EcoMind AIDemo build · fictional business, simulated data

Ask 200 documents a question. Get the page it came from.

An enterprise knowledge assistant where every streamed answer cites its source — and clicking the citation lands on the exact highlighted passage in the original PDF.

Enterprise RAGStreaming answersSource viewerIngestion pipelineSelf-hosted LLM configReact + TypeScript

Build something like this Live demo — Assistant

Live demos are password-gated — request access via WhatsApp, takes a minute.

EcoMind source viewer with highlighted passage — The moment that sells it: the cited passage, highlighted on the original page.

The challenge

Enterprise buyers don’t fear wrong answers as much as unverifiable ones. An internal assistant that can’t show its page is a liability in HR and safety contexts.

Knowledge-ops teams also need the unglamorous half: what’s indexed, what failed, what a re-index costs — visible, not buried in logs.

The solution — three decisions

01

The page is the proof

The source viewer renders a document page — serif, justified, footered — with the cited passage in marker yellow. Answer → page → highlight is the whole trust story.

02

Streaming is non-negotiable

Answers render token by token. Instant text reads as canned; a stream reads as a live model at work.

03

Ops get a real surface

Library, ingestion jobs, and retrieval settings (top-K, thresholds, reranker, llama-3.3-70b) are first-class screens — because the buyer here is the team that runs it.

How it works

In

Company PDFsHR, ops, specs, safety

Nightly syncsSharePoint + Drive drops

EcoMind pipeline

Chunk + embed11,857 chunks · e5-large-v2

Retriever + rerankertop-K, thresholded

Generationself-hosted llama-3.3-70b

Out

Streaming answersnumbered citations

Source viewerhighlighted passage, real page

The demo implements this shape end to end with a simulated service layer — the “extend for production” section below lists what swaps in for live deployment.

Product tour

Streamed grounded answer with sources — A policy question answered with inline citations and a source list underneath.

Ingestion pipeline dashboard — Documents → chunks → embeddings, with a week of ingest jobs. The 11,857-chunk figure is a sum, not a slogan.

Document library — 200 documents across HR, ops, specs, safety, IT, and finance — with processing states.

What the demo shows

Three scripted question flows across HR, maintenance, and PTO topics
Ten past conversations that reload their grounded answers instantly
A workspace settings page with working retrieval controls
Dense enterprise UI: 13px body, 36px rows, icon-rail shell

Under the hood

Cited passages are stored per document+page; the viewer renders them into generated page context so every citation resolves
Non-cited pages get deterministic filler prose per category — browsing never breaks the illusion
Chunk totals are computed from the doc list; library, KPIs, and jobs can’t drift apart
Icon-rail shell (the portfolio’s sixth distinct app shell) keeps 200-doc density navigable

Built as a demonstration — on purpose.

Meridian Corp is fictional and labeled as a demo on every screen. Nothing here is presented as client work: no client names, no outcome metrics, no testimonials. The proof is the running product — open the live demo above (password on request) and check every claim.

What I’d extend for production

Real embedding + retrieval over the corpus (e5/bge + pgvector)
Chunk-to-page-coordinate mapping for true PDF highlighting
Per-space permissions so answers respect document ACLs