# Custom AI Prompt by Signaliz (`signaliz/custom-ai-prompt`) Actor Run structured AI prompts over company or custom records through the Signaliz public API, with optional web search and output fields. - **URL**: https://apify.com/signaliz/custom-ai-prompt.md - **Developed by:** [Signaliz](https://apify.com/signaliz) (community) - **Categories:** Lead generation, Agents, Automation - **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing $5.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Custom AI Prompt by Signaliz Run structured AI prompts over company or custom records through the Signaliz public API. This Actor wraps `POST /custom-ai-prompt` and supports flat public API input, batch rows, prompt templates, output fields, and search flags. ### What it does - Accepts one flat request, JSON records, a list of domains, pasted CSV, a CSV URL, or an Apify dataset ID. - Supports `prompt`, `user_template`, `system_prompt`, `output_fields`, `search`, `web_search`, `temperature`, and model override. - Defaults to `google/gemini-3.1-flash-lite`. - Preserves every original input column. - Appends structured AI results, credit usage, errors, normalized request, and raw Signaliz response. - Retries transient `429` and `5xx` responses with bounded backoff. - Writes one dataset item per input row and a summary to the key-value store under `SUMMARY` and `OUTPUT`. ### Input For a single company: ```json { "domain": "stripe.com", "company_name": "Stripe", "prompt": "Score this company for enterprise sales readiness.", "search": true, "output_fields": [ { "name": "score", "type": "number" }, { "name": "reason", "type": "text" } ] } ```` For row-aware batches, use `records`, `csv_text`, `csv_url`, or `source_dataset_id` with `user_template`: ```json { "records": [{ "company_name": "Stripe", "domain": "stripe.com" }], "user_template": "Score {{company_name}} at {{domain}} for enterprise sales readiness." } ``` ### Output Each dataset item includes the original row plus fields like: ```json { "company_name": "Stripe", "domain": "stripe.com", "success": true, "score": 87, "reason": "Strong enterprise fit.", "credits_used": 2, "model": "google/gemini-3.1-flash-lite", "search": true, "normalized_request": { "domain": "stripe.com", "prompt": "Score this company for enterprise sales readiness." }, "raw_response": {} } ``` ### Pricing Pay per result through Apify. The Actor uses the synthetic default dataset item event, so each dataset item is one billable result. ### About Signaliz Signaliz is a GTM data quality platform by Content Marketing Media. It powers enrichment, validation, and signal workflows for outbound teams operating at serious volume. # Actor input Schema ## `domain` (type: `string`): Company domain for a single flat request. ## `company_name` (type: `string`): Optional company name for the single request. ## `prompt` (type: `string`): Prompt to run for each row. ## `user_template` (type: `string`): Optional row-aware template. Use {{field\_name}} placeholders from each input row. ## `output_fields` (type: `array`): Structured fields to return. Use strings or objects with name, type, and description. ## `records` (type: `array`): Batch rows to process with the prompt or prompt template. ## `domains` (type: `array`): Alternative batch mode for a list of domains. ## `csv_text` (type: `string`): Paste CSV rows. Original columns are preserved in output. ## `csv_url` (type: `string`): Public URL to a CSV file. ## `source_dataset_id` (type: `string`): Read rows from another Apify dataset. ## `datasetId` (type: `string`): Alias for source\_dataset\_id. Included for compatibility with existing Signaliz Apify actors. ## `search` (type: `boolean`): Enable Signaliz web search context. ## `enable_search` (type: `boolean`): Alias for search. ## `enable_online` (type: `boolean`): Alias for search/online Signaliz model context. ## `web_search` (type: `object`): Optional advanced web\_search config forwarded to Signaliz. ## `model` (type: `string`): OpenRouter model ID used by Signaliz. ## `temperature` (type: `number`): Model temperature. ## `chunk_size` (type: `integer`): Rows grouped before the next bounded processing slice. ## `max_concurrency` (type: `integer`): Maximum simultaneous Signaliz API calls. ## Actor input object example ```json { "domain": "stripe.com", "company_name": "Stripe", "prompt": "Score this company for enterprise sales readiness.", "output_fields": [ { "name": "score", "type": "number" }, { "name": "reason", "type": "text" } ], "search": true, "enable_search": true, "enable_online": true, "model": "google/gemini-3.1-flash-lite", "temperature": 0.3, "chunk_size": 25, "max_concurrency": 5 } ``` # Actor output Schema ## `results` (type: `string`): One row per processed prompt input. ## `summary` (type: `string`): Aggregate counts, credit totals, and elapsed time. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "domain": "stripe.com", "company_name": "Stripe", "prompt": "Score this company for enterprise sales readiness." }; // Run the Actor and wait for it to finish const run = await client.actor("signaliz/custom-ai-prompt").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "domain": "stripe.com", "company_name": "Stripe", "prompt": "Score this company for enterprise sales readiness.", } # Run the Actor and wait for it to finish run = client.actor("signaliz/custom-ai-prompt").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "domain": "stripe.com", "company_name": "Stripe", "prompt": "Score this company for enterprise sales readiness." }' | apify call signaliz/custom-ai-prompt --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=signaliz/custom-ai-prompt", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Custom AI Prompt by Signaliz", "description": "Run structured AI prompts over company or custom records through the Signaliz public API, with optional web search and output fields.", "version": "1.0", "x-build-id": "xmLfqCKWJEWG4obqO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/signaliz~custom-ai-prompt/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-signaliz-custom-ai-prompt", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/signaliz~custom-ai-prompt/runs": { "post": { "operationId": "runs-sync-signaliz-custom-ai-prompt", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/signaliz~custom-ai-prompt/run-sync": { "post": { "operationId": "run-sync-signaliz-custom-ai-prompt", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "domain": { "title": "Domain", "type": "string", "description": "Company domain for a single flat request." }, "company_name": { "title": "Company name", "type": "string", "description": "Optional company name for the single request." }, "prompt": { "title": "Prompt", "type": "string", "description": "Prompt to run for each row." }, "user_template": { "title": "Prompt template", "type": "string", "description": "Optional row-aware template. Use {{field_name}} placeholders from each input row." }, "output_fields": { "title": "Output fields", "type": "array", "description": "Structured fields to return. Use strings or objects with name, type, and description.", "items": { "type": "object", "properties": { "name": { "title": "Name", "type": "string", "description": "Output field name." }, "type": { "title": "Type", "type": "string", "description": "Output field type, such as text, number, boolean, array, or json." }, "description": { "title": "Description", "type": "string", "description": "Instructions for this output field." } }, "required": [ "name" ] }, "default": [ { "name": "score", "type": "number" }, { "name": "reason", "type": "text" } ] }, "records": { "title": "Records", "type": "array", "description": "Batch rows to process with the prompt or prompt template.", "items": { "type": "object" } }, "domains": { "title": "Domains", "type": "array", "description": "Alternative batch mode for a list of domains.", "items": { "type": "string" } }, "csv_text": { "title": "CSV text", "type": "string", "description": "Paste CSV rows. Original columns are preserved in output." }, "csv_url": { "title": "CSV URL", "type": "string", "description": "Public URL to a CSV file." }, "source_dataset_id": { "title": "Apify Dataset ID", "type": "string", "description": "Read rows from another Apify dataset." }, "datasetId": { "title": "Apify Dataset ID (alias)", "type": "string", "description": "Alias for source_dataset_id. Included for compatibility with existing Signaliz Apify actors." }, "search": { "title": "Use search", "type": "boolean", "description": "Enable Signaliz web search context.", "default": true }, "enable_search": { "title": "Enable search", "type": "boolean", "description": "Alias for search.", "default": true }, "enable_online": { "title": "Enable online mode", "type": "boolean", "description": "Alias for search/online Signaliz model context.", "default": true }, "web_search": { "title": "Web search config", "type": "object", "description": "Optional advanced web_search config forwarded to Signaliz." }, "model": { "title": "Model", "type": "string", "description": "OpenRouter model ID used by Signaliz.", "default": "google/gemini-3.1-flash-lite" }, "temperature": { "title": "Temperature", "minimum": 0, "maximum": 2, "type": "number", "description": "Model temperature.", "default": 0.3 }, "chunk_size": { "title": "Chunk size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Rows grouped before the next bounded processing slice.", "default": 25 }, "max_concurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum simultaneous Signaliz API calls.", "default": 5 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```