vpeetla-aivpeetla-ai/venkat-ai-platform/.cursor/rules/vap-principal-architect-bar.mdc

venkat-ai-platform / rules

Cursor rule2 starsChanged 7 months agoMITView on GitHub

Primary quality bar for Venkat AI Platform — design docs, tradeoffs, risks, cost, scale

Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- frontend/AGENTS.mdAGENTS.md
- frontend/CLAUDE.mdCLAUDE.md
- aegis-gatewaySkill
- agentic-engineeringSkill
- deploy-vercel-renderSkill
- governed-ai-stackSkill
- grill-with-contextSkill
- hitl-side-effectsSkill
- langgraph-orchestrationSkill
- loop-engineeringSkill
- portfolio-adrSkill
- principal-ux-architectSkill
- rag-governanceSkill
- repo-fix-prSkill
- setup-vpeetla-skillsSkill
- tdd-agent-loopsSkill

The file

We split this vap-principal-architect-bar.mdc into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Prefer tables: options considered, why chosen, what was sacrificed, and reversal criteria.
line 16
Very specific:
Document token/embedding/indexing/worker spend drivers and mitigation (caching, routing to smaller models, batching, pruning RAG).
line 22
Distinctive:
When instructions conflict, this rule + the design document win over ad-hoc shortcuts.
line 39

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

vap-principal-architect-bar.mdc

---
description: Primary quality bar for Venkat AI Platform — design docs, tradeoffs, risks, cost, scale
alwaysApply: true
---

# Venkat AI Platform — Principal AI Architect bar (always on)

This repository is governed as a **publishable Principal AI Architect program**, not a demo hack.

## Non-negotiables

1. **Design-before-build for material changes**  
   Any net-new subsystem (agents, data planes, auth, scheduling, external integrations) must be preceded by an update to `docs/PRINCIPAL_AI_ARCHITECT_DESIGN_DOCUMENT.md` (or linked ADR) covering tradeoffs, risks, operational impact, and cost.

2. **Explicit tradeoffs**  
   Prefer tables: options considered, why chosen, what was sacrificed, and reversal criteria.

3. **Risk analysis**  
   Include threat modeling hooks for agentic systems (tool misuse, prompt injection, data leakage, third-party ToS, financial/compliance copy).

4. **Cost & unit economics**  
   Document token/embedding/indexing/worker spend drivers and mitigation (caching, routing to smaller models, batching, pruning RAG).

5. **Scalability path**  
   State current limits, next scaling lever (async workers, queue depth, DB pooling, multi-tenant isolation), and what breaks first under load.

6. **Observability**  
   Langfuse (or equivalent) spans must remain meaningful on critical paths; avoid silent failure modes in dual-writes (Qdrant/Pinecone/notifications).

7. **Compliance posture**  
   Market and portfolio narratives are **informational only** unless reviewed by licensed professionals; surface uncertainty and jurisdiction limits.

## Where “memory” lives

- Human + agent anchor: `docs/PRIMARY_REQUIREMENT_MEMORY.md`  
- Living architecture: `docs/ARCHITECTURE.md`  
- Publication-ready deep design: `docs/PRINCIPAL_AI_ARCHITECT_DESIGN_DOCUMENT.md`

When instructions conflict, **this rule + the design document win** over ad-hoc shortcuts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free