sally/connect-your-ai_

Bring the AI you already use. Sally is what it reads before it writes.

Connect Claude or ChatGPT in two minutes. Your agent reads your brand's second brain and live context — projects, orders, deals — drafts newsletters and campaigns with sources, keeps CRM and tasks current, and stops at an approval gate before anything reaches a customer. Over a hundred tools, under exactly the permissions you grant.

Start free trial connection guide

mcp/session

> read my Sally context

← 3 brands · 6 finished projects this month · 2 open follow-ups · brand voice loaded

> draft the October newsletter for Northwind

← draft ready · 4 claims, each linked to its source

> log the call with Maurice, follow up in two weeks

← activity logged · follow-up created · due in 14 days

> send the newsletter

← approval requested · nothing sent yet

Getting connected

From signup to a drafted newsletter in three steps.

1. Connect

In Sally: Brand overview → Connect your AI → pick Claude or ChatGPT and paste one link into the app you already use; sign in with your Sally login. Other MCP clients use a scoped key. Two minutes, no code.

2. It reads first

Every session starts with your brand's second brain and live context: finished projects, orders, deals, open follow-ups, standing instructions. The agent knows what happened before it writes a word.

3. It works, you approve

It drafts the newsletter with sources, updates CRM and tasks, files handoffs — and anything outward-bound stops for your yes, in My Work or in your inbox.

What it can do

Everything you can do in Sally, your agent can do too.

Marketing first — that is the job. But if a human can do it in the UI, an agent with the right permissions can do it over the connector (MCP, for the technically curious).

Marketing

marketing.message.create · marketing.campaign.create · marketing.audience.sync · marketing.message.propose_send

Draft newsletters in the visual builder format, assemble campaigns, manage audiences and senders — and propose sends that always wait for approval.

Second brain

sally.context · memory.search · memory.intake · memory.intake.execute

Read what the brand knows before writing. Turn meeting notes into structured records, follow-ups and durable context.

CRM

crm.person.create · crm.deal.update · crm.activity.add · crm.follow_up.add

Organizations, people, deals, activities, and follow-up reminders — the customer context your marketing is written from.

Projects & tasks

project.runtime_context · task.create · task.move · task.handoff.create · comment.add

Full board control: statuses, priorities, checklists, comments, dependencies, and structured handoffs — the work that becomes evidence.

Timesheets & clients

timesheet.add · timesheet.report · client.create · client.update

Log time, pull workspace-wide reports, and keep client records current — useful for agencies billing real work.

Workspaces & structure

workspace.list · project.create · project.status.create · project.member.add

Set up and reshape structure where permissions allow: projects, statuses, members, and workspace context.

Agent-ready context

Agents start informed and hand off cleanly.

The most expensive part of agent work is re-establishing context. Sally makes context and handoffs first-class tool calls.

project.runtime_context

One call returns what an agent needs before touching a project: summary, statuses, open and blocked tasks, relevant memory, recent activity, blockers, approvals, trust policies, and the recommended workflow.

task.resume_context

Pick up any task cold: the latest handoff, evidence, approvals, blockers, decisions, recent comments, related memory, and a recommended next action.

task.handoff.create

When an agent finishes or gets stuck, it files a structured handoff: a concise summary comment, an optional blocker or approval request, a status move, recorded evidence, and a decision brief that lands in My Work.

Control

Autonomy you can dial, boundaries you can trust.

Proposals before actions

Agents can propose actions instead of executing them. You review, approve, or deny — and Sally records the outcome either way.

Trust policies per agent

Allowlist safe actions for auto-execution — creating tasks, adding comments, logging CRM activity — while everything else waits for a human.

Typed approval gates

Publishing, credentials, payment data, customer data, client decisions, live deploys, and destructive actions each have an explicit approval type. Mass sends are proposals by design.

Typed blockers

Missing access, failing tests, ambiguous requirements, pending client decisions — agents raise structured blockers instead of improvising.

Everything on the record

Agent connections, runs, and actions are visible, revocable, and written to the operational event ledger and audit log.

Real permission checks

Every tool call passes the same permission resolver as the web app. An agent can never do more than the human who authorized it.

Working with Sally

next/action

Connect Claude or ChatGPT today.

Start a trial, connect the AI you already use, and give it its first real job: this week's newsletter, written from what actually happened — with every send behind your approval.

Start free trial

7 days free. No credit card required.