# AI Lead Enricher & Personalizer (`enezli/ai-lead-enricher-personalizer`) Actor Lead enrichment with email verification and AI-written outreach. Cleans your lead list, verifies each email, and generates a send-ready personalized message per lead, each grounded in a real fact with a send-readiness score. Stop guessing which leads are worth contacting. - **URL**: https://apify.com/enezli/ai-lead-enricher-personalizer.md - **Developed by:** [Turgay NANTA](https://apify.com/enezli) (community) - **Categories:** AI, Lead generation - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $50.00 / 1,000 message generateds 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 ## AI Lead Enricher & Personalizer — From a raw lead list to send-ready outreach Turns a raw lead list into a **send-ready outreach package**: firmographic enrichment, **email verification**, and **fact-grounded** personalized cold-outreach messages — plus a **"can I send this?" verdict** for every lead. ### What it does Most tools give you either raw data or a blind draft. This actor closes the whole chain in **one run**: **enrich → VERIFY the email → write a send-ready FULL message → send-readiness gate.** Connect a Maps/Leads Finder scraper's dataset directly, or paste your own list, and get a prioritized "contact these first" table instead of rows you still have to think about. ### Why it's different 1. **One chain, one run** — enrichment + verification + a complete message together (most tools give you only data, or only text). 2. **Groundedness / anti-hallucination** — every message ships with the single fact it is grounded on; fabricated personalization is flagged deterministically (no silent "Nobel-prize" hallucinations). 3. **Send-Readiness gate** — every lead gets a `Send / Verify / Skip` verdict: no blind sending → bounce + domain-reputation protection. 4. **Multilingual + anti-slop** — clean, cliché-free copy. **Pick the output language** (English / Türkçe / Deutsch / Español / Français) or use **Auto** to detect it per lead from the domain's country suffix (`.com.tr` → Turkish, `.de` → German, `.fr` → French …). Wrong-language outreach kills conversion — this fixes it. 5. **ICP qualification gate** — define your ideal customer (industry / country / keywords); leads that don't fit are **filtered out before the paid step**. You don't pay to process junk leads. 6. **Multi-touch follow-up sequence** — instead of a single email, generate a 2–4 touch follow-up sequence (most replies come from follow-ups), produced in a single LLM call. 7. **Cost-preview gate** — run with `onayliLeadSayisi = 0` first: the actor reports how many leads it found and the estimated events/cost **without processing or charging**. Approve, then run again. ### Input | Field | Description | |---|---| | `leads` | The lead list — any of `{company, website, name, title, email, industry, size, country}`. A scraper dataset can be connected directly. | | `enrichFields` | Which firmographic fields to fill when missing (email is verify-only, **never fabricated**). | | `outreachTone` | Message tone (friendly-professional / formal / direct / consultative / warm). | | `outreachTouches` | 1 = single email; 2–4 = multi-touch follow-up sequence. | | `senderOffer` | Your value proposition (appears in the message). | | `language` | Output language: English / Türkçe / Deutsch / Español / Français, or **Auto** (detect from domain). | | `icpSectors` / `icpCountries` / `icpKeywords` / `icpMinScore` | (Optional) ideal-customer profile; leads below the threshold are filtered out for free. | | `model` | (Advanced) LLM model — the default is fast and economical. | | `onayliLeadSayisi` | `0` = preview (count + cost, no charge); `N` = process the first N qualified leads. | ### Output Delivered in two layers: - **Dataset (table) — one row per lead, sorted by priority.** Columns: `Priority` · `Fit` · `Company` · `Person` · `Title` · `Industry` · `Email` · `Deliverability` · `Language` · `Message Subject` · `Sequence` · `Basis` · `Decision` · `Reason`. Scan, sort, filter, and export directly. Leads removed by the ICP gate appear last with a `Filter out` decision (full transparency). - **Full data on each row:** the enriched fields plus `email_verification` (`deliverability` / `score` / `reason`), `outreach_message` (touch 1), `outreach_sequence` (all touches when `outreachTouches > 1`), `groundedness`, `send_readiness`, and `personalization_facts`. - **Run summary (last record):** `verdict_distribution` (`send` / `verify` / `skip`), `total_to_send`, and a priority-ranked `contact_first` list — your "where do I start" answer. ### How to use 1. Collect leads with a scraper (Maps / Leads Finder), or paste your own list. 2. Connect the output to this actor as `leads`. 3. Set tone, language, and (optionally) your ICP. Run once with `onayliLeadSayisi = 0` to preview the count and cost. 4. Approve by setting `onayliLeadSayisi`, run again, and grab the prioritized decision table from the Dataset tab. ### Data & compliance Only **publicly available business data** (business email, company industry, etc.) is processed. No private/personal data is created, and **emails are never fabricated**. ### Pricing (Pay-Per-Event) You only pay for what you use — no monthly subscription. Three events: - **`actor-start`** — one charge per run (fixed platform/orchestration cost). - **`lead-enriched`** — charged once per qualified lead that is processed (one enrichment pass). - **`message-generated`** — charged once per lead for the generated outreach message/sequence. Leads filtered out by the ICP gate are **never charged**. Run with `onayliLeadSayisi = 0` first to see the exact estimated event counts before spending anything. # Actor input Schema ## `leads` (type: `array`): The companies/people to enrich. Any of {company, website, name, title, email, industry, size, country} is enough. A Maps/Leads Finder scraper's dataset output can be connected DIRECTLY. ## `enrichFields` (type: `array`): Firmographic fields to fill when missing. (email is NEVER fabricated by the LLM — it only comes from the input and is verified; bounce/reputation protection.) ## `outreachTone` (type: `string`): Tone of the generated message. ## `outreachTouches` (type: `integer`): 1 = a single cold email (default). 2-4 = a multi-touch follow-up sequence (first email + polite follow-ups) — most replies come from follow-ups. Generated in a single LLM call (cost ~the same, value higher). ## `senderOffer` (type: `string`): A short value proposition to include in the message (what you sell / what you provide). If empty, the message stays generic. ## `language` (type: `string`): Language of the enrichment and message output. If 'Auto' is selected, the language is chosen per lead from the domain's country suffix (e.g. .com.tr -> Turkish, .de -> German); an unknown suffix (.com/.io) falls back to English. ## `icpSectors` (type: `array`): Ideal-customer industries. If filled, leads whose industry does not match are FILTERED OUT and never enter the paid step. e.g. ['software', 'logistics']. ## `icpCountries` (type: `array`): Ideal-customer countries/regions. e.g. ['Turkey', 'Germany']. ## `icpKeywords` (type: `array`): Signals searched in the company name / website / industry / title text. e.g. ['e-commerce', 'SaaS', 'export']. ## `icpMinScore` (type: `integer`): Leads with a fit score BELOW this threshold are FILTERED OUT and never enter the paid enrichment/message step (no payment for junk leads). 0 = ICP gate off (all leads processed, backward compatible). Suggested: 50. ## `model` (type: `string`): LLM model. The default is cheap and fast; pick a stronger model for deeper messaging. ## `onayliLeadSayisi` (type: `integer`): 0 = PREVIEW: the actor only reports how many leads there are and the estimated events/cost, WITHOUT processing (no charge). After reviewing and approving, set this number (e.g. the number of leads found) and run again -> the first N leads are processed. User approval against unexpected bills. ## Actor input object example ```json { "leads": [ { "company": "Acme Software", "website": "acme.com", "name": "Jane Miller", "title": "Marketing Director", "email": "jane.miller@acme.com" }, { "company": "Beta Logistics", "website": "betalogistics.com", "name": "Tom Reed", "title": "Operations Manager", "email": "tom@betalogistics.com" } ], "enrichFields": [ "email", "industry", "size", "country" ], "outreachTone": "samimi-profesyonel", "outreachTouches": 1, "senderOffer": "", "language": "English", "icpSectors": [], "icpCountries": [], "icpKeywords": [], "icpMinScore": 0, "model": "claude-haiku-4-5-20251001", "onayliLeadSayisi": 0 } ```` # 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 = { "leads": [ { "company": "Acme Software", "website": "acme.com", "name": "Jane Miller", "title": "Marketing Director", "email": "jane.miller@acme.com" }, { "company": "Beta Logistics", "website": "betalogistics.com", "name": "Tom Reed", "title": "Operations Manager", "email": "tom@betalogistics.com" } ] }; // Run the Actor and wait for it to finish const run = await client.actor("enezli/ai-lead-enricher-personalizer").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 = { "leads": [ { "company": "Acme Software", "website": "acme.com", "name": "Jane Miller", "title": "Marketing Director", "email": "jane.miller@acme.com", }, { "company": "Beta Logistics", "website": "betalogistics.com", "name": "Tom Reed", "title": "Operations Manager", "email": "tom@betalogistics.com", }, ] } # Run the Actor and wait for it to finish run = client.actor("enezli/ai-lead-enricher-personalizer").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 '{ "leads": [ { "company": "Acme Software", "website": "acme.com", "name": "Jane Miller", "title": "Marketing Director", "email": "jane.miller@acme.com" }, { "company": "Beta Logistics", "website": "betalogistics.com", "name": "Tom Reed", "title": "Operations Manager", "email": "tom@betalogistics.com" } ] }' | apify call enezli/ai-lead-enricher-personalizer --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=enezli/ai-lead-enricher-personalizer", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AI Lead Enricher & Personalizer", "description": "Lead enrichment with email verification and AI-written outreach. Cleans your lead list, verifies each email, and generates a send-ready personalized message per lead, each grounded in a real fact with a send-readiness score. Stop guessing which leads are worth contacting.", "version": "0.1", "x-build-id": "gOFgDOzWbW8UhU1DJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/enezli~ai-lead-enricher-personalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-enezli-ai-lead-enricher-personalizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/enezli~ai-lead-enricher-personalizer/runs": { "post": { "operationId": "runs-sync-enezli-ai-lead-enricher-personalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/enezli~ai-lead-enricher-personalizer/run-sync": { "post": { "operationId": "run-sync-enezli-ai-lead-enricher-personalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "leads" ], "properties": { "leads": { "title": "Lead list", "type": "array", "description": "The companies/people to enrich. Any of {company, website, name, title, email, industry, size, country} is enough. A Maps/Leads Finder scraper's dataset output can be connected DIRECTLY." }, "enrichFields": { "title": "Fields to enrich", "type": "array", "description": "Firmographic fields to fill when missing. (email is NEVER fabricated by the LLM — it only comes from the input and is verified; bounce/reputation protection.)", "items": { "type": "string", "enum": [ "email", "industry", "size", "country" ], "enumTitles": [ "Email (verify only)", "Industry", "Company size", "Country/region" ] }, "default": [ "email", "industry", "size", "country" ] }, "outreachTone": { "title": "Outreach tone", "enum": [ "samimi-profesyonel", "resmi", "doğrudan-net", "danışman", "sıcak-arkadaşça" ], "type": "string", "description": "Tone of the generated message.", "default": "samimi-profesyonel" }, "outreachTouches": { "title": "Number of touches (follow-up sequence)", "minimum": 1, "maximum": 4, "type": "integer", "description": "1 = a single cold email (default). 2-4 = a multi-touch follow-up sequence (first email + polite follow-ups) — most replies come from follow-ups. Generated in a single LLM call (cost ~the same, value higher).", "default": 1 }, "senderOffer": { "title": "Your offer / value proposition", "type": "string", "description": "A short value proposition to include in the message (what you sell / what you provide). If empty, the message stays generic.", "default": "" }, "language": { "title": "Output language", "enum": [ "auto", "Türkçe", "English", "Deutsch", "Español", "Français" ], "type": "string", "description": "Language of the enrichment and message output. If 'Auto' is selected, the language is chosen per lead from the domain's country suffix (e.g. .com.tr -> Turkish, .de -> German); an unknown suffix (.com/.io) falls back to English.", "default": "English" }, "icpSectors": { "title": "ICP — Target industries (optional)", "type": "array", "description": "Ideal-customer industries. If filled, leads whose industry does not match are FILTERED OUT and never enter the paid step. e.g. ['software', 'logistics'].", "default": [], "items": { "type": "string" } }, "icpCountries": { "title": "ICP — Target countries/regions (optional)", "type": "array", "description": "Ideal-customer countries/regions. e.g. ['Turkey', 'Germany'].", "default": [], "items": { "type": "string" } }, "icpKeywords": { "title": "ICP — Keywords (optional)", "type": "array", "description": "Signals searched in the company name / website / industry / title text. e.g. ['e-commerce', 'SaaS', 'export'].", "default": [], "items": { "type": "string" } }, "icpMinScore": { "title": "ICP threshold (0 = off)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Leads with a fit score BELOW this threshold are FILTERED OUT and never enter the paid enrichment/message step (no payment for junk leads). 0 = ICP gate off (all leads processed, backward compatible). Suggested: 50.", "default": 0 }, "model": { "title": "Model (advanced)", "enum": [ "claude-haiku-4-5-20251001", "claude-sonnet-4-6" ], "type": "string", "description": "LLM model. The default is cheap and fast; pick a stronger model for deeper messaging.", "default": "claude-haiku-4-5-20251001" }, "onayliLeadSayisi": { "title": "Approved lead count (cost approval)", "minimum": 0, "type": "integer", "description": "0 = PREVIEW: the actor only reports how many leads there are and the estimated events/cost, WITHOUT processing (no charge). After reviewing and approving, set this number (e.g. the number of leads found) and run again -> the first N leads are processed. User approval against unexpected bills.", "default": 0 } } }, "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 } } } } } } } } } } ```