+ 45 updates shipped in 7 weeks, and we're just getting started
Any agent, governed in one step
Name it, get a key, change one URL. Whatever framework or cloud it runs on, it's protected from its first call.
Every agent, tool and server in view
What each agent can do, what it actually did, and what it can reach, drawn from its own traffic and your cloud.
Stop attacks, not work
Block what's dangerous, ask a person only when it matters, and let everything else run at full speed.
In progress
Now
Being built right now. Some of it is already in your dashboard in early form.
- Threat intel01
Run your AI incident queue from Intertrace, start to finish.
Incident triage
Give each incident a status, an owner and notes, and keep that history alongside its timeline and evidence.
- Discovery02
Go from "we found 300 agents" to "all 300 governed" in an afternoon.
Govern discovered agents from the dashboard
The one-command fleet onboarding, as a button on Discover: pick the agents found in your clouds and govern them, with the exact setting to apply to each.
Designed, starting soon
Next
Designed and queued. These start as soon as the work above lands.
- Platform01
Learn the whole product in an afternoon, and manage it as code.
Six concepts, not thirty
One agent page, templates instead of roles and packs, and declarative config you can keep in git with itr apply.
- Developer machines02
Govern the coding agents your engineers already use, where they run.
Coding-agent hooks that decide
Hooks for Claude Code, Cursor and Codex that allow, ask or block each action on the laptop, not only report it, with device and user identity on every call.
Shaping it now: tell us what you need
Exploring
Ideas we're shaping with customers. Tell us if one would unblock you.
- Integrations01
Keep every credential in your vault, wherever the gateway runs.
Vault credentials on the hosted gateway
Secret references (HashiCorp Vault, AWS Secrets Manager) work today on a gateway you host. We're exploring resolving them on the hosted gateway too, and adding 1Password.
Tell us you need this →
+ Already in your hands
The roadmap, delivered.
- ImprovedProtection trends, week on weekDefense
- NewApproval health: which rules are worth a person's timeDefense
- ImprovedThreat intel loads fast at any rangeThreat intel
- ImprovedReview a new agent in one placeAgents
- ImprovedSeamless releasesPlatform
- NewThreat intel rebuilt around incidents and techniquesThreat intel
Help us decide what comes first.
The order changes with what you tell us. If something here would unblock your team, or something you need is missing, we want to hear it.
This roadmap shows direction, not commitments: items move between stages as we learn, and we don't publish dates for work that isn't done. What has shipped is on the changelog.
+ The AI watching your AI
See what's already live on your own agents.
Book a 30-minute risk assessment, or open the Simulation Lab and try it now.