Skip to content
NewSecurity Audit for AI-Built Apps. Fixed scope, clear report
GeekTech

Insights: page 2

Hands-on guides to AI security, vibe coding, automation, governance and engineering.

  • AI Automation

    How to Automate Invoice Processing with AI

    How to automate invoice processing with AI: extract fields to a schema, check them in code, match to orders, route exceptions to people and block fraud.

    7 min read

  • Vibe Coding

    How to Review AI-Generated Code Before You Merge

    How to review AI-generated code before merging: check scope first, read the risky parts, test the tests, and set pull request rules that enforce review.

    7 min read

  • AI Engineering

    How to Evaluate LLM Output Quality in Production

    How to evaluate LLM output quality in production: what to log, how to sample and grade real responses, and how to catch quality drift before users do.

    7 min read

  • AI Security

    PHP2Shell: How to Check and Patch Your PHP Servers

    PHP2Shell (CVE-2026-109618, CVE-2026-109619) lets attackers run code on unpatched PHP. Find out if you're affected, how to patch, and what to check after.

    7 min read

  • AI Governance

    Shadow AI: How to Find the AI Tools Your Team Uses

    How to find shadow AI in your company: check OAuth grants, SSO, network and expense records, survey staff, then approve, restrict or replace each tool.

    7 min read

  • AI Automation

    How to Calculate the ROI of an AI Automation

    How to calculate the ROI of an AI automation: measure a baseline, count net hours saved and every running cost, then set a payback test before you build.

    6 min read

  • Vibe Coding

    Supabase Row-Level Security Mistakes and How to Fix Them

    The Supabase row-level security mistakes common in AI-built apps, how to find each one with SQL and the Security Advisor, and how to fix them for good.

    8 min read

  • AI Security

    How to Test an LLM Feature Before Launch

    How to test an LLM feature before launch: what to attack, how to write test cases you can rerun, and the pass criteria to agree before go-live.

    6 min read

  • Vibe Coding

    Taking an AI-Built Prototype to Production

    Your AI-built prototype works and users are arriving. What to add before it holds real data: tests, CI/CD, environments, monitoring, backups, cost limits.

    5 min read

  • AI Governance

    How to Write a Company AI Use Policy

    How to write a company AI use policy staff will read: approved tools, data rules, review duties, disclosure and a route for new-tool requests.

    5 min read

  • AI Security

    How to Secure AI Agents That Can Use Tools

    AI agents that call tools can take real actions. How to scope their permissions, contain prompt injection and test an agent before it touches production.

    6 min read

  • AI Engineering

    When Does a Company Need a Fractional AI CTO?

    What a fractional AI CTO does, the signs you need one, how it compares with hiring or consultants, and how to set up the engagement so it delivers.

    5 min read

Get AI security and automation insights, monthly

AI security, automation and governance, written by engineers. No spam, unsubscribe any time.

Book a free 30-min call