Skip to content
AKSHAY KANKAL
Back to the work

CreditRiskMonitor

Used by about 50 developers

Safe guardrails for 50 developers using AI

Developers use AI to help write code. This sets the boundary of what those AI tools are allowed to touch, the same way for everyone.

Architecture diagram for Safe guardrails for 50 developers using AIDeveloper. Select to see why it is here.DeveloperThe guardrails. Select to see why it is here.The guardrailsAllowed tools. Select to see why it is here.Allowed toolsAllowed code. Select to see why it is here.Allowed codeAllowed data. Select to see why it is here.Allowed dataThe AI tool. Select to see why it is here.The AI toolThe harness decides the reach, not the agent

Click any box in the diagram to see why it is there

Problem

Developers adopted AI coding tools faster than anyone wrote rules for them. Without a shared setup, every developer quietly decides for themselves what those tools are allowed to open.

Approach

One shared setup, built on the Model Context Protocol, so every developer works inside the same boundary rather than inventing their own.

Architecture

The harness defines which tools, which code and which data an agent is able to reach. The boundary is set in one place rather than in each local setup.

At a glance

  • One shared setup instead of 50 people each deciding for themselves what an AI tool may access.
  • Spells out exactly which tools, which code and which company data an AI assistant can reach, and blocks the rest.

Want the longer version?

akshaykankal@gmail.comBack to all three