Your AI agent is confidently wrong about your data. Sigil fixes that.

Every team asks your AI agent the same question and gets a different number. Sigil makes them all get the right one. Built in production at a $13M Series A SaaS.

Get started free

Free to start. No credit card. Works with Claude, ChatGPT, or Cursor.

Claude

Hey Sigil, what's our monthly churn rate and how is it trending?

Used 3 integrations, loaded tools

Get contextSigil

{

"metric": "logo_churn_rate",

"formula": "churned_customers / active_at_month_start",

"active_definition": "subscription_status = 'active' AND mrr > 0",

"exclude": ["trial_only accounts (never converted)"],

"gotcha": "Paused subscriptions are NOT churned until 90 days"

}

List subscriptionsStripe

{

"status": ["active", "canceled", "past_due"],

"created_range": "last 6 months",

"expand": ["customer"],

"returns": "2,847 subscriptions with status transitions"

}

Execute SQLSnowflake

{

"query": "SELECT month, COUNT(CASE WHEN churned...) / COUNT(active_start)...",

"source_table": "dim_customers joined with Stripe subscription data",

"trailing_months": 6

}

Logo churn: 3.2% in July, down from 4.1% in June. 3-month trend: improving.

Excludes trial-only accounts (never converted). Paused subscriptions held for 90 days before counting as churned. Active = subscription_status 'active' AND mrr > 0.

THE GAP

Same question. Different answers. Every time.

Your AI agent queries your tools correctly. It returns valid data. But it gives your VP Sales one pipeline number and your CFO another because it doesn't know what your metrics actually mean in your business. That gap costs you in board meetings, forecasts, and trust.

CHOOSE YOUR PATH

Where does it hurt?

Your VP Sales and CFO see different pipeline numbers

Metric definitions, exclusion rules, and field aliases. The context that makes AI agents accurate on revenue questions. Built by a RevOps practitioner running 1,470 HubSpot properties daily.

See RevOps use cases →

80% of your time on ad-hoc questions that AI could answer, if it had context

Table schemas, join logic, metric formulas, and known gotchas. Structured context that takes text-to-SQL from 21% to 98%+ accuracy. Works with BigQuery, Snowflake, Postgres, and 6 more.

See data & analytics use cases →

HOW IT WORKS

Three steps to accurate answers

You wouldn't hand a new hire your CRM and say “figure it out.” Give your agent the same onboarding.

Connect

Add Sigil to Claude, ChatGPT, or Cursor. One line. Runs alongside your existing data connections and doesn't replace anything.

Define

Sigil asks the questions your new hire would ask: “What counts as a qualified deal?” “Which pipeline is the real one?” “Do we include partner deals in win rate?” Your answers become the agent's permanent context.

Trust

Every agent in your org now queries through your definitions. The right filters. The right properties. The right exclusions. Your VP Sales and your CFO see the same number.

Get started free

No credit card. 2-min setup.

INTEGRATIONS

Works with any tool your AI agent connects to.

If your AI agent can connect to it, Sigil can add context to it. HubSpot, Gong, BigQuery, Snowflake, Stripe, PostHog, and hundreds more.

HubSpotGongBigQuerySnowflakePostgresStripePostHog+ any tool

See all integrations →

“Most AI tools have access to data. What they don't have is context.”
HubSpot CPO, Spring 2026

“60% of agentic analytics projects relying solely on MCP will fail by 2028 without a semantic layer.”
Gartner D&A Summit, 2026

Same question. Same answer. Every time.

No more triple-checking. No more “where did you get that number?” Free to start.

GET STARTED FREE LOG IN

Free to start. No credit card. Works with 50 fields or 50,000.