What Intercis does not cover
These are the five things a buyer should know before a pilot. Each one is a cost of running the product as it works today, and each one is the answer we would give if you asked.
The five costs
Being in-path is a setting, not a law
Your agent reaches us because its base URL says so: pointing
ANTHROPIC_BASE_URL at our endpoint is what puts us in the path, and a
compromised process can point it back and call the provider directly. Pair Intercis with an
egress rule that blocks direct calls to api.anthropic.com and
api.openai.com from the network your agents run on. With that rule we can
claim tamper resistance. Without it we are a control a compromised process can walk around.
Only the provider API wire is visible
We read the tool calls that cross the Anthropic and OpenAI API wire. A tool the provider
runs on its own servers never crosses it: hosted MCP calls, web search, file search, code
interpreter and image generation are the item types listed in
_HOSTED_ITEM_TYPES in apps/proxy/openai_routes.py, and we ran a
response body full of them through our own extractor to check what happens. It returns
nothing to judge, so no verdict is computed and no audit row is written. If your agents
rely on hosted MCP servers, that part of their behaviour is invisible to us today.
Streaming is buffered before anything is judged
To judge a tool call we have to see all of it, so a streamed response is buffered in full, reassembled and judged before any of it reaches your agent. That adds latency equal to the length of the stream before your agent sees its first token, and on an interactive coding agent a person is waiting through it. We publish no latency number.
We are a new place your prompts pass through
Putting us in the path adds a trust boundary, and your prompts and tool inputs cross it in plaintext. Relayed traffic goes upstream on your own provider key, which we do not store, but the classifier call runs on an Intercis credential and carries the tool name and the full tool input to Anthropic or OpenAI under our account rather than your agreement with them. We run the service hosted; there is no self-hosted build you can buy today, and how one would be licensed is not decided.
The provider routes are ours to maintain
We speak three routes today: Anthropic's POST /v1/messages, and OpenAI's
POST /v1/responses and POST /v1/chat/completions. A new provider,
or a new shape at one we already speak, is engineering work on our side, and until it is
done that traffic is not governed. Per-provider route maintenance is ours for as long as
the product exists, and it is the standing cost of sitting outside your agent process
instead of inside it.
All five apply to a pilot as much as to a year of production. The pilot page has the price, what the 90 days involve and how to start.
Start a 90-day pilot