You will get AI Workflow Automation with LLM Integrations
Project details
I automate the manual process that's eating your team's hours — form or trigger -> AI enrichment -> your tools (Sheets, Notion, HubSpot, CRM, Slack).
Typical flows:
• Lead form -> AI classification (intent, urgency, priority) -> CRM + auto-reply draft.
• Document / email -> AI extraction to structured JSON -> Sheets / Notion.
• Ticket inbox -> AI triage + routing.
• Scheduled job -> AI summary to Slack / email.
Stack: LLM orchestration (direct SDK, LangGraph, or LangChain — per job), OpenAI / Claude / Groq, Node.js or Python. Integrates with Sheets, Notion, HubSpot, Airtable, Gmail, n8n, Zapier.
Live demo: autoleads-six.vercel.app — AI lead classification dashboard, structured JSON extraction, priority scoring, Spanish auto-reply drafts. Source on my GitHub.
Included: typed code (TS / Python), Zod/Pydantic schemas, retries + logging, error alerting (Advanced), monitoring (Advanced), docs + handover video, 30 days async support.
~2.5y backend + AI dev at a LATAM B2B SaaS (NDA). Native Spanish. Written English — async-first; voice optional for kickoff or demo. GMT-3, US business hours overlap.
Send me 2-3 sentences on your process + tool list.
Typical flows:
• Lead form -> AI classification (intent, urgency, priority) -> CRM + auto-reply draft.
• Document / email -> AI extraction to structured JSON -> Sheets / Notion.
• Ticket inbox -> AI triage + routing.
• Scheduled job -> AI summary to Slack / email.
Stack: LLM orchestration (direct SDK, LangGraph, or LangChain — per job), OpenAI / Claude / Groq, Node.js or Python. Integrates with Sheets, Notion, HubSpot, Airtable, Gmail, n8n, Zapier.
Live demo: autoleads-six.vercel.app — AI lead classification dashboard, structured JSON extraction, priority scoring, Spanish auto-reply drafts. Source on my GitHub.
Included: typed code (TS / Python), Zod/Pydantic schemas, retries + logging, error alerting (Advanced), monitoring (Advanced), docs + handover video, 30 days async support.
~2.5y backend + AI dev at a LATAM B2B SaaS (NDA). Native Spanish. Written English — async-first; voice optional for kickoff or demo. GMT-3, US business hours overlap.
Send me 2-3 sentences on your process + tool list.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
AI-Enhanced Classification, Natural Language Generation, Natural Language Understanding, Sentiment Analysis, Text RecognitionAI Development Language
PythonAI Models
ChatGPT, GPT-3, GPT-4, LLaMAWhat's included
| Service Tiers |
Starter
$150
|
Standard
$500
|
Advanced
$1,000
|
|---|---|---|---|
| Delivery Time | 5 days | 7 days | 10 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | ||
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | |
Model Deployment | - | ||
Model Documentation | - | ||
Model Monitoring | - | - | |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | |||
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | |||
Source Code |
Optional add-ons
You can add these on the next page.
Additional Revision
+$25
Additional Integration (Notion / HubSpot / Airtable beyond scope)
(+ 3 Days)
+$150
Monitoring Dashboard (add to Starter or Standard)
(+ 5 Days)
+$250
30 Days Extended Support
+$150Frequently asked questions
About Federico
Backend Engineer | NestJS, LangChain, RAG, WhatsApp AI Chatbots
Campana, Argentina - 12:25 pm local time
Here's what I build:
• AI chatbots & virtual assistants — WhatsApp Business, web widgets, custom channels. Intent detection, FAQ + human handoff, conversation logs, admin dashboards.
• AI process automations — lead enrichment, document parsing, CRM sync. LangChain/LangGraph orchestration. Integrations with Sheets, Notion, HubSpot, n8n, Zapier.
• AI backend MVPs — NestJS REST APIs with JWT auth, Postgres + Drizzle, Zod validation, Swagger docs, Docker, CI. 3–4 weeks from idea to deployed product.
Tech stack I work with daily:
• Backend: NestJS, Node.js, Express, TypeScript, Python (FastAPI / Flask).
• AI/LLM: LangChain, LangGraph, RAG + vector DBs (Pinecone), OpenAI, Claude, Groq/Llama. Prompt engineering, structured output (Zod / Pydantic).
• Databases: PostgreSQL + Drizzle/Prisma, MongoDB, MySQL, DynamoDB.
• DevOps: Docker, AWS (EC2/Lambda/S3), Vercel, Railway, Serverless.
• Testing: Vitest, Jest, Supertest, pytest.
Live proof (code + deployed):
• ChatPyME — WhatsApp-style AI assistant with intent routing + human handoff.
• AutoLeads — AI lead-classification dashboard (structured extraction, priority scoring).
• NestAI-Starter — production-grade NestJS + AI backend template with auth, tests, Docker, Swagger.
How I work:
• Fixed-scope / fixed-price for productized deliverables; hourly for open-ended work.
• Weekly demos, code in your repo from day one.
• Typed code (TS / Python), tested, deployed via Docker / Vercel / Railway.
• Docs handover + 30 days post-launch support.
• Spanish native, English fluent. Based in Argentina — GMT-3 overlaps US business hours end-to-end.
If you have a clear brief — send it, I reply within a few hours. If you're still scoping, I offer a free 20-min discovery call to help shape it.
Steps for completing your project
After purchasing the project, send requirements so Federico can start the project.
Delivery time starts when Federico receives requirements from you.
Federico works on your project following the steps below.
Revisions may occur after the delivery date.
Scoped discovery brief (async-first)
You answer 6-8 scoped questions in Upwork chat or share a short Loom walkthrough of your process. I reply with a written scope doc and timeline. Voice kickoff call optional.
Design the flow + prompt engineering
I sketch the pipeline (input -> LLM -> output/integration), draft the system prompt, and define the structured JSON schema. You review before I write a line of code.