The agency snapshot
The full configuration a lead-gen agency puts on a new client instance, published as a list. Copy it into a script, or build it by hand from this page.
- Every object listed
- No email required
- Scriptable over MCP
The short answer
- Seven groups of objects: pipeline stages, dispositions, ICPs and segments, cadences, suppression, agent policy, and access scopes. Together they are what makes a fresh instance a working one.
- Every object has an MCP tool with the same effect as its screen, so the whole setup can be a script you version rather than a checklist someone works through.
- One-click snapshot apply is on the roadmap. Until it lands, the script is how a repeatable setup exists, and it is worth writing on the first client rather than the fourth.
Why this exists
An agency's real product is a configuration. The same stages, the same cadences, the same guardrails, applied to a new client in a day rather than a fortnight. Publishing the object list means you can build that whether or not you use our tooling.
The snapshot, object by object
1. Pipeline stages
A lead-gen agency's client usually needs two pipelines rather than one.
- New business: New lead (10%), Contacted (20%), Qualified (35%), Meeting booked (50%), Proposal sent (65%), Negotiation (80%), Won, Lost.
- Client delivery, if you track it here: Onboarding, Active, At risk, Renewed, Churned.
- Probability on every stage, because the weighted forecast is a sum of the board rather than a separate spreadsheet.
2. Dispositions and outcomes
- Call outcomes: connected, voicemail, wrong number, not interested, callback requested, booked.
- Meeting outcomes: held, cancelled, no-show, rescheduled.
- Loss reasons: price, timing, chose a competitor, no budget, no decision, wrong fit. Six or fewer, or nobody uses them honestly.
3. ICPs and segments
- One ICP record per target the client sells to, with titles, size, industry and geography.
- A segment per campaign, drawn from the data bank against the ICP.
- A do-not-contact segment for the client's existing customers and their named competitors.
4. Cadences
- Cold outreach, four steps over twelve days.
- Inbound reply, three steps over five days.
- Reactivation of a stale list, three steps over fourteen days.
- Referral partner outreach, four steps over thirty days.
- Every one with a reply pausing the sequence for that contact.
5. Suppression
- The client's existing customer list, imported before anything sends.
- Their competitor domains.
- Anyone who unsubscribed from their previous provider, if you can get the list.
- Applied at audience freeze and re-checked at send time.
6. Agent policy
- Every agent in review, which is the seeded default.
- Guardrails: three days minimum between touches, per-cadence cap, per-mailbox and per-domain daily caps, business-hours window.
- The kill switch owner named, and told they own it.
- Auto only for classification, pausing on reply, and suppression on unsubscribe or bounce.
7. Access scopes
- Your team, scoped by channel and area to what they work on.
- The client's own read access, if they get one, scoped to their pipeline and reports.
- MCP tokens issued with the narrowest scope that does the job, and revoked when a project ends.
How to apply it today
Write the setup as a script that calls the MCP tools: pipeline_stage_upsert for stages, icp_create and segment_create for audiences, suppression_add for the exclusion lists, agent_policy_set and agent_guardrails_set for the rules, and user_grant_channel and user_grant_area for access.
Run it against each new instance. It is slower than a snapshot button and it is faster than clicking, and unlike a habit it can be reviewed in a pull request.
Branding, meaning your name, logo, theme and subdomain on the app itself, is on the roadmap. Tell a client that at the start rather than at the demo.
Write the setup once, run it per client
Every object here has a tool, so the standard configuration can live in version control.