“Who approved that email?”
An AI draft reached a key account with the wrong price. Nobody checked it before it left.
sales: Every rep runs the same motion.
ConvOps runs your sales playbook as governed AI agent workflows. Research lands as structure. Outreach waits for your approval before anything leaves. Follow-ups start from the meeting.
chatgpt · claude · nothing sends without approval · one motion for every rep
new chat
task
step 1 of 5Northwind Logistics
research draft approve send approvalfollow-up proposal
the problem
Ten reps. Ten playbooks.
AI writes outreach in seconds. Whether it is on message, accurate or checked depends on the rep.
“Where did that decision go?”
The pilot scope agreed on the call lives in one rep's notes. The proposal never saw it.
“What happens when someone leaves?”
Their accounts, their context and their way of selling leave with them.
watch it work
One prospect, research to proposal.
A real account, run through the Sales Outreach pack from ChatGPT. Every rep, the same motion.
01you, in ChatGPT
Name the account.
You name the prospect and ask for an intro. ConvOps creates the task and attaches Prospect Research. The motion starts the same way for every rep.
example
Research Northwind Logistics and draft an intro to their ops lead.
task created · Prospect Research attached
Researching first. Findings land on the task, not in this chat.
02the AI · research
Research lands as structure.
Company, contacts and buying signals become fields on the task, deduplicated. The next step and the next rep read the same record.
example
- industry
- Freight and logistics
- size
- About 800 people
- contact
- Dana Ruiz · Head of Operations
- signal
- Hiring three dispatch coordinators
- fit
- Strong · manual handoffs between teams
structureddeduplicated
03the AI
It remembers what works.
Before drafting, the AI recalls the team's rulings: what logistics buyers respond to, and what never to say. Every draft starts from the same lessons.
example
askintro to a logistics ops lead
memoryLogistics buyers care about on-time rates. Lead with that.
memoryNo pricing in a first email. Decided in the Q2 review.
routeCase studies: sales/case-studies/logistics/
04you approve
Nothing sends until you say so.
The draft waits at the approval gate. You read it, edit it or send it back. Outbound leaves only when a person releases it.
example
waiting for you
Send the intro to Dana Ruiz?
Subject: On-time rates at Northwind · 92 words
EditApprove send
approvedSend step unlockedThe follow-up waits for the meeting.
05the AI · follow-up
The meeting writes the follow-up.
After the call, notes, commitments and next steps land on the same thread of work. The follow-up is drafted from what was actually agreed.
example
Thanks for the time today, Dana
agreedA pilot with the Lisbon dispatch team
nextSecurity review by the 14th
ownerDana shares this quarter's on-time data
commitments capturedsame thread as the research
06the AI · proposal
The proposal inherits everything.
The proposal runs in the same line of work. It starts from the research, the call and the decisions that led here. Nobody types the account again.
example
Pilot proposal: Lisbon dispatch
from researchThree coordinators hired for manual handoffs
from the callPilot scope agreed with Dana
from memoryLead with on-time rates
researchmeetingmemory
example
Research Northwind Logistics and draft an intro to their ops lead.
task created · Prospect Research attached
Researching first. Findings land on the task, not in this chat.
the workflow
The outreach motion, running.
Five steps from first look to proposal. Nothing leaves the building until a person releases it.
workflow · Sales Outreachrunning · step 1 of 5
- 01
Prospect research
Companies and contacts land as structured, deduplicated tasks.
- 02
Outreach drafted
Written against your positioning, inside the process.
- 03
You approve the send
Every outbound message waits until a person releases it.
needs a person - 04
Meeting follow-up
Notes, commitments and next steps on the same thread.
- 05
Proposal
Inherits the research, the call and the decisions.
what it remembers
What wins stays with the team.
The next rep and the next agent start with every lesson the team already paid for.
What works
Logistics buyers care about on-time rates. Lead with that.
what wins
What never to say
No pricing in a first email. Decided once, recalled before every draft.
decided once
Account history
Research, calls and decisions on one thread per account.
one thread
Where the proof lives
Case studies and pricing sheets, so no draft starts with a search.
where it lives
the difference
Ten playbooks vs one motion.
- Each rep prompts their own way
- AI drafts go out unchecked
- Call notes stay in one rep's head
- Proposals start from a blank page
Approval before send
The send sits behind a requires_approval gate. The run does not advance until it is met.
One pack, four workflows
Prospect Research, Outreach Message, Meeting Follow-Up and Proposal. Inspect every step and gate before you install.
Edit once, every rep inherits
Change a step in the template and the next run, for every rep, uses it. Runs already in progress keep going.
Context on the thread
Follow-ups and proposals run in the same task lineage, and decisions recorded on steps become memories the next run recalls.
start this week
Four moves to your first run.
Connect the AI tool your team already uses, install the workflows, and run one real piece of work through them.
- move 1
Install the Sales Outreach pack
- move 2
Point Prospect Research at your segment: it lands as structured tasks, not a doc
- move 3
Draft outreach with the approval gate on: nothing sends until you release it
- move 4
After the first meeting, the follow-up workflow already has the context
install these
sales
Prospect ResearchBuild a qualified prospect list from ICP to review. The AI drives through Find, Qualify, and a list-review checkpoint.sales
Outreach MessageSend personalized outreach from prospect to logged outcome. The AI drives Research, Draft, and a send checkpoint.sales
Meeting Follow-UpTurn a meeting into a sent follow-up. The AI drives through Extract, Draft, and a send-review checkpoint.sales
ProposalBuild a client proposal from requirements to client-ready. The AI drives through Scope, Draft, and two checkpoints.built on
The parts doing the work.
GovernanceApprovals before anything leaves.The brainWhat wins, kept by the team.WorkspacesOne per team or client, searched together.ConnectWorks in ChatGPT, Claude and more.
ConvOps is the operations layer for AI agents: an MCP server that holds your team's process as workflows, with approval gates, a shared memory and an audit trail. It runs no AI models.
questions
What teams ask.
Will AI email my prospects on its own?
Not past an approval gate. Outbound sits behind requires_approval; the workflow drafts, the run stops, and nothing leaves until a human releases it. Remove the gate only when you decide to.
What comes in the box?
The Sales Outreach pack: Prospect Research, Outreach Message, Meeting Follow-Up, and Proposal, each a real workflow with steps and gates you can inspect on this site before installing.
How do we keep every rep on the same motion?
The motion is the template. Edit a step once and every subsequent run, for every rep, inherits it. The playbook stops being a doc people half-remember.
Where does the context from a call end up?
In the thread of work: follow-ups and proposals run inside the same task lineage, and decisions recorded on steps become memories the next run recalls.