Overview / Narrative Journeys

End to end · four stories

Narrative journeys — AI in action, end to end.

The stack is not a diagram. It is four threads of work that used to take days, or used to not happen at all. Each story follows a single input all the way to a real output — no hand-waving between the steps.

Asset Ops Hermes PM GBrain Claude Code four single threads

Four threads

Trigger, AI, outcome.

Each journey is the same shape: something happens, AI does the work, a real outcome lands. Hover any node to trace its thread.

Trigger AI does the work Outcome

Shoot → asset

Supplier shoot Gemini analysis Directus DAM

Meeting → task

Meeting ends Hermes Fizzy card

Question → answer

A question GBrain Grounded answer

Idea → app

An idea Claude Code Live on huxapps.com

Journey 01 · Asset Ops

From a supplier shoot to a shoppable asset.

A supplier sends over a folder of photos and videos — 80 files, zero metadata, no naming convention. In any previous reality this lands with the marketing team as a manual cataloguing project. Today it lands in the pipeline.

01 · ingest

Raw media lands in Drive

Photos and videos arrive in a shared Google Drive folder from the supplier — untagged, unordered, mixed quality.

Google Drive
02 · discover

Deduplication to real subjects

Asset Ops scans the folder and collapses variants to canonical subjects — the same product shot from three angles counts once, not three times.

read-only
03 · analyse

Gemini writes the full record

Each image gets 14 structured fields: subject, tags, alt-text, suggested uses, colour palette. Videos get a timestamped shot list, reusable segments, and quotable moments.

Gemini vision
04 · publish

Into the DAM with originals preserved

Originals go to Cloudflare R2, video goes to Cloudflare Stream, and typed metadata rows land in Directus — all linked, all searchable.

writes
05 · ready

Marketing searches a live library

The team opens the DAM and finds every asset already described, tagged, and labelled with where it can be used — from day one.

Directus DAM
The payoff. Weeks of manual cataloguing becomes hours. Nothing is untagged. Nothing sits in a shared drive nobody can navigate. The asset library is searchable before the supplier's invoice arrives.

Journey 02 · Hermes huxberrypm

From a meeting to tracked tasks.

A Google Meet ends. In a previous world, the action items live in a bullet-point document that nobody checks, assigned to nobody, due never. In this one, the meeting note is already being read.

01 · capture

Meet wraps with auto-notes

Gemini meeting summary is written automatically — decisions, action items, attendee ledgers. No manual note-taking required.

Google Meet
02 · read

Hermes reads the notes hourly

The huxberrypm profile ingests new meeting summaries on a schedule — scanning for anything that looks like a decision or a commitment made to someone.

hourly cron
03 · draft

Task cards drafted from decisions

Each action item becomes a structured task card proposal — title, description, suggested owner, context extracted from the meeting thread.

proposed · not yet real
04 · approve

One-tap review on Telegram

Proposals arrive in Telegram with inline approve/reject buttons. Nothing hits the board without a human tap. Control stays human; friction drops to seconds.

human-in-the-loop
05 · land

Approved cards on the Fizzy board

Approved tasks appear on the Fizzy project board, assigned and dated — ready to be picked up in the next standup.

Fizzy
The payoff. Action items stop dying in meeting notes. Capture is automatic; control stays human. The board reflects what was actually decided — not what someone remembered to add later.

Journey 03 · GBrain

Ask the ERP and CRM in plain English.

Someone needs to know the status of a deal, the current stock position, or what was decided in a call last week. In the old model they wait for a report, or ask the person who knows. In this one, they ask directly.

01 · ask

A plain-English question

"What are the open opportunities in hospitality right now?" — typed in chat, no special syntax, no knowledge of which system holds the answer.

natural language
02 · recall

GBrain answers from its index

Conversational questions — context, history, decisions, definitions — are answered from the 2,000+ pages GBrain has already indexed, with citations back to the source.

semantic + graph
03 · measure

Exact numbers from the warehouse

For anything that needs a precise count or ranking, GBrain queries the Metabase analytics warehouse — sub-second SQL, no waiting on a scheduled report.

Metabase warehouse
04 · verify

Freshest data straight from source

When the warehouse lacks a field or the question needs today's state, GBrain queries the live system directly — Odoo or NetSuite — and grounds the answer there.

Odoo · NetSuite
05 · answer

A grounded, cited response

The answer comes back in plain English, citing which source it came from and at what freshness. Conversation continues — follow-up questions work too.

cited · grounded
The payoff. No SQL. No waiting on a report. No asking the person who happens to know. The business is queryable by anyone, in the language they already speak.

Journey 04 · Claude Code

From an idea to a deployed app.

A business need surfaces — track something, automate something, surface something for customers. In a company without in-house engineers, this used to mean a six-week agency engagement or an indefinite backlog item. Today it means a conversation.

01 · brief

A rough idea in chat

A plain-language description of what's needed — no spec, no wireframes, no ticket. Just the problem and the outcome that would solve it.

natural language
02 · research

Claude Code reads the real systems

Before writing a line, Claude Code reads the codebase, the relevant APIs, and the GBrain wiki context — so the code it writes is grounded in how the systems actually work.

GBrain context
03 · build

Working code, written and tested

Claude Code writes the implementation, iterates on errors, and verifies behaviour — running tests and inspecting output as it goes.

Next.js · TypeScript
04 · verify

Previewed and confirmed in a browser

The running app is opened in a browser preview. Claude Code checks the visual output, clicks through flows, and confirms the behaviour matches the brief before shipping.

browser preview
05 · ship

Live on a huxapps.com subdomain

Deployed to Cloudflare Pages or Vercel. A huxapps.com subdomain is pointed at it. The thing is live. This very site was built and deployed exactly this way.

production
The payoff. A non-engineering company ships real software in a day. The backlog shrinks instead of growing. The person with the idea can see it running before they've finished explaining it.

Keep exploring