Your questions, answered.
- Days free from cloud workspace creation, with no card or automatic paid conversion
- 30
- Hour planned in the onboarding guide; not a measured setup time
- 1
- Governed calls that reach a model if it stops. It fails closed
- 0
What Token Observe is
What the product does, who it suits, its current stage, that it has no reference customers yet, and the limits of a pilot.
- What is Token Observe?
- What is Token Observe not?
- How does Token Observe work out what our AI costs?
- Is Token Observe the same product as AgentControl Plane?
- What does agent action assurance mean, and is it still what Token Observe leads with?
- Who is Token Observe for?
- What does Token Observe include?
- What stage is Token Observe at, and can it run production-critical workloads?
- What does early access mean for us in practice?
- Who else is running this?
- Is Token Observe wrong for us?
- What are the limits we would have to accept?
Licence, pricing and support
The source-available licence, how the product is metered, the free 30-day trial, the support model, what procurement needs on data processing, and how your records leave if you stop.
Deployment and operations
What it runs on, how long onboarding takes, backup and restore, upgrades and rollback, air-gapped installs, and why there is no high-availability topology.
Security and threat model
The threat model, key custody, injection and redaction limits, whether the audit log can be rewritten, vulnerability disclosure, and what has not been tested.
- What is Token Observe’s threat model?
- Where do provider API keys live, and what stops Token Observe leaking them?
- How does Token Observe handle prompt injection, and how good is the detection?
- What are the limits of Token Observe’s redaction?
- Can an administrator rewrite the audit log?
- What does off-box anchoring not prove?
- Has Token Observe had an independent penetration test?
- How do we report a vulnerability, and what happens next?
- Does the vendor see our prompts?
- Who inside our organisation can read prompts and traces?
Compliance and evidence
EU AI Act, ISO/IEC 42001, NIST AI RMF and OWASP mappings, what an evidence export proves, retention and erasure, and which certifications do not exist.
- Does Token Observe make us compliant with the EU AI Act?
- Do you have SOC 2, ISO 27001 or ISO 42001 certification?
- How does Token Observe map to ISO/IEC 42001 and the NIST AI RMF?
- Are evidence exports signed?
- How does Token Observe map to the OWASP LLM and agentic top tens?
- What are the retention and erasure controls, and what do they not cover?
How it works
The request path step by step: how an agent is onboarded, what happens inline, what streaming and failover do, what happens when something is unavailable, and what you do when a policy blocks work it should not have.
- How does an agent start routing through Token Observe?
- What happens on one governed request?
- How much latency does Token Observe add?
- Does streaming work, and do policies still hold on a stream?
- What happens to our agents if Token Observe is down?
- What happens when Token Observe blocks something it should not have?
- What happens when a model provider fails?
- How are tools and MCP servers governed?
Alternatives and adjacent tools
Where Token Observe sits against gateways, observability, security platforms and identity products, and the case for and against building it yourself.
- How is Token Observe different from an LLM gateway?
- We already have LLM observability. What does Token Observe add?
- How is Token Observe different from an AI security platform or an AI firewall?
- How is Token Observe different from an agent identity or control-tower product?
- Why not build this ourselves?
Read the complete product limits before choosing what your trial will test.
Read the product limitsTry it free for 30 days.
Create a cloud account and workspace. No card or server installation. Model calls and Google BigQuery scans can incur separate provider charges.