FIG. 00 — PROFILE

AI that runs the business while no one's watching it.

Sakshi Bhujade — AI Automation Consultant

I build production AI systems, sales research bots, CRM enrichment pipelines, RAG search over your own team's data for founders and ops teams done doing repetitive work by hand. Built on n8n, Make, GPT-4o, and GCP, with validation baked in so nothing breaks silently.

SYS.01 TRIGGER SYS.02 AI AGENT LLM · RAG · TOOLS SYS.03 ACTION FEEDBACK / LOGGED TO DB RESULT

Worked With

FIG. 01 — COMPANIES

About

FIG. 02 — SUMMARY

Most operations teams are running on a patchwork: a CRM nobody trusts, research done manually before every call, follow-ups that fall through when someone's busy. It's not that the work is hard, it's that it's repetitive, and repetitive work is where good people burn out and good data goes stale.

I builds the systems that take that work off someone's desk entirely: AI that researches a lead before the call happens, scores how the call went after, and keeps a searchable memory of every conversation so nothing gets re-explained twice. Production-grade, not proof-of-concept validation layers included, so the system doesn't quietly start failing the week you stop watching it.

I built this kind of system in healthcare robotics,Mass Media, Public Sector, enterprise sales operations, Contractual Projects and freelance client work since 2024.

60–80%Manual work removed per system
30+Production systems shipped
100%Follow-ups drafted for human review — never auto-sent
2024-Building agentic AI in production

Capabilities

FIG. 03 — COMPONENT LEGEND
AI & Reasoning
The part that thinks: understands documents, drafts responses, decides what happens next.
Prompt EngineeringAgentic AIMulti-Agent Systems RAG PipelinesStructured Output ValidationFuzzy Mapping NLPComputer VisionMLOps
Automation & Integration
The part that acts: moves data between the tools you already use, on a schedule or a trigger.
n8nMakeWebhooks & API OrchestrationBatch Processing / Rate Limiting
Cloud & Infrastructure
The part that doesn't go down: production hosting, storage, and deployment.
Google Cloud (Compute, Storage, Cloud Run)Vertex AI OpenAI APIAWS (EC2, S3, Lightsail)
Engineering
The part underneath: the code and databases that keep it maintainable.
PythonJavaC / C++SQLJavaScriptHTML/CSS MySQLVector DatabasesDockerGitLinux

Systems Built

FIG. 04 — CASE STUDIES
Freelance · 2025 – Present

Sales Intelligence System

Client: Growth Pilot Partners
Problem

Reps walked into meetings without full context on the person across the table, and most of what happened in the call was forgotten by the next one.

Solution

A four-part n8n system. Before every meeting it pulls email history, a scraped LinkedIn summary, and live company research into one briefing with talking points, red flags, and discovery questions. After the call, it scores performance across four dimensions, drafts (but never auto-sends) a follow-up email, and embeds the transcript so every past conversation becomes searchable. A Telegram bot answers plain-English questions about any past meeting, cited to the exact call and date.

Impact

Every meeting is now researched before it happens and searchable after no re-explaining a client's history from memory.

01 Pre-call brief (email + LinkedIn + company research)
02 Post-call scoring + Gmail draft follow-up
03 Transcript → vector embedding → semantic search
04 Telegram bot Q&A over past meetings
05 LinkedIn intake form closes the data gap automatically
Stack
n8nSupabaseGPT-4oOpenAI Embeddings ApifyApollo.ioScrapingDogGmail API Telegram Bot APIGoogle Forms
DeltaVix Global · 06/2024 – 01/2026

CRM Enrichment & Multi-Platform Content Engine

Problem

HubSpot contacts arrived incomplete and inconsistent, with no reliable way to enrich them at scale.

Built

An AI research → normalization → CRM update pipeline with fuzzy mapping and enforced JSON validation, paired with a Make-based content engine that routes, detects language and generates platform-specific content automatically. plus Gemini-powered agents handling customer support and lead qualification.

Stack
n8nMakeGeminiHubSpotPython
Caredose Health-Tech · 01/2024 – 07/2024

GarudCV — Medicine Detection

Problem

Blocked medicine slots on a packaging line went undetected until downstream.

Built

Real-time computer-vision QA that halts the line via HMI the moment a blockage appears. Deployed on Raspberry Pi and Odroid.

Stack
OpenCVGCPFlaskRaspberry Pi
Caredose Health-Tech · 01/2024 – 07/2024

AI-Powered Pick & Place Arm

Problem

Robotic arms needed precise, real-time coordinates for pharmaceutical-grade handling.

Built

A coordinate-mapping model driving accurate, real-time pick-and-place in production.

Stack
Computer VisionPythonMLOps

Experience

FIG. 05 — TIMELINE
2025 — PRESENT
Freelance AI Automation Consultant
Independent
  • Shipped a four-part sales intelligence system that eliminated manual pre- and post-call research for a client, cutting related admin work by up to 80%.
  • Integrated LLMs and AI agents into CRMs, messaging APIs, and data enrichment services across multiple client engagements.
06/2024 — 01/2026
Gen-AI Consultant, DeltaVix Global
Full-time
  • Built and shipped agentic AI systems for customer support, lead qualification, and content generation, cutting manual workload up to 60% via n8n/Python automation.
  • Implemented fuzzy mapping, validation layers, and structured JSON enforcement so AI outputs stayed reliable in production.
01/2024 — 07/2024
AI/ML Developer, Caredose Health-Tech Pvt. Ltd.
Full-time
  • Shipped two production computer-vision systems, real-time defect detection and robotic pick-and-place, to edge hardware in a live pharmaceutical packaging environment.

How I Work

FIG. 06 — PROCESS
01

Discovery

A short call to find the highest-leverage manual process worth automating first.

02

Map the workflow

A walkthrough of exactly how the process runs today: tools, handoffs, edge cases.

03

Prototype

A working version built before full build-out, so we validate the approach early.

04

Build

Production build with validation layers and error handling from day one.

05

Deploy

Shipped into the tools you already run on, no new system to learn.

06

Refine

A tightening pass once real usage surfaces the edge cases a spec can't predict.

Frequently Asked

FIG. 07 — FAQ
01How long does a project typically take?
Depends on scope, a discovery call usually narrows it down in the first conversation.
02How much does this cost?
Varies by system complexity; you'll get a real number after we scope it together, not before.
03Do you work with early-stage startups?
Yes, infact most freelance work so far has been with small, fast-moving teams.
04Can you integrate with our existing CRM?
Yes, that's the core of most systems built to date, including a HubSpot enrichment pipeline.
05What if the AI gives a wrong answer?
Every system includes validation and structured-output checks with multiple testing layers, so a bad output gets processed rather than shipped.
06Is my data safe?
Systems are built with secure API practices and data validation at every step.
7What do you build on?
Mainly n8n, Make, Vertex Ai and other mainstream platforms.
8Do you offer ongoing support?
Yes, on a scope agreed upfront.
9How do we start?
Book a call, the first step is finding the one process worth automating first.

Education & Certificates

FIG. 08 — CREDENTIALS
04/2020 — 03/2024
B.Tech, Computer Science & Engineering
Yeshwantrao Chavan College of Engineering, Nagpur
Build a Face Recognition Application using Python — AI-For-India Event
GUVI
Google Cloud Practitioner Program
Google Developer Students Club
Prompt-off: Match the Masterpiece
UpGrad