Official company update
Introducing Agent Activity: See What Your AI Agents Are Actually Doing
Publisher preview
- See every step: Agent Activity traces each agent session’s prompts, MCP and tool calls, read/write access, and sensitive data touches. - Control what’s allowed: Custom guardrails by model, MCP server, and skill let you flag or block, starting from 100+ built-in policies. - Endpoint to production: It’s now in early access across OX.VibeSec and OX.Cloud, with a new LiteLLM connector. For the past year, the first question security teams asked about AI was simple: do we have agents running, and where? That question now has an answer. The harder one is what comes next: what are those agents actually doing?
A saved ApplyDjinn digest is not available for this story yet.
This preview is supplied by the publisher. The complete publication remains at its original source.
Request a correction or removalApplyDjinn context
What else is visible for OX Security?
These are observations in our catalog around the company, not claims made by the article. A publication does not establish why hiring, search interest, or share prices moved.
Current roles
17
30-day current-market scope
Company stories · 30d
13
13 official · 0 independent
Attention records · 7d
0
0 Google · 0 Polymarket
Coverage mix
Attention sources
No matching record in this window.
Open roles
17
Technical roles
4 of 17
Observed hiring change
+4 roles
Hiring and market history
Daily vacancy snapshots show this company’s observed hiring; no standalone public ticker is assigned.
Vacancy history
Current role mix
4 technical · 13 other
24% of currently observed roles are technical.
Vacancy history uses saved daily snapshots through 2026-11-02. News counts are dated publications; attention counts are matched records, not search volume or prediction probabilities.