Create intermediate Works with: Any AI

Open-Ended Response Coding

Json output Has example

Theme analysis of free-text answers.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Code open-ended survey responses into themes. Survey question: [SURVEY_QUESTION]. Purpose of the analysis: [PURPOSE]. Responses (anonymized, one per line with an ID): [PASTE_RESPONSES]. Existing codebook, if any: [CODEBOOK].

Step 1: Read the responses and propose a codebook of 6 to 12 themes, each with a name, a definition, include and exclude rules, and a verbatim example.
Step 2: Code each response with one or more themes. Return valid JSON only, in this shape:
{"codebook": [{"theme": string, "definition": string, "include": string, "exclude": string, "example_id": string}],
"coded": [{"id": string, "themes": [string], "sentiment": "positive"|"neutral"|"negative"|"mixed", "confidence": "high"|"medium"|"low", "notes": string|null}],
"summary": [{"theme": string, "count": number, "share_percent": number, "representative_quotes": [string, string]}],
"uncoded_or_unclear": [string],
"limitations": [string]}

Rules: use only the responses given; quotes must be verbatim and free of personal details; if a response is ambiguous, set confidence to low and explain in notes; do not force a theme; report counts based on the coded list so they add up. After the JSON, add a two-sentence plain-text recommendation on how to check coding reliability by having a second person code 20 responses.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

{"codebook": [{"theme": "Slow support", "definition": "Waiting too long for an answer", "include": "mentions of days waited", "exclude": "complaints about the answer itself", "example_id": "R14"}],
"coded": [{"id": "R14", "themes": ["Slow support"], "sentiment": "negative", "confidence": "high", "notes": null}, {"id": "R15", "themes": ["Pricing", "Missing feature"], "sentiment": "mixed", "confidence": "medium", "notes": "Wants an export; says it is too costly for what it does"}],
"summary": [{"theme": "Slow support", "count": 18, "share_percent": 22.5, "representative_quotes": ["Took five days to get a reply", "Nobody answered my email for a week"]}],
"uncoded_or_unclear": ["R31"], "limitations": ["80 responses; single coder"]}
Second coder: code 20 responses independently and compare.

• qualitative
• coding