Same question. Two answers. One is $530K off.
Same CRM. Different answers. Your forecast is wrong and you don't know it yet.
Built at a $13M Series A B2B SaaS company, not a pitch deck
Sigil started as an internal tool at a $13M Series A B2B SaaS with over a thousand HubSpot fields across three objects and 389 active workflows. Deployed company-wide as the primary self-serve analytics tool, it answers real revenue questions daily for every team.
The accuracy numbers come from testing real business queries against the data team's known-correct answers, before and after adding the context layer. Your board deck matches your CRM. First pull. Every time.
From setup to accurate answers in 22 minutes
Give it access
Add Sigil's MCP URL to Claude, ChatGPT, or Cursor. Takes 2 minutes. Your agent now has a context layer alongside its HubSpot connection.
Have the onboarding conversation
Your agent asks what pipeline stages mean, which deals to exclude, how you calculate win rate. You answer like you would for a new hire. Sigil remembers it permanently. ~20 minutes, once.
Every question gets the right answer
From now on, every agent in your org queries through your definitions. The right filters. The right properties. The right exclusions. No more "confidently wrong."
What "pipeline" actually means at your company
Metric definitions
What "win rate" or "ACV" actually means in your business. Which fields to use, how to calculate, what to exclude.
formula: closed_won / (closed_won + closed_lost)
exclude: partner_deals, renewals
Field aliases
Your team says "ACV" but HubSpot calls it hs_acv. Sigil maps the language gap so your agent uses the right property.
maps_to: hs_acv
note: "not amount, not arr"
Exclusion rules
Test deals, internal accounts, churned-then-returned. The records that silently corrupt every report.
exclude_when: owner = "Integration User"
applies_to: all revenue queries
Known gotchas
The tribal knowledge that lives in someone's head. "Always use fiscal quarters." "Close date was wrong before March."
before 2024-03-01. Use
hs_date_entered_closedwon instead."
Sits alongside, never replaces
Raw CRM data
Deals, contacts, companies, properties. Everything in HubSpot, exposed to your agent as-is.
Your definitions
Metric formulas, field aliases, exclusion rules, known gotchas. The meaning behind the data.
Accurate answers
Combines raw data with your context. Every query uses the right filters, properties, and calculations.
Your data stays in HubSpot. Sigil stores only your definitions — metrics, aliases, rules. It never sees your CRM data.
Before you ask
No. Your data stays in HubSpot. Sigil only stores your business definitions — metric formulas, field aliases, exclusion rules. Your AI agent queries HubSpot directly through your existing MCP connection. Sigil never sees your CRM data.
About 22 minutes total. 2 minutes to add the MCP connection. ~20 minutes for the onboarding conversation where you define your key metrics. Once.
No. Sigil works whether you have 50 HubSpot fields or 5,000. It scales with your complexity. Free to start.
No. You add one URL to Claude, ChatGPT, or Cursor. Then you have a conversation in plain English about what your metrics mean. No code required.
"Most AI tools have access to data. What they don't have is context."
— HubSpot CPO, Spring 2026 Spotlight
"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.