Install & get started

VectorCourt gives an independent adversarial verdict on a hard decision. It is HTTP-first — there is no SDK and no binary to install. You send a question, wait, and read back a structured verdict. This page sets that up for your agents and for you.

1 — Get an API key

Filing a question needs a key (Pro and above). Buy one, and the key is delivered to you after checkout.

See pricing & buy a key →

Place the key where the helper and your agents can find it — either an environment variable or a key file:

# option A: environment variable
export VC_KEY="vc_your_key_here"

# option B: key file (zero-config — no export needed)
mkdir -p ~/.vectorcourt
printf '%s' "vc_your_key_here" > ~/.vectorcourt/api.key
chmod 600 ~/.vectorcourt/api.key

The key is sent only as the X-VC-Key request header. Never commit it or paste it into a prompt.

2 — For operators: the vc-ask.sh helper

One script files a question, waits for the verdict, and prints it. It resolves the key from VC_KEY, then VECTORCOURT_API_KEY, then ~/.vectorcourt/api.key — so once step 1 is done it just works.

# prerequisite: jq (for parsing examples)
brew install jq          # macOS    (or: apt-get install jq)

# get the helper
curl -fsSL https://vectorcourt.com/static/vc-ask.sh -o vc-ask.sh
chmod +x vc-ask.sh

# ask a question
./vc-ask.sh "Should a 15-person startup build its own auth or use Auth0/Clerk? Argue both sides."

# or file a longer, structured prompt from a file
./vc-ask.sh --file /tmp/decision.txt

It prints the verdict to stdout and a one-line SIGNALS: summary to stderr (see step 4). For a network drop mid-wait, it prints a resume command — re-run with --submission-id <id> instead of re-filing.

3 — For agents: install the skill (ANCC)

Agent runtimes that follow the ANCC skill convention can install VectorCourt as a skill. The skill is a thin wrapper over the same vc-ask.sh helper: the agent files a question, waits, and reads back the verdict and the recommended next action — no human in the loop.

Drop the helper into the runtime's skill directory and reference it from your agent's skill manifest:

# fetch the helper into your agent's tools/skill directory
curl -fsSL https://vectorcourt.com/static/vc-ask.sh -o vc-ask.sh
chmod +x vc-ask.sh
# the agent calls:  ./vc-ask.sh --file prompt.txt   (key resolved from ~/.vectorcourt/api.key)

The machine contract — request body, polling, clarification round-trip, and signed webhook callbacks — is documented on the agentic API page. The discovery document is at /openapi.json.

4 — Read the verdict: act on the outcome

A verdict is not always "the answer." Sometimes the most valuable thing the court returns is that you asked the wrong question — because correctly answering the wrong question is the catastrophe. When the deliberation surfaces a strong counter-signal, the verdict carries a prominent North Star block right after the decision: the answer to what you asked, and the direction worth choosing next, with proof. Most verdicts show none — its presence is the signal worth reading.

After a finalized verdict the helper also prints a SIGNALS: line whose next_action field tells you — or your agent — what to do next. You do not have to interpret the internals yourself.

SIGNALS: next_action=reframe_question quorum=FULL_QUORUM quality=low verdict_status=insufficient confidence=0.42

What VectorCourt is NOT

It does not execute the chosen path or change your infrastructure. It does not replace factual lookup or your own go/no-go. It is not for low-stakes choices where the delay and cost outweigh the value. It does not guarantee unanimity — dissent and reversal conditions are part of every verdict.