Agent Team template
Combines CRM context with bounded browser research, explains the qualification decision, creates an unsent email draft, and updates the lead after approval.
One-message setup · 4 specialists · Managed browser · Instant sample
Designed for
Founder-led sales and revenue operations teams using HubSpot and Google Workspace
Outcome
Turn one inbound lead into an evidence-backed status and ready-to-review follow-up package.
Say what should be true when the work is done.
Codelit runs one labeled Sample with no account, model, or external App calls.
Review the evidence, then reuse the same brief with your data when it is useful.
Normalizes the connected HubSpot record and preserves launch policy.
Fast structured model
Collects current visible firmographic evidence from one approved profile.
Visual research model
Chooses a supported HubSpot status and drafts one permission-aware follow-up.
Balanced sales reasoning model
Creates the unsent draft first, then applies the exact CRM status after approval.
Structured output model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A workflow skill that captures the operating contract, tool boundaries, and escalation rules for Lead Qualification Team.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes task resources, prompt templates, connector tools, and audit records behind a permission-aware boundary.
tools · resources · prompts
Read the HubSpot contact and preserve the approved research and follow-up fields.
Use Browser Operator to gather current visible company evidence.
Choose one allowed CRM status and prepare a permission-aware unsent follow-up draft.
Verify outreach permission, create the approved unsent Gmail draft, then update HubSpot.
Open it in Codelit and describe the result. Codelit handles common setup while Flow stays available for direct editing and Activity keeps the proof.
Try agentA support workflow that reads product docs, checks account and billing state, drafts empathetic replies, and escalates sensitive requests with source-linked evidence.
A code-first support agent built around specialist ownership, function tools, MCP resources, guardrails, traces, and eval loops so customer answers can move fast without leaking account state.
An n8n-centered workflow that turns a business automation request into a tested app workflow with conditional logic, human-in-the-loop checks, cost controls, and failed-run repair notes.