Stop unsafe AI actions. Prove governed decisions.
2 SDKs
TypeScript + Python
15+
documented integrations
4 verdicts
allow · block · redact · review
2 SDKs
TypeScript + Python
15+
documented integrations
4 verdicts
allow · block · redact · review
Obsvr proof lab
Run three representative actions through a simplified local policy model. Watch the verdict, execution count, and evidence hash change together—without sending content anywhere.
Write your own payload in the full playgroundIntercepted call
{
"type": "tool.call.pre",
"tool": "sql_query",
"arguments": {
"query": "DROP TABLE customers;"
},
"agent": "data-agent"
}evaluating…
This page models selected public rules in your browser. The production SDK adds the full policy pipeline, authenticated HMAC chaining, optional device signatures, delivery accounting, and provider-specific enforcement boundaries.
The stakes
Three facts you can verify - a deadline, an attack path, and a leak. Obsvr addresses them through enforcement, investigation, and verifiable evidence.
Dec 2, 2027
EU AI Act - Annex III high-risk rules
Annex III rules apply from Dec 2027; high-risk AI embedded in regulated products follows in Aug 2028. Art. 12 logging cannot be backfilled after deployment.
source: Regulation (EU) 2026/174490+
organizations hit by prompt injection
In 2025 alone. It is now the #1 risk on OWASP's Top 10 for LLM applications - and it arrives as ordinary input your agent is trusted to read.
source: CrowdStrike 2026 Global Threat Report34.8%
of data sent to AI is now sensitive
The cited workplace dataset found over a third of enterprise data shared with AI was sensitive. Your own exposure depends on your traffic and controls.
source: Cyberhaven 2025 AI Adoption & Risk ReportCompliance reality
If you run AI in a regulated environment - fintech, healthcare, an EU AI Act high-risk system - these are already your questions.
A missing answer is an audit finding, and a stalled enterprise deal.
One leaked prompt becomes a breach disclosure you can't scope or defend.
A control you can't prove counts as no control - the deployment doesn't ship.
From 2 December 2027, Annex III high-risk systems enter the deferred rules window, including lifecycle logging obligations. Turn that on late and the gap is permanent.
See the article-by-article coverageThe gaps
Not an observability tool. Not a trace viewer.
Logs record the violation after it happened. They can't block the call.
Output filters clean up after generation. They never stop what was sent.
Dashboards show what happened. They can't produce a record an auditor can verify.
A detector only sees the traffic that reached it. It can't tell you about the call that bypassed it entirely.
obsvr = control + enforcement + proof + coverage
What obsvr does
Decide once what's allowed, what's blocked, and what needs a human to sign off. Try new rules on live traffic first - nothing actually blocked - until you're sure.
Explore SecureSee it in action
Edit policies from the dashboard and live SDKs pick them up in minutes - no redeploy, every incident traced to its root cause.
Events captured
0
Open incidents
0
Controls passing
3 / 3
Live event stream
Incident board
Measured, not marketed
24.7–25.1µs p50 across two complete 0.11.2 benchmark passes.
63.2–64.1µs p50 with rules, PII scan, quotas, hooks, signing, and enqueue.
524.3–525.1µs p50 under the same local-policy benchmark shape.
Two complete passes verified retained signatures, chain links, accounting, and declared loss.
Reproducible: BENCHMARKS.md · raw evidence retained for both runs
Integrations
Supported provider, framework, and protocol routes produce one decision format. The coverage grade tells you which routes enforce and which only observe.
Comparison
Adjacent tools each solve a slice. The rows that matter to an auditor are the ones only a governance layer answers.
| Capability | Guardrailsinput/output filters | Gatewaysrouting and access layers | Observabilitytraces and analytics | Orchestratione.g. LangChain, CrewAI | Enforcementpre-execution controls | obsvrgovernance |
|---|---|---|---|---|---|---|
| Core governance capabilities | ||||||
| Cryptographically signed, tamper-evident decision chain | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | |
| Audit trail independently verifiableVerify integrity without trusting the vendor. | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | |
| Versioned policy identity attached to governed decisionsReproduce exactly why a decision was made, months later. | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | Not publicly documented | |
| Shadow mode for policy changesRehearse rules on live traffic before enforcing them. | Not publicly documented | Not publicly documented | ||||
| Cross-language deterministic enforcement | Not publicly documented | Not publicly documented | ||||
| One-click evidence pack with offline verification | Not publicly documented | |||||
| Enforcement, audit, and compliance evidence in one platform | ||||||
| Shared with adjacent tools | ||||||
| Blocks policy violations at runtime | ||||||
| Deterministic decisions, no AI classifier in the decision path | Not publicly documented | |||||
| Customer-controlled evidence storage (BYO cloud) | ||||||
FAQ
7 questions
12
Contact
Control what your LLMs and agents are allowed to do. See obsvr intercept, enforce, audit, and export evidence from real LLM and agent traffic.