Intercis and Lakera
Lakera is a Check Point company, with a published price table and a public badge list.
| Intercis | Lakera, from their own pagesRead 12 September 2026: lakera.ai, lakera.ai/ai-agent-security, platform.lakera.ai/pricing, trust.lakera.ai. | |
|---|---|---|
| In-path proxy or SDK | In-path proxy, out of your process. Your base URL points at us and the agent's code does not change. We govern Anthropic's POST /v1/messages and OpenAI's POST /v1/responses and POST /v1/chat/completions. |
"AI agents are being built faster than security teams can govern them. Discover your agent landscape, assess risk, and enforce protection in real time." (lakera.ai/ai-agent-security) Whether that sits in the request path or inside your code, their pages we read do not say. |
| What happens to a denied action | The tool_use block is taken out of the model's response and one text block naming the policy takes its place, so the agent runtime has no tool call to run. |
What a caller receives when protection acts, their pages we read do not say. |
| What the buyer sees per event | One row per governed tool call: the agent, the tool name, a short excerpt of the target, the verdict, the policy, the wire route, a command fingerprint and the structured tool input. Rows are hash-chained per tenant by a database trigger. | lakera.ai/ai-agent-security shows a Risk Posture dashboard: counts of critical, high and shadow risk agents, a security score, and findings mapped to OWASP LLM and MITRE ATLAS identifiers. What one enforcement record holds, their pages we read do not say. |
| Published pricing | Yes. $200 a month for the first agent and $190 for each additional agent, on the pilot page. | Yes. platform.lakera.ai/pricing listed Community at $0 a month with 10k requests and an 8k-token prompt cap, SaaS; and Enterprise priced "Let's chat!", SaaS or Self-hosted. |
| Certification | No. Intercis is not SOC 2 certified and no audit is underway. An evidence-package export is a roadmap item without a date. | Yes. trust.lakera.ai, titled "Lakera - Check Point AI Security | Trust Center", shows six badges: CSA, HIPAA, SOC 2 Type II, ISO 27001:2022, CCPA and GDPR. The badge list is public and the documents sit behind a Get Access request; the sub-processor link points at checkpoint.com. |
| Self-hosted | No, hosted only today; self-host licensing is undecided. | Yes. The Enterprise hosting row on platform.lakera.ai/pricing reads "SaaS or Self-hosted". |
What we do to a denied call, and the five costs
When policy denies a tool call, the proxy does not hand a verdict back to your code: it
replaces the provider's response. The model's tool_use block is gone, one
assistant text block naming the policy is in its place, and stop_reason is
end_turn, so the agent runtime has nothing to execute. That is
_make_blocked_response in apps/proxy/main.py, read at commit
87ccd47 on 12 September 2026.
Being in-path is a setting, not a law
Your base URL points at us and a compromised process can point somewhere else, so the control holds only if you also stop the agent reaching the provider directly.
Only the provider API wire is visible
We judge tool calls that cross the Anthropic and OpenAI API wire. A hosted MCP call has already run by the time the response reaches us, so it is observed, not governed: it writes one observe row and is never judged or blocked.
Streaming is buffered before anything is judged
The proxy collects a streamed response in full before judging it, so your agent waits the length of the stream, and nothing in the repository measures that delay.
We are a new place your prompts pass through
Your prompts and tool inputs cross our proxy in plaintext, the classifier call goes out on an Intercis credential carrying the tool name and the full tool input, and how a self-hosted deployment would be licensed is not decided.
The provider routes are ours to maintain
We speak Anthropic's messages route and OpenAI's responses and chat-completions routes, and another provider is engineering work on our side.