Multi-agent sales workflow: from first search to a booked meeting
Chain the Research, Qualifier, Writer and Reply agents through your lists and inbox, so finding, scoring, writing and answering run as one relay with your approval at the key moments.
- 7 days free
- No card required
- Nothing sends without your yes
One request. The agent does the rest.
Type it to Penny, or use it as the agent’s brief and let it run on its trigger.
Every Monday, find 30 new people who fit my ideal customer with Apollo and save them to “Weekly pipeline”. The Qualifier scores them, the Writer writes first lines for the Fits, and replies get drafts with times from Calendly.
- Research Agent saves new people to a list on schedule
- Qualifier starts on its own and tags them Fit, Maybe or No
- Writer starts when Fits reach its list and writes first lines
- You approve the campaign launch
- Reply Agent drafts every labelled reply with open times
- Found and saved
- 30
- Tagged Fit
- 19
- First lines written
- 19
- Replies drafted
- Every labelled reply
One agent doing everything is hard to trust and hard to fix. A team of specialists, each with one job and one clear output, is how good sales teams already work: someone researches, someone qualifies, someone writes, someone answers. Prosyo’s agents work the same way and hand work to each other through your lists and your inbox.
How the relay works
The Research Agent runs on a schedule and saves new people who fit to a list. Saving people to a list is an event, so the Qualifier, set to run when people are added to that list, starts on its own and tags each person Fit, Maybe or No with a reason. The Fits go to the Writer’s list, and the Writer writes a personal first line for each one. You approve the launch. When people reply, each reply is labelled, and the Reply Agent drafts an answer with open times from your calendar.
Why specialists beat one big agent
- Each agent has a short brief, so its behaviour is easy to read and easy to change.
- Each step leaves a visible result, a list, a tag, a line, a draft, so you can check the relay at any point.
- Each agent has its own permissions. The Qualifier can tag freely, while sending always waits for you.
Set it up
- Create the four agents from their templates: Research, Qualifier, Writer and Reply Assistant.
- Point them at the same lists: Research saves to “Weekly pipeline”, the Qualifier watches it and adds Fits to “Ready to write”, the Writer watches that list.
- Schedule the Research Agent weekly, and set the Reply Agent to the labels you want.
- Keep campaign launches and sending on review.
Good to know
Up to two agent runs are active at a time in a workspace, and others wait their turn, so the relay runs in order without overlapping. Every run has a page that says what it did in plain words, with the credits each step used, and anything waiting for you can be approved right there.
Connected in a click, used on your terms
Sign in once. Every action is marked Reads or Changes data, and changes wait for your approval.
Research Agent asks before it acts
You choose how much it does alone. Reading and research always run straight away; anything that sends, spends or changes another app waits as a card you approve, unless you allowed it.
- Review each stepIt asks before every step, unless you allowed that action to run on its own.
- Review changesIt reads and researches freely, then brings every change back to you.
- Run routine workSaving people, tagging and preparing drafts run on their own. Sending, paid actions and other apps still wait.
Use cases that pair well with this one
On demandBuild Apollo prospect lists that only hold people who fitPoint the Research Agent at Apollo with a plain-language brief. It finds the people, checks each one against your ideal customer and saves the fits to a Prosyo list, ready for outreach.Research Agent

On demandAI ABM: reach the whole buying committee of every target accountFor each target account, the Research Agent maps the buying committee by role, finds the people with your lead data apps and saves one list per role, ready for coordinated outreach.Research Agent
High intentReach former champions the moment they change jobsWhen Intent spots a past champion at a new company, the Research Agent finds their new details with Apollo and saves them to a list, so you are first to say congratulations.Research Agent How do agents start each other?
Through your lists and your inbox. An agent that saves people to a list starts any agent set to run when people are added to that list. A labelled reply starts the Reply Agent.
Do they all run at once?
Up to two runs are active at a time in a workspace; the others wait their turn, so the relay runs in order.
Where do I stay in control?
Each agent has its own approval level and allowed actions. Launching a campaign and sending replies wait for your yes.
When does it run?
On the schedule you choose: every day, on weekdays, or one day each week at a set time in your time zone. You can still click Run now at any moment.
Which apps does it use, and do I need accounts?
It uses Apollo.io, with one-click sign-in; Calendly, with one-click sign-in. Each app works with your own access, so the agent only sees what your account can see, and anything an app charges for is billed by that app.
Can the agent act without my approval?
Reading and research run straight away. Routine work such as saving people to a list or tagging can run alone if you allow it. Sending, paid actions and changes in other apps wait for your yes unless you explicitly allowed that action.
What does a run cost?
Each step uses AI credits like a Penny question, and you set the most steps and credits one run may use. A run pauses at either limit until you continue it. Paid actions such as enrichment, and charges from connected apps, are separate.
Can I change what the agent does?
Yes, in plain words. Edit the brief, attach a skill such as your own playbook, tick or untick apps and change what needs approval. The next run follows the new instructions, and finished work stays saved.
Which agent runs it, and what pairs well with it?
The Research Agent, Prosyo’s ai prospecting agent. Start from its template and use this request as the brief. It pairs well with the Qualifier Agent and the Writer Agent, which can pick up its results through your lists and inbox.
How do I see what the agent did?
Every run has a page that says what it did in plain words, with the credits each step used and anything waiting for you. Results show as formatted answers, tables or diagrams, and you get a notification when a run finishes or needs your approval.
Which Prosyo plan do I need?
Agents come with the Penny Agents, Penny SDR and Penny SDR All-in plans: 5, 10 or 20 agents. Every workspace starts with a 7-day free trial, no card required.
Your next 10 meetings are already on LinkedIn.
7 days free, no card. Pay later and change your mind? Full refund within 7 days.
- 7 days free
- No card required
- Cancel in two clicks








