ShipCheck: Knowledge-Graph Verification Before DeploymentShipCheck: Knowledge-Graph Verification Before Deployment
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Rajan's avatar
Rajan Mishra
• Oct 16
"Can I upgrade our payment service from v2 to v4 tonight?"
Engineers propose production changes like this based on partial mental models. The facts that invalidate the plan are already documented — but scattered across release notes, migration guides, and stale architecture docs.
Standard AI tools fail catastrophically here.
A typical RAG chatbot uses semantic similarity search over raw text chunks. But similarity search has NO concept of: ❌ Relational dependency chains ("v4 requires SDK v3, but production runs SDK v2") ❌ Authority hierarchy ("Release Notes supersede stale architecture docs") ❌ Policy exceptions ("Emergency hotfixes bypass 24h staging soak rules")
To solve this, I built SHIPCHECK: 👉 "Before you ship a change, let the agent try to break your plan."
Instead of treating documentation like an unorganized soup of text embeddings, ShipCheck models production facts as a structured knowledge graph queried with deterministic GROQ graph traversal:
1️⃣ Dependency Traversal: Maps microservice relationships and version constraints deterministically. 2️⃣ Authority Weighting: Prioritizes active incident postmortems and verified release notes over stale wiki pages. 3️⃣ Adversarial Verification: The agent actively tries to invalidate your deployment proposal before it touches staging or prod.
Structure beats plain retrieval every single time.
💻 Check out the open-source repo: https://github.com/aiwithrajan/shipcheck
━━━━━━━━━━━━━━━━━━━━━━━━━━
I'm an AI Systems & Agent Architect and Verified GitHub Sponsor.
If your engineering team or startup wants to move beyond naive RAG chatbots to build deterministic verification agents, knowledge graphs, or custom LangGraph workflows:
Drop me a DM or connect on GitHub! Let's build something unbreakable. 🛠️
#DevOps #PlatformEngineering #AI #SoftwareEngineering #BuildInPublic #OpenSource #Python
Completed work
AI Agent DesignerSoftware ArchitectureUI DesignGoogle Antigravity
Post image
Andrei's avatar
Andrei Stalbe
• Oct 17
How do the version constraints get into the graph—are they extracted from the docs automatically, or reviewed first? I'd be curious how you catch an incorrectly extracted dependency before it affects a deployment check.
Rajan's avatar
Rajan Mishra
• Oct 17
Great question, Andrei! This hits the exact vulnerability of automated knowledge pipelines.
In ShipCheck, we treat data integrity with 3 architectural layers:
1️⃣ Dual-Track Ingestion (Schema-First vs. Extracted): • High-authority constraints (like package manifests, OpenAPI...
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started