AboutProductResourcesContact
The I-THAM blog

Insights on securing AI

Analysis and field notes on AI security: prompt injection, agentic AI risk, interpretability and the frameworks shaping how organisations protect AI.

Featured

Autonomous AI is here. But can you trust it to act on your behalf?

The old question was whether our AI is secure. The one that matters now is whether we can trust it to act.

Read the article
You delegate a goal to an autonomous agent, and an I-THAM checkpoint verifies every action it takes across email, code, payments and calendar, holding an unusual payment for approval
Isometric scene of a person delegating to an AI agent, with a checkpoint verifying each action1YouSet the goal, not every step.2The agentPlans and acts across your tools.3A checkpoint on every actionEach action is checked against the goal.4Held for approvalAn unusual payment waits for a person.
  • YouSet the goal, not every step.
  • The agentPlans and acts across your tools.
  • A checkpoint on every actionEach action is checked against the goal.
  • Held for approvalAn unusual payment waits for a person.
All articles

Latest from I-THAM

Autonomous AI Is Here. But Can You Trust It to Act on Your Behalf?
Blog
September 18, 2026

Autonomous AI Is Here. But Can You Trust It to Act on Your Behalf?