Projects

Fifteen systems, built in dependency order.

Each phase reuses the infrastructure — auth, eval, observability, deploy — established in the phase before it. This is a build order, not a list.

1 in progress · 14 planned

Core foundations(4)

RAG, agentic orchestration, document intelligence, MCP — the infrastructure every later project reuses.

  1. 01

    RAG Starter Kit

    In progress

    SMBs (law firms, clinics, agencies) have policies, SOPs, and past client emails scattered across drives with no searchable interface.

    Next.js chat UI
    FastAPI
    LangGraph retrieval node
    pgvector similarity search
    LLM synthesis + citations

    Every call traced in Langfuse — a DeepEval CI check fails the build if retrieval precision drops below threshold.

    • FastAPI
    • Next.js
    • Postgres + pgvector
    • LangGraph
    • LlamaIndex
    RAG
    How it works
    1. 01

      Ingest

      Documents (PDFs, DOCX, email exports) go through the FastAPI backend, get chunked with LlamaIndex, embedded with OpenAI's text-embedding-3-small, and stored in Postgres — each chunk's embedding lives in a pgvector Vector(1536) column next to the source document and page number it came from.

    2. 02

      Ask

      The Next.js chat UI sends the question to FastAPI, which hands it to a LangGraph retrieval node — a small state graph rather than a single hard-coded function, so the retrieval logic can grow branches later without a rewrite.

    3. 03

      Retrieve

      The node embeds the incoming question and runs a similarity search against pgvector to pull back the chunks most relevant to it.

    4. 04

      Synthesize

      Those chunks go to the LLM with instructions to answer only from what was retrieved and attach a citation — source document and page — to every claim, so nothing in the answer is unsourced.

    5. 05

      Trace

      Every step of that call — retrieval, synthesis, latency, token counts — is logged to Langfuse, so any single run can be pulled up and inspected after the fact.

    6. 06

      Gate

      Before any change ships, a DeepEval golden set of 20-30 real question/answer pairs runs against the retrieval pipeline in CI. If precision drops below threshold, the build fails and the deploy is blocked — the eval isn't a report, it's a gate.

  2. 02

    Multi-Tenant Customer Support Agent

    Planned

    SaaS companies are drowning in repetitive tickets and need escalation logic they can trust.

    Ticket webhook
    Classify
    Retrieve
    Draft reply
    Confidence gate
    Auto-resolveorEscalate to human

    CRM write-back and a per-tenant Langfuse trace on every ticket.

    • LangGraph
    • Zendesk/Intercom API
    • Stripe
    • multi-tenant Postgres
    Agent
  3. 03

    Document Intelligence Pipeline

    Planned

    Legal, insurance, and real-estate teams manually re-read contracts for clause risk.

    Upload
    Parse (native / OCR fallback)
    Chunk vs. clause schema
    Risk-flag scoring
    Reviewer UI

    Every flag links back to its exact page in the source document.

    • unstructured.io / LlamaParse
    • OCR fallback
    • Pydantic-constrained generation
    Extraction
  4. 04

    MCP Server for Internal Data Access

    Planned

    Every agent needs to query internal systems (CRM, database, ticketing) but hand-rolled tool schemas don't compose.

    Claude Desktop / Cursor
    MCP server (auth-scoped)
    list_customers · get_order_history · flag_risk_account
    Internal Postgres / CRM

    Published to the MCP registry — callable by any client, including the agents from projects 02 and 05.

    • MCP Python/TS SDK
    • OAuth-scoped access control
    MCP
Agentic & multi-system(3)

Multi-agent orchestration, browser automation, real-time voice.

  1. 05

    Multi-Agent Workflow Automation

    Planned

    Sales/ops teams manually qualify inbound leads and draft outreach.

    CrewAI · LangGraph · enrichment APIs

    Multi-agent
  2. 06

    Browser Agent for Competitive Monitoring

    Planned

    Businesses want to track competitor pricing/inventory changes without a human checking daily.

    Playwright · browser-use-style agent loop · cron · diff-based change detection

    Browser agent
  3. 07

    Voice AI Receptionist

    Planned

    Local service businesses (clinics, salons, restaurants) miss calls constantly and can't afford 24/7 staff.

    Whisper / streaming STT · ElevenLabs · Twilio · LangGraph booking flow

    Voice
Deep technical differentiation(4)

Fine-tuning, guardrails, graph retrieval, classical ML — proof this goes past API wrapping.

  1. 08

    Fine-Tuned Local Model + vLLM Deployment

    Planned

    API costs and latency don't scale for a narrow, high-volume classification or style-matching task.

    PyTorch · LoRA / PEFT · vLLM · Ollama

    Fine-tuning
  2. 09

    Open-Source Eval & Guardrails Toolkit

    Planned

    Eval and injection-defense get rebuilt ad hoc inside every LLM project instead of shipped once as a reusable, testable layer.

    Python package · PyPI · GitHub Actions

    OSS
  3. 10

    GraphRAG for Relationship Intelligence

    Planned

    Some questions aren't 'find the similar chunk,' they're 'how are these entities connected' — vector search alone fails here.

    Neo4j · entity/relationship extraction · hybrid retrieval

    GraphRAG
  4. 11

    Recommendation & Personalization Engine

    Planned

    Personalized ranking rarely needs an LLM in the loop — embeddings and collaborative filtering are usually faster and cheaper to serve.

    scikit-learn · embedding-based similarity · Redis

    Classical ML
Operational maturity & monetization(4)

Orchestration across everything above, a shipped product, an audit layer, a public asset.

  1. 12

    MLOps Orchestration Layer

    Planned

    All prior projects need a real retraining/monitoring loop, not manual reruns.

    Airflow / Prefect · MLflow · Terraform · OpenTelemetry

    MLOps
  2. 13

    Monetized Micro-SaaS (Support Agent, Productized)

    Planned

    Take the multi-tenant support agent and turn it into a product with paying customers, not a demo.

    Stripe billing · marketing landing page · self-serve onboarding

    SaaS
  3. 14

    Enterprise Security/Compliance Layer for Agents

    Planned

    Enterprises won't deploy an agent that can't prove it's safe.

    structured audit logging · RBAC middleware · approval-queue UI

    Security
  4. 15

    Public LLM/Vector-DB Cost & Latency Benchmark Dashboard

    Planned

    Nobody has a trustworthy, independent, continuously-updated comparison of LLM providers and vector DBs on a fixed task.

    Airflow · Next.js · vLLM · pgvector / Qdrant

    Benchmark