cscron
The customer success manager's day on scheduled agents: a daily health pulse, an ARR-weighted at-risk digest, onboarding tracking, renewal forecasts, expansion signals, ledger-gated customer touches, and a book scorecard.
Overview
cscron runs a customer success manager's post-sale day on a schedule, on our servers. Three tasks run on a clock: a daily reply scan that drafts responses for the accounts that answered, a Monday value-realized pass folded into the health score, and a customer QBR on the first of the month built from usage, outcomes and open risks. Five more run on demand: expansion signals, post-close handoff, customer-touch drafts, the advocacy engine, and score narration. Scheduled tasks fire in the runtime's 06:15 UTC window. Actions stay draft-first. From the health board, a reviewed success plan, renewal task, or expansion follow-up can remain in-app or enter the Planhat or Gainsight provider review queue.
Customer touches are ledger-gated: a contact ledger rate-limits outreach so accounts are never over-messaged.
What this role does for a founder
See what each customer needs next. Help you keep the customers you win, understand whether they are getting value, and prepare expansion conversations you can justify.
Receives the buyer goals and commitments from the sales handoff. It adds CRM, billing, support and success-platform signals as you connect them; without customers it explains the setup it needs and stays quiet.
Before it has work
- Customers on the record
- CRM connected
- Billing, support or success signals (optional, some in preview)
Where its work goes
- To Customer support: A customer risk that needs an issue resolved. Coordinate the response and bring the resolution back.
- To Account executive: A supported expansion need or a renewal conversation. Prepare the commercial next step.
- To GTM strategist: Customer outcomes and recurring needs. Improve targeting and the proof the site can use.
Needs actual customers and connected customer signals: a CRM, and where you use them a billing account and a support or success platform, several of which are in preview. Before those exist it can explain the setup and prepare a handoff template; it will not manufacture a health report. The full overview, with the work, outputs, an example and the measures to watch, is on the Customer success page.
Get started
- Buy a seat at /pricing ($99 per person per month, which licenses this role and every other one), then set up at /onboarding.
- Open your console and connect your CRM, inbox, and customer-success tools in Settings. We custody each token encrypted and read it on the schedule; there is nothing to install.
- In the console, run setup ("run cscron setup"). The wizard collects your identity, book, and health signals, verifies connectors, registers the scheduled tasks, and writes your config.
- Choose where drafts land in Settings: an in-app draft queue, or your Google Drive. Nothing is sent without your approval.
Connectors it uses
You connect these in the console and we custody the tokens encrypted, reading them on the schedule: your CRM, inbox, and customer-success / usage tools. The wizard verifies each and skips gracefully what you don't have.
Built-in CSM craft library
cscron ships with a deep, cited CSM craft library so your customer drafts read like a seasoned success manager from day one, before you have uploaded a thing. It covers value realization (measuring the outcome the customer bought, not logins), the health-score framework, proactive health intervention on leading indicators, onboarding milestones and time-to-first-value, the QBR that reframes value to the executive sponsor, the renewal playbook, expansion timing, and executive-sponsor engagement. On your first scheduled run these notes seed your knowledge library, so every AI draft grounds on real CSM method instead of generic prose.
This craft grounds how to run an account. Your proof points, the outcomes, usage figures, and named wins a draft cites, come only from the sources you upload in the console Library tab, so a draft never presents a playbook line as your customer's result. Full grounding model: Persona Console.
Licensing & the control plane
Your licence is checked before a run, never during one. The scheduler enumerates only the tenants whose cscron subscription is current, so a lapse means the next run is not scheduled, and a run already under way is never cut off. Every run reports its telemetry to your Rollup either way. Details: Licensing & renewal.
Your console (runs on our servers, nothing to install)
By the numbers (live). cscron ships 8 hosted skills, 3 of them on an auto-run schedule (daily driver: value-realization-tracker). Tier: front-line. These counts are read from the live registry, not hand-typed.
cscron has a control surface in your browser at /cscron/console. It drives the hosted runtime that runs cscron's agents on our servers on a schedule, so nothing depends on you keeping an app open. Scheduled AI work runs on your own provider key (Claude, OpenAI or OpenRouter; every tier is bring-your-own-key), after any platform-funded first-run allowance the deployment turns on. The free deterministic checks need no key. A key turns drafting on; nothing is sent until you turn the send layer on. Bedrock is built but not accepting keys yet; Settings shows it as coming soon until the transport is validated.
Today and Activity link to the original work in this workspace. Work also opens saved research and drafts. A direct link can retrieve an older finding or draft beyond the recent queue. Research expands its facts and quotes; historical drafts keep their status and disable unavailable edit actions.
Under its heading the console shows the one number cscron was hired to move: the first week of connected data after the hire, day 30, day 60 and your target, or a note naming the connection that would supply a missing week. A role with no number the platform can measure says why instead. You pick the number and set the target on Home.
- Schedule. A runtime on/off switch, plus every skill with its cadence and tier. Toggle any skill or run one now.
- Draft queue and Runs. Review the drafts your runs produced and see what ran, when, and what it cost.
- Live coach (front-line seats). On-demand interactive coaching: practice a live buyer roleplay, build a pre-call brief for a connected meeting, draft a reply to an inbound thread, write a deal-specific battle card for a competitor, or draft the lesson out of a deal you closed. Draft-only, on your budget, nothing sent.
- Build. Probe an MCP server you have already connected to see the tools it offers, and check a custom skill draft against the same compiler the fleet runs. Both are read-only: probing lists tools without calling one, and validating saves nothing.
- Settings. Budget meter, identity, and bring-your-own-key.
Delivery. Output is draft-first and lands where you choose: your in-app draft queue by default, and optionally your Google Drive "Accounts" folder, where the console names the last files that landed so you can tell delivery is working without going to look. For a security-strict team that needs real Gmail or Outlook drafts and CRM writes on their own credentials, an optional self-hosted path (n8n on your own machine) is available. Nothing is ever auto-sent. Full walkthrough: Persona Console.