← back

Measure AI answers from your own tools.

Two read endpoints and an MCP server. Scores only — the measurement corpus and question graph stay ours. Free tier: 50 calls per key per day.

Get a key

Self-serve: sign in to your dashboard and create one under Developer (up to 5 per account). No account yet? Join the founding trial — or run a free readiness check with your email to start a record. Keys look like frk_... and go in the Authorization header.

Building something bigger — an agency integration, a platform? hello@tryfrontrow.app for a partner tier.

AI-readiness score

Can machines read this store? 0–100, with the checks. Add run=true to measure fresh.

curl "https://api.tryfrontrow.app/v1/readiness?domain=allbirds.com&run=true" \
  -H "Authorization: Bearer frk_..."

{"domain":"allbirds.com","score":88,"band":"ready", ...}

AI answer share

The latest measured share of AI answers naming the brand, with confidence interval and the full report link. Available for domains on our measurement record.

curl "https://api.tryfrontrow.app/v1/score?domain=allbirds.com" \
  -H "Authorization: Bearer frk_..."

{"domain":"allbirds.com","shelf_share":0.75,"confidence_interval":0.02, ...}

More reads — free within the meter

GET /v1/report/{auditId}     full report JSON (your account's, or public)
GET /v1/audits?domain=       run history + statuses
GET /v1/runs/{id}            poll a run you started

Run measurements — prepaid

Runs are debited in full before they start — a running job can never be interrupted by an empty balance — and failed runs refund automatically. The $99 audit is brand-level at any catalog size (facts sampled from your top ~20 products); per-product depth is the $1 check. Measurement calls draw prepaid credits from your account (top up on your account page): product check $1, snapshot $5, deep audit $99. Live-plan accounts have checks and snapshots included. Runs are paid before they start; failed runs refund automatically.

curl -X POST https://api.tryfrontrow.app/v1/audits \
  -H "Authorization: Bearer frk_..." -H "content-type: application/json" \
  -d '{"domain":"yourstore.com"}'

{"id":"01...","status":"queued","poll":"https://api.tryfrontrow.app/v1/runs/01...","charged_cents":9900}

POST /v1/snapshots  {"domain"}                    store snapshot · $5
POST /v1/checks     {"domain","productId"}        product check · $1
POST /v1/batches    {"domain","productIds"?:[]}   up to 100 checks at once · $1 each,
                                                  quoted and debited in full at submission —
                                                  refused whole if the balance is short

MCP server

Give your agent the answers. Streamable HTTP at https://api.tryfrontrow.app/mcp; tools: ai_readiness_score, ai_shelf_score.

// claude code
claude mcp add frontrow https://api.tryfrontrow.app/mcp \
  -t http -H "Authorization: Bearer frk_..."

Fair use: scores may be shown in your product with attribution ("Measured by FrontRow"). Reselling raw responses or bulk-harvesting the corpus is not licensed. Full audits and monitoring run on plans.