salescron
The enterprise AE's day on scheduled agents: 15 skills, 6 scheduled tasks, a learning loop, and a setup wizard that configures it to YOUR company (name, products, competitors, brand, proof points).
Overview
salescron runs an enterprise software AE's day on a schedule, on our servers. Five tasks run on a clock: a morning pre-call brief for every meeting on the calendar, an evening post-call follow-up drafted from what was said with the commitments captured, a Monday retrospective on which deals moved and which stalled, a Friday synthesis turning the week's calls into next week's focus, and a quarterly narrative written from the record. Ten more run on demand: account scoring, account-plan scoring, meeting-prep research, joint success plans, value framing, buyer loss debriefs, pricing proposals, two deck builders, and score narration. Scheduled tasks fire in the runtime's 06:15 and 17:15 UTC windows. Everything is draft-first, and there is nothing to install.
What the follow-up reads (since 12 September 2026). With Zoom, Google Meet, Teams, Fathom or Gong connected, the evening follow-up reads the call itself: the transcript or the meeting summary as the tool delivered it, up to four thousand characters, kept on the account record. What was agreed, who owns what, and any date come from there, and the account notes are the second source. With no meeting tool connected it works from the notes alone and says so in the draft.
Follow-ups come in two lengths, and the short one is the default. Almost every call, discovery, scoping, a working session, gets the warm two-paragraph recap: what was agreed, next steps with an owner and a date, and the assumptions to check before sending. A rich account record is not a reason to write more. The longer strategic version is reserved for multi-stakeholder or executive conversations that raised a build-versus-buy question, a consolidation discussion, or a named internal initiative, and when the call is ambiguous the draft comes back short. An inflated recap costs you a rewrite and reads as vendor noise; that asymmetry is why the default leans the way it does.
The strategic version adds four beats, and two of them are honesty rules rather than pitch. It states what the product would replace and what it sits alongside and leaves in place, because the second half is what answers the "another tool to manage" worry. And anything that does not ship today is tagged as roadmap rather than described as if it exists.
It ships with no company baked in: setup interviews you for your company, products, competitors, brand kit, and your own customer proof points. The package contains no other vendor's content.
What this role does for a founder
The follow-up a sales hire would own, prepared for you to approve. Help you turn buyer interest into a qualified opportunity, a clear next step, and a well-supported buying decision.
Receives replies and researched companies from Sales development, or reads the opportunities and contacts in the CRM you connect. It keeps the confirmed brief behind every draft, so a reply reflects what you sell and what you can claim.
Before it has work
- Replies or opportunities to work
- A connected mailbox and calendar
- A CRM for stage and note updates
Where its work goes
- To Sales engineer: A technical question and the deal context. Answer from supported material, or say what is not supported.
- To Customer success: A confirmed sale, the buyer goals and the commitments made. Prepare onboarding so nothing promised is lost.
- To Sales leader: Opportunity changes and the evidence behind them. Inspect pipeline quality and what needs attention.
Most useful once replies or opportunities exist. Sending needs a connected Gmail (verified) or Outlook (preview) and the send layer turned on; opportunity updates need a connected CRM. It cannot commit you to pricing, terms or delivery outside the scope you approved. The full overview, with the work, outputs, an example and the measures to watch, is on the Account executive 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 Salesforce, Gmail, and Google Calendar in Settings. We custody each token encrypted and read it on the schedule; there is nothing to install.
- In the console, run setup ("run salescron setup"). The wizard collects your identity, company context, and proof points, resolves your Salesforce user, verifies connectors, registers the 6 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: Salesforce, Gmail, Google Calendar, Drive, and Slack. The wizard verifies each and skips gracefully what you do not have.
Two more are built but unproven, and the role's page badges them. ZoomInfo needs a partner agreement with the vendor before its API is available to us, and Clari's vendor API path has not been verified against a live account. Treat both as build-outs rather than connectors you can rely on. Octave and Sumble are planned and have no connector at all yet. n8n is not something you link here either; it is the write-back path for Salesforce, a product capability rather than a vendor connection.
Built-in AE craft library
salescron ships with a deep, cited AE craft library so your drafts read like a top-1% rep from day one, before you have uploaded a thing. It covers value framing (the value pyramid), MEDDPICC qualification, discovery questions, multithreading, champion development, competitive displacement, objection handling, mutual action plans, late-stage negotiation, and forecast honesty. On your first scheduled run these notes seed your knowledge library, so every AI draft grounds on real AE method instead of generic prose.
This craft grounds how to frame a deal. Your proof points, the stats, logos, and quotes a draft cites as results, come only from the sources you upload, so a draft never presents a playbook line as your customer's outcome. Extend or replace the seeded craft with your own plays anytime in the console library. 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 salescron 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.
Updates: a silent Monday check against /api/v1/versions/salescron; updates are never applied without your say-so.
Your console (runs on our servers, nothing to install)
By the numbers (live). salescron ships 15 hosted skills, 6 of them on an auto-run schedule (daily driver: value-framing-brief). Tier: front-line. These counts are read from the live registry, not hand-typed.
salescron has a control surface in your browser at /salescron/console. It drives the hosted runtime that runs salescron'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 salescron 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.