Dev4AiBots · Project Showcase

AI systems that survive real users.

Devraj Gadhvi — AI Engineer. Every project below has a live demo, public source, a story, and proof measured from the build. Nothing here is claimed without evidence.

Live — working deployment you can open Source — public repository Proof — measured evidence from the build Honest — stated limits, not hidden
01

PRAMAAN

Zero-trust RAG · Next.js · pgvector · RBAC

Story: Enterprise RAG leaks — poisoned documents, broken authorization, confident hallucinations. I built a 5-layer security pipeline: ingestion scanner, authorization enforced inside the SQL query before the model sees data, evidence-grounded synthesis, PII shield, and a hash-chained audit log.

5 security layersRBAC in SQLhash-chained audithackathon → production rebuild
02

Semantic Code Search

AST + vector search · hybrid RRF ranking

Story: Keyword search fails when you ask "where do we retry failed payments?". This engine maps natural language to code with dense + sparse + RRF fused ranking, explained per result.

evals/benchmark.tsdocs/evaluation.mdlive /api/query
03

Production RAG System

hybrid retrieval · verified citations · eval gate

Story: Most RAG demos look good once and fall apart on the second question. This one is built to be held accountable: hybrid retrieval (dense + BM25 + RRF), cross-encoder reranking, and every answer chained to verbatim source quotes — unsupported claims return insufficient_evidence. A McNemar eval regression gate fails CI when quality drops.

13 testsMcNemar eval gatehybrid dense + BM25 + RRFDocker + FastAPI
04

AI Automation Platform

n8n · FastAPI · LiteLLM · Postgres RLS

Story: A multi-tenant AI-employee platform: six n8n workflows (support, lead capture, booking, knowledge ingestion) orchestrated by a Master Orchestrator with LiteLLM intent routing. Isolation is enforced in Postgres Row-Level Security, webhooks are idempotent, and a synthetic replay harness lets anyone docker compose up and watch it run — no real API keys required.

6 workflowsRLS multi-tenancyidempotent webhookssynthetic replay harness
05

AI Eval Lab

evals · pass@k · McNemar gate

Story: You can't claim safety without testing it. A regression-gating harness for grounded QA: six rule graders, unbiased pass@k and pass^k, cluster bootstrap CI, and an exact McNemar gate that fails CI on a real drop.

143 testslive CI reportgate verified exit 2
06

AI Employee Platform

agent loop · human gate · RLS · n8n

Story: A sales-ops agent that scores gone-quiet leads with per-signal attribution, drafts the follow-up, then stops for a named human approval written into a hash chain before anything can send — Postgres RLS isolation, AES-256-GCM vault, idempotent webhooks.

209 testslive consolegreen CI
07

MCP PostgreSQL Server

JSON-RPC 2.0 · parameterized SQL

Story: A Model Context Protocol server written against the spec without an SDK — db_query, db_schema, db_tables, db_insert, all with parameterized statements and read-only enforcement on queries. One stdio endpoint that turns any MCP-compatible agent into a safe database assistant.

12 testsno SDK dependencyparameterized SQLread-only enforcement
Experiments
E1

Deep Research Orchestrator

simulated experiments — labeled

Story: Research agents should plan, spend, and stop. This orchestrator grows a search tree under a budget with a fixed seed — deterministic, replayable, honest that experiment metrics are simulated.

metrics simulated — labeled
E2

LLM Finetuning Framework

artifact-lineage pipeline · simulated metrics

Story: A pipeline DAG where the served endpoint records which weights it runs and the model card carries the eval hash — 23 tests, stage metrics labelled as deterministic simulation.

23 testsstage metrics simulated — labeled

Credentials — 16 verified

IBM AI DeveloperIBM RAG & Agentic AIIBM AI Engineering Vanderbilt AI Agent DeveloperVanderbilt Agentic AI in Python Vanderbilt Generative AI AutomationVanderbilt GenAI Software Engineering Vanderbilt Build Anything with AIDeepLearning.AI GenAI for Software Dev UiPath RPAMicrosoft Coding & Automation for Data Analysis Microsoft Intro to Sales & AIGoogle AI Essentials Edureka GenAI for HR WorkflowsJetBrains Build a Game with AI Coding Agent IBM Building AI Agents & Workflows
Honesty contract: no degree claimed · no prior paid employment claimed · every credential verifies · every system states what it proves and what it does not · nothing here is claimed without evidence.
Let's build something real.

hello@dev4aibots.com · github.com/dev4aibots · linkedin.com/in/devraj0770 · Immediate start · Remote worldwide