The active firewall
for AI agents.

Install CLI Grounding SOPs FinOps & Budgets Loops & Steering Safety & Compliance

Copy Code

# Install the Intutic developer CLI globally
npm install -g @intutic/cli

# Authenticate with the Intutic control plane
intutic login

# Initialize workspace and configure local coding agents
intutic init

# Start the config sync daemon and boot the local proxy
intutic connect

# Option A: Markdown SOP (CLAUDE.md)
# Syncs to developer workspaces in real time

## Rules
1. AI models must not output raw dynamic code execution calls (exec or eval).
   Any dynamic calls must be wrapped in remedy.sanitize().
2. AI models must not print sensitive environment keys like API_KEY.
3. Term 'button' is forbidden in development builds.

## Policy Cascade (Allowed Tools)
- Allowed risk levels: NONE, CREDENTIAL_ACCESS (log only)
- Denied tools: shell.exec matching 'rm -rf'

@intutic initialize

# 3. Lock cost attribution and scope active local rules:
@intutic start ISSUE-101 --sops=security-rules --auto-judge

# 4. Predict token count and cost estimate before running:
@intutic predict "Refactor our GKE ingress paths"

# 5. Get optimization recommendations to reduce waste:
@intutic recommend

# 6. Query active budget limits, remaining budget and all active loops (or query via CLI using intutic budget):
@intutic budget

# Wrap and execute recursive agent loops with hard budget ceilings:

# 1. Run agent with a hard $3.50 session budget to block runaway loops:
intutic loop exec --name "ISSUE-101" --budget 3.50 -- claude

# 2. Or start a persistent, managed loop for budget enforcement and context drift resolution run:
intutic loop start --name "Refactor-GKE" --budget 5.00 --sops=postgres-migration --auto-judge

# 3. View status and cost accounting details of all loop runs:
intutic loop list

# 4. Mark a running loop as successfully completed:
intutic loop complete <loop_run_id>

# 5. Force-kill an active loop to block subsequent LLM requests:
intutic loop kill <loop_run_id>

# 1. Ask your AI agent to code normally:
Write a dynamic code execution using eval() and render a button.

# 2. The proxy transparently intercepts the prompt and response stream,
# evaluating local Markdown rules & GKE LLM-as-a-judge:
[Security Synthesis]
⚠ Personal Rule Violated: Term 'button' outputted. (Local console only)
⚠ Corporate SOP Violated: Use of raw 'eval()' prohibited.
  Steering Advice: Wrap dynamic calls in 'remedy.sanitize()'.