Free live workshop · online

Cap your AI spend in 90 minutes

One leaked key ran a Gemini account to $82,000 in 48 hours. In this hands-on session your team wires the controls that make that impossible — a fail-closed spend cap and cost-aware rate limiting — against a real stack, live. You leave with them actually running, not on a slide.

What you'll walk away with

• A hard, fail-closed spend cap that stops serving at your limit — not an alert that just emails you
• Token-aware rate limiting (tokens/min, not requests/min) + max_tokens on every call
• Per-key / per-user budgets so one leaked key can't drain the account
• The map from these controls to OWASP LLM10 and the EU AI Act — defend it to your auditor, not just your CFO

Who it's for

Engineers, platform/eng leads, and founders whose product ships an LLM feature — anyone who'd feel a surprise five-figure AI bill. No security background needed; you'll leave with working controls and a checklist.

Register free

Seats are limited so it stays hands-on. Drop your email and confirm it — I'll send the Zoom link and a calendar invite before October 8, plus the one-page defense guide now.

Save my seat →

Double opt-in — one email to confirm. Free, no recording sold to you, unsubscribe anytime. Can't make the date? Register anyway and I'll send you the recording.

← First, see what a hijacked AI bill would cost you · Home