Project · Product workflow

AI Content Workflow Platform

A traceable local product workflow that connects source evidence, human decisions, AI output and final delivery.

Content generation was not the real bottleneck

An ambiguous content request can quickly fragment across source files, AI conversations and manual edits. This project turned that work into a local product workflow: preserve the source, let a person choose direction, generate a candidate, then complete human editing and acceptance before delivery.

01Before the productRequests, source evidence and AI output lived in separate places, making decisions difficult to reconstruct.

02After the productEach stage retains its input, decision and output in one traceable chain.

Keep the model inside a human-owned decision system

AI accelerated analysis, candidate generation and implementation. Aaron kept the decisions that determine product scope, evidence quality and final delivery under human control.

Define the problem before the features

Discovery and a Lean PRD narrowed the first product slice and its completion criteria.

Make human decisions explicit

People choose direction, edit the candidate and decide whether the result can be delivered.

Keep every AI run reviewable

Source records, context manifests, job receipts and candidate artifacts remain separate.

Separate build completion from UAT

The browser flow was tested after implementation, including failure states, reload behaviour and navigation.

Accept the Windows product, not the development environment

The final delivery criterion was a launchable local executable.

A traceable path from source to accepted delivery

The workflow gives every stage a defined input and output. When something fails, the team can return to the stage that owns the decision instead of rewriting the entire result.

01Preserve the sourceCreate a source record and raw snapshot before interpretation.

02Choose the directionAI proposes options; a person selects the problem worth solving.

03Generate a candidateThe model works from versioned context and leaves a job receipt.

04Edit deliberatelyA candidate becomes a deliverable only after human revision.

05Accept and recordBrowser UAT and manual publication records close the workflow.

The content product workflow from source intake to accepted delivery — **Product workflow**The system handles repeatable work while people retain direction, editing and delivery decisions.

Traceable lineage from SourceRecord to Manual Publication Record — **Architecture lineage**Source, context, AI jobs, candidate artifacts and authored deliverables remain independently reviewable.

The product was accepted as a bounded local system

Completion required more than a working screen. The core lineage had to run end to end, failure states had to remain visible and the private product had to launch in its Windows delivery form.

Product definition01

The Lean PRD fixed the single-user local scope, non-goals and acceptance criteria.

Integration and UAT02

Core tests, provenance fixtures, Relay tests and the production build passed before browser acceptance.

Windows delivery03

The private product ships as one Windows x64 executable and keeps application traffic on loopback.

Product screen for selecting a content direction — **Direction choice**A person selects the direction before candidate generation.

Product screen showing scheduled content — **Schedule state**Human confirmation remains visible before delivery.

Product screen showing versioned workflow guidance — **Workflow guidance**Channel-specific rules remain centrally managed and versioned.