graphs-and-jev
Accenture thought piece and site on stack migration with Google Cloud, placing Jev as the System 1 layer that routes, classifies and gates.
This repository is mostly documentation or write-up rather than runnable code.
Overview
graphs-and-jev hosts an Accenture thought piece, served as a live site, on accelerating stack migration and modernisation with Google Cloud. It presents five delivery pillars: the existing stack, a governed MCP Tool Shed, System 1 with Jev, ADK with Gemini and connected context, and measured outcomes. The README is explicit that it is not a product, service offer or pricing page.
In the planned reference architecture, Jev is the System 1 reflex layer: a discriminative model that routes, classifies and gates bounded decisions, called from AlloyDB AI via TypeSafe's hosted API rather than embedded in the database, while ADK with Gemini handles System 2 orchestration. The live service is a single Rust process on Cloud Run serving the publication; its demonstrations use deterministic Rust rules or browser fixtures and do not actually call MCP servers, AlloyDB AI, Gemini or Jev.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Route, classify or gate a bounded migration decision (planned architecture)(inferred) | — |
How it works
- Existing systems land documents in Cloud Storage (planned)
- MCP Tool Shed exposes governed tools
- Jev routes, classifies and gates bounded decisions
- ADK with Gemini orchestrates complex reasoning
Strengths
- Clear architectural placement of a decision model
- Honest about what the demo does and does not run
Caveats
- Thought piece; demos do not call Jev
- Not a product
Getting started
Open the live site linked from the README.At a glance
- Type
- MCP server
- Status
- discussion
- Language
- Rust
- Runtime
- Cloud Run static site + API
- Has code
- yes
Use cases and integrations
How curated lists describe it
The MCP Tool Shed: an Accenture thought piece on agentic migration and…
wh000wh000/awesome-jev-live
Frequently asked questions
Is this a product?
No, it is an Accenture thought piece.
Does the demo call Jev?
No, demonstrations use deterministic rules or fixtures.
Where does Jev fit in the architecture?
As a System 1 layer called from AlloyDB AI to route, classify and gate decisions.
Related projects
Claude skill that gives a ten-line gut-check on whether Jev could help with what you are building, citing tested patterns.
Agent skillbetaMarkdownThirty worked Jev uses in ten levels, from a smart if statement to a pi coding agent that writes its own Jev questions.
ProjectbetaTypeScriptAgent skill that makes a coding agent try Jev first for bounded judgments like classify, rank or gate, and log each attempt.
Agent skillbetaPythonIndependent Markdown reference on the Jev API, patterns and limits, written for engineers and coding assistants to build from.
ServiceCommunity directory of Jev apps, resources and runnable offline examples, with a guide skill and a searchable JevList web UI.
ArticleproductionTypeSafe's official cookbook for a two-stage skill-suggestion workflow that selects a skill and can reject the shortlist.
Articleproduction