks, or recommends. Changes nothing. Human role: does all the work; may ignore the system entirely.
- How it is governed
- Output schema validation. A human reads it before it counts.
- Anthropic (Claude Certified Architect – Foundations (CCAR-F))A single, well-prompted LLM call, which is often enough. source
- OpenAI (OpenAI agent guidance (Agents SDK, Codex, OpenAI Academy))One model request with clear instructions and context. source
- Google Cloud (Generative AI Leader)Prompt engineering: zero-, one- and few-shot prompting (exam §3.2). source
- Microsoft (AI-901 (Azure AI Fundamentals) and AB-100 (Agentic AI Business Solutions Architect))System and user prompts for generative AI models (AI-901). source
How Koko classifies AI · the full ladder is taught in AI & Agentic Delivery Foundations.
Try it
Illustrative demoA researcher is starting a review and wants a defensible protocol up front. Edit the inputs to tailor the output — it's baked synthetic data, so nothing leaves your browser until you run it live.
- Plan a literature review for this question: search strings, inclusion/exclusion criteria, and themes to code.
- Design a screening workflow (title → abstract → full text) with decision rules.