Tabular Prompting
What it does
A method of presenting data as a markdown table before submitting a request to an LLM. The tabular structure helps the model more accurately track relationships between objects and their properties, reducing errors when processing complex queries with multiple conditions. Increases answer accuracy by an average of 40%.
When it helps
Use this technique when you need to analyze structured data with multiple filtering or comparison conditions. Particularly effective when working with multiple objects and their properties: comparing products, analyzing candidates, choosing from options, summarizing by criteria. Apply when the LLM gets confused by text descriptions of data or loses connections between objects and their characteristics. Ideal for tasks where accuracy of condition matching and minimizing errors is important.
A prompt you can paste
Generic by design: it applies the technique without knowing your task. Adapt the marked parts.
You are an expert data analyst. Your task is to analyze data and provide insights based on specific criteria. **Data:** Please analyze the following data regarding streaming services: | Сервис | Цена в месяц ($) | Качество видео | Эксклюзивный контент | Семейный доступ | | :---------- | :--------------: | :------------: | :------------------------ | :-------------: | | Kinoflix | 16 | 4K HDR | Фильмы студии "Gamma" | Есть | | Streamly | 12 | 1080p | Сериалы "Omega" | Есть | | ViewMax | 18 | 4K HDR | Шоу от "Delta" | Нет | | Cinetop | 14 | 4K HDR | Фильмы студии "Gamma" | Есть | | EpixHD | 11 | 1080p | Сериалы "Omega" | Нет | **Your Task:** Based on the data provided, identify which streaming service(s) best fit the following criteria for a family: 1. **Price:** Must be **no more than $15** per month. 2. **Access:** Must include **family access**. 3. **Video Quality:** Must be **4K HDR**. **Output Requirements:** - List all services that meet ALL three criteria. - For each recommended service, briefly explain why it meets the criteria. - If no service meets all criteria, state that clearly.
If this one does not fit, the two closest alternatives in the corpus are Anti-Bias Prompting and Multilingual Ensemble Prompting, which target the same failure from a different angle.
Worked example
The same technique applied to a concrete job: turn a messy sales export into a defensible summary. Use it as the pattern for your own case rather than as a finished artefact.
You are an expert data analyst. Your task is to transform a messy sales export into a defensible summary by leveraging the "Thinking with Tables" technique. ### Data Input (Messy Sales Export) Present the raw, unstructured sales data here. Imagine this is a block of text or a list of comma-separated values that needs to be cleaned and organized. *Example of messy data structure (replace with actual messy data if provided):*
Get this written for your actual task
Paste what you are trying to do and the corpus will be matched against it directly. Free, no account, about ten seconds.
single retrieval pass
That number is low on purpose, and it is real. It is the raw similarity of one retrieval pass: no specialist read the paper, no judge compared anything, the first plausible match won.
one of which is this page
Picking the right one for a specific task is the work, and it is the work GetDecision does.
| This page | one technique, generic prompt |
| What you just ran | one technique matched to your wording, nothing verified |
| Full run | ten specialists read the papers in full, a judge ranks the top three for your task and shows its reasoning, generation on the model you pick, saved to your history |
See the top three for your taskTen specialists, a judge, and the reasoning shown. Free account, first run included.
Run the full analysis