Sales team
≈ $120M revenue (approx.) · 35-person sales team · one CRM
CRM-connected agent
Pipeline questions, follow-up drafts and account summaries with the CRM connected through each user's own OAuth credentials, so nobody's agent can reach a deal its user cannot see.
- Organization
- Sales team on a CRM
- Reality
- Deal data visible to some, not to all
- Runs on
- The company's cloud tenancy
- Scope
- A CRM-connected agent with per-user credentials
Where they started.
Sales wanted an agent that could answer pipeline questions, draft follow-ups and summarize accounts. The blocker was access: a shared integration would let anyone's assistant see everyone's deals, and outbound messages sent by an agent without review were a non-starter.
What was built.
- The CRM connected as a first-party MCP service with credentials scoped to tenant, user and service: each person's agent sees exactly what that person can see.
- Outbound messages composed by the agent and approval-gated before they leave.
- Pipeline questions, account summaries and follow-up drafts as a conversation with the data.
- Scheduled work, like a Monday pipeline brief, run per user with that user's own access.
What changed.
- No one's agent can reach a deal its user cannot.
- Follow-ups drafted in minutes and sent only after a human says so.
- A pipeline brief that arrives before the meeting instead of during it.
- The same connector pattern for the next system sales asks for.
Pipeline data is the company's forecast. Per-user credentials and private inference keep it exactly as visible as it was before the agent arrived, and no more.
The company's cloud tenancy
Components involved.
More like this.
Security certification body
≈ $10–15M revenue (approx.) · ~150 employees · ~100,000 CRM contacts
- Use Case:
- CRM contact database refresh
- Results:
- Roughly one hundred thousand contacts validated, deduplicated and enriched through a tiered waterfall of trust. Every changed value carries a source and a confidence tier, and a re-run kit stays with the customer.
Global law firm
≈ $3B+ revenue · Thousands of lawyers · dozens of offices
- Use Case:
- Walled-matter research assistant
- Results:
- Document search and drafting inside the firm's own tenancy: every answer cited to its source, every matter isolated by role, and nothing ever sent to a third-party model.
Franchise operations team
≈ $300M+ system-wide sales (salon brand) · 700+ studios · a handful of business coaches
- Use Case:
- Franchisee business coach
- Results:
- An agent that knows the operating playbook and every location's numbers, so a small coaching team's best advice reaches every franchisee, with opportunities surfaced instead of requested.
Have one like it?
Every spotlight started as a conversation about a process nobody liked doing, under a data-locality constraint.