Prospect Research AI workflow template: A prospect list worth reaching out to.

The Prospect Research template makes your AI build a qualified prospect list: define the ideal customer profile, find candidates with a source for each match, check each against every criterion and disqualifier, then enrich the keepers. You approve the ICP before any search and the list before outreach.

5 steps · 2 approvals · 1 loop back

Start free Book a demo

Prospect Research · example runyour AI client

01Define ICPyou approve
02Find
03Qualify & Enrich
04List Reviewyou approve
05Completeclosing note

task created · workflow attached

example · the steps are this template's real steps

in short

What does the Prospect Research template do?

For founders and sales teams who build target account lists and need a reason, and a source, for every name on them.

It is a stored workflow, not a prompt. Your AI client receives one step at a time from ConvOps over MCP, does the work, and advances. The engine holds the run at each of its two approvals until a person says yes.

Build a list of 20 prospects that match a defined ideal customer profile
Research companies in a target industry and geography that fit your offer
Qualify a raw list down to the accounts actually worth reaching out to

step by step

How does the Prospect Research workflow run?

5 steps, in this order. Below each one is the instruction your AI receives at that step, exactly as the template stores it.

Define ICPwaiting for you

Find

Qualify & Enrich

List Reviewapproval

Completeclosing note

01
Define ICP
waits for your approval
Define the ideal customer profile before finding anyone. Do not search yet.
What good looks like:
- Industry or vertical: specific, not "businesses"
- Company size: employee count or revenue band
- Geography: region, country, or city
- Buying trigger: the signal that makes them a fit right now (hiring, funding, tech in use, growth, a pain you solve)
- Disqualifiers: what rules a company out, stated explicitly
- Target count: how many prospects this list should hold
If the operator's criteria are vague, push for specifics: a loose ICP produces a useless list.
Save the full ICP as a task note with task_notes_add. Then ask the operator to approve it before any searching begins. This is a checkpoint: the AI cannot advance until you approve.
no rejection path · the run moves on only when approved
02
Find
the agent works
Read the task notes with task_notes_list: the note from the Define ICP step contains the approved criteria. Work from it.
Find candidate companies matching the ICP. For each candidate capture:
- Company name and website
- Why it matches: the industry, size, geography, and trigger that qualify it
- A source or link backing the match
Cast a slightly wider net than the target count, since some will drop at qualification. Do not filter hard yet: that is the next step.
Save the candidate list as a task note with task_notes_add. The Qualify step reads this note.
03
Qualify & Enrich
the agent works
Read the task notes with task_notes_list: the Find note holds the candidates and the Define ICP note holds the criteria and disqualifiers. Work from them.
For each candidate:
- Check it against every ICP criterion and disqualifier: keep, drop, or flag as uncertain, with a one-line reason
- For each kept account, enrich with what you can find: the likely buyer role, a contact name or channel, and any current trigger
- Drop anything that hits a disqualifier
Produce the qualified, enriched list trimmed toward the target count.
Save the qualified list as a task note with task_notes_add. If it exceeds 10,000 characters, split across notes or store where the operator keeps documents and record the location. The List Review step reads this note.
04
List Review
waits for your approval
Read the task notes with task_notes_list: the note from the Qualify step contains the final list with reasons and enrichment. Work from it.
Present the qualified list for review: how many accounts, how each was qualified, and any uncertain entries flagged for a decision.
Ask the operator to approve the list before it goes to outreach. This is a checkpoint: the AI cannot advance until you approve. If you reject, the workflow returns to Qualify & Enrich to adjust.
rejected → back to Qualify & Enrich
05
Complete
closes with a note
The qualified prospect list is approved and ready for outreach. Confirm the final list is saved as a task note, then close out the task. This note is the named input for an Outreach Message workflow.

where a person decides

Where do you approve in Prospect Research?

Two steps wait for a person. You answer in the chat; the engine records the verdict and the audit row records who gave it.

step 1

Define ICP

A loose ICP produces a useless list. You approve industry, size, geography, buying trigger, disqualifiers and target count before any search.

what you review

Industry or vertical: specific, not "businesses"
Company size: employee count or revenue band
Geography: region, country, or city
Buying trigger: the signal that makes them a fit right now (hiring, funding, tech in use, growth, a pain you solve)
Disqualifiers: what rules a company out, stated explicitly
Target count: how many prospects this list should hold

no rejection path · approve to continue

step 4

List Review

The AI shows how each account qualified and flags uncertain ones. Approve it for outreach, or reject and the run returns to Qualify & Enrich.

reject → back to Qualify & Enrich

gates the engine checks without you

Complete closes only when your AI leaves a closing note. The note is saved to the task as context, so later work can find why it ended the way it did.

what you need

What do you need to run Prospect Research?

Read from the template's own steps: the tools they call, the files they write, and whether they touch code.

An AI client: Claude Code, Claude (desktop, web, Cowork), OpenAI Codex, ChatGPT, Cursor, OpenCode, or any MCP client. ConvOps does not run the model; your client does the work.
ConvOps: A workspace with Prospect Research installed. It attaches to the task task type, so new work of that type starts on it.
Tools your AI calls: workflow_advance to move between steps, plus task_notes_add and task_notes_list to save and read each step's output.
Where the work lands: Task notes in ConvOps. Each step saves its output with task_notes_add, and the next step reads it back.
A repository: No. A plain chat client is enough.
Roles named in steps: None. One AI runs every step.

Connect your AI client first, then install Prospect Research from the catalog in the ConvOps app. See how to connect a client

make it yours

How do you customize Prospect Research?

An installed template is a workflow in your workspace. Ask your AI to change it in plain words; the edit lands on the one step that needs it.

ChatGPTexample

new chat

more example prompts

"In Find, only use LinkedIn and company websites as sources."
"Add a column to Qualify & Enrich: estimated deal size."
"After Complete, start an Outreach Message task for each approved account."

the difference

Prospect Research: without a workflow vs with it

You start finding companies before agreeing on who a good prospect even is, and the list drifts off-target
Unqualified names pile up and a rep wastes a week on accounts that were never a fit
You build half a list, close the chat, and have to rebuild the criteria and findings from memory
A month later nobody can say why an account made the list or who signed off on it
The process lives in a prompt, and each run follows it a little differently

questions

Prospect Research template FAQ

What goes into the ICP?

Industry or vertical, company size, geography, a buying trigger (hiring, funding, tech in use, growth, a pain you solve), explicit disqualifiers and a target count.

How does qualification work?

Each candidate is checked against every ICP criterion and disqualifier and marked keep, drop or uncertain with a one-line reason. Kept accounts are enriched with the likely buyer role, a contact and any current trigger.

What happens to the approved list?

It is saved as a task note and is the named input for an Outreach Message workflow. Both ship in the Sales Outreach kit.

Which AI clients can run the Prospect Research template?

Any MCP client connected to ConvOps. Verified clients: Claude Code, Claude (desktop, web, Cowork), OpenAI Codex, ChatGPT, Cursor, OpenCode. It needs no repository, so a plain chat client works.

Workflows that run next to it

sales

Outreach MessageSend personalized outreach from prospect to logged outcome. The AI drives Research, Draft, and a send checkpoint.5 steps · 2 gates

sales

ProposalBuild a client proposal from requirements to client-ready. The AI drives through Scope, Draft, and two checkpoints.5 steps · 3 gates

sales

Meeting Follow-UpTurn a meeting into a sent follow-up. The AI drives through Extract, Draft, and a send-review checkpoint.5 steps · 2 gates

universal

PlanTurn strategic work into reviewed, executable plans. The AI drives through Analyze, Draft, phases, and execution.10 steps · 5 gates

your next step

Teach it once. Then let it run.

on your ownStart freeConnect your AI tool in one line. Nothing to install.with your teamBook a demoWe show ConvOps on your team's real work.keep readingThe Sales Outreach kitProspect Research with the workflows it connects to.