Skip to content
From the blog

Automate prospect research without slop

You can automate the finding and the fetching. You cannot automate deciding what a fact means for your offer. The way to keep that honest is to make every automated answer arrive with the line it came from, its link and its date. Here is the test, the shape, and the check.

By Kshitij Maheshwari, co-founder · Updated August 2026 · 11 min read

The four shapes

Spot the four ways a research line goes wrong

Almost every bad automated line is one of four shapes, and all four land with the one person alive who can falsify them instantly. Learn the four and you can catch one without reading two hundred emails.

The shape How it reads in an email The check that catches it What the check costs
The confident invention "Saw you opened a Berlin office last month." Open the link the step gave you and search that page for five words of the quote. Opening one page.
The horoscope "Noticed you are scaling the sales team this year." Put a competitor's name in and read it again. Still true means it says nothing. One swap, before you write.
The true and pointless "I see you run a help center on Zendesk." Ask what the fact makes them responsible for this quarter. Nothing means it is trivia. One question, in your head.
The wrong company "Following your move to a four-day week." Match the domain on the source link against the domain you are sending to. One look at two addresses.

No published measurement exists of how often an automated research line is wrong: no vendor publishes an error rate for its own research step, and no research institution has measured one. The four shapes come from the mechanism, and from the check that catches each.


The test

Ask whether someone could point at it

One question decides what you automate, and you can run it on the step in front of you before you finish reading this paragraph.

Definition

The show me the line test: could a person answer this by pointing at one line on one page? If yes, a machine can. If the answer only exists after somebody decided what that line means for your business, that part stays yours.

A machine can point at it
  • What did their changelog say shipped last month?
  • Which payment providers are named on their integrations page?
  • How many locations does their contact page list?
  • Which customer does their newest case study name?
Only you can answer it
  • Is that release a problem for them or a victory lap?
  • Does the thing they added replace what you sell, or feed it?
  • Is the person who announced it the person who owns the budget?
  • Does any of it earn you a first line, or is it merely true?

How much research an account is worth is a different question, and our cold email personalization guide settles it. This page starts after that decision, and asks what the automated step has to hand back.

If the step cannot show you the line, you have not automated research. You have automated writing.


The worked example

Make the answer arrive as a row, not a paragraph

Same account, same question, two output shapes. One of them can be checked across two hundred rows and the other cannot.

The question asked of both: did this company ship anything in the last sixty days that touches what we sell?

Don't

Ask for a summary

Acme has been investing heavily in automation and recently expanded its platform, positioning them well for growth.

  • Nothing in it can be opened
  • Checking it means doing the research again
  • It will read like this on every row
Do

Ask for four fields

Yes / "Scheduling now runs on our own queue" / acme.com/changelog / 14 July 2026

  • The claim and its receipt travel together
  • Checking is opening one link
  • An empty answer stays visibly empty

An illustrative walkthrough of the method, not a specific client result. We report real numbers only when they are real.

A changelog is the cheapest surface to test this on, because it is dated, public and theirs. What a release actually entitles you to say is in our product launches signal.


The cheapest fix

Tell it what to do when it finds nothing

One sentence added to the instruction, and your empty rows stay visibly empty instead of quietly becoming fiction.

A step that is never allowed to say "I found nothing" will always find something. Columbia's Tow Center tested AI search tools in March 2025 and found them generally bad at declining to answer questions they could not answer accurately. They give an incorrect or speculative answer instead.

The fix, in one sentence

Write the permission into the instruction: if the page does not state it, answer nothing found and leave the quote blank. Different tools, same habit. Staying quiet is not the default, so you have to ask for it.


The check

Check the lines, not the emails

A column of short quoted lines can be read in one sitting. A stack of finished emails cannot, and the wrongness lives in the lines anyway.

  1. 1

    Open the rows that said yes

    A random sample is mostly rows that found nothing. The expensive errors sit in the confident positives going out this week.

    Exact setting

    Filter: answer is not empty. Sort: send date, this week first.

  2. 2

    Read the quote against the link

    You are checking one thing: whether the page says the line. Whether a bought field is right at all is a different job, and our data enrichment guide owns it.

  3. 3

    Hand it to the other person

    Whoever wrote the instruction reads the output for what they meant. Somebody who never saw it reads it for what it says. On a two-person team, swap.

There is no budget argument for skipping this. Clay's own product documentation, checked August 2026, says you can test up to 10 inputs at a time for free and that test runs do not cost credits.

Want the research layer built so you can check it in a sitting?

Book a Fit Check


The design decision

Decide where a wrong answer is allowed to land

Truth is one of two questions a line has to pass before it sends. The other is permission, and personalization without being creepy owns that one.

The through-line

The same wrong answer costs you differently depending on where you put it. In a filter it costs one skipped account, quietly. In a sentence you sent, it costs the account and your credibility with the one person who can falsify it.

So the column you trust least belongs in the list logic, not in the first line. Same imperfect answer, and the worst case becomes a skipped account instead of a burned one.


How we decide

Count what checking costs before you count what the tool costs

The subscription is the visible number and the small one. What you are buying is a pile of answers somebody now has to look at, and at two people that somebody is you.

1
Price the reading, not the seat

Ask how many rows a week you can honestly open. That number is your sending volume, whatever your plan says.

2
Shape the output so checking is a glance

A quoted line and a link can be scanned. A paragraph has to be researched again, which is why nobody does it.

3
Cut the list before you cut the check

If you cannot check what you are sending, send fewer emails to accounts you can say something true about.

4
Know which ceiling you moved

Automation swaps a limit on how many accounts you can research for a limit on how many you can check.

The three ceilings a seed team runs into are in our seed-stage outbound playbook. Research is the one automation moves rather than removes, and that move is the whole reason the check has to exist.

Operator note
How we run it

We size a campaign by what we can read, not by what we can enrich. When the two disagree, the list gets shorter. It is the least popular rule we run and it has never once been the wrong call.

KM
Kshitij Maheshwari
Co-founder, Real Good GTM

Failure modes

Four ways teams break their own check

Every one of these is a team that built a check, ran it once, and then quietly stopped.

The check outlives the instruction

Every edit makes it a new step, and last week's check does not carry over. Clay's documentation says the same thing mechanically: editing a saved instruction does not change the columns already running on the old one.

The check happens after the send

Reading the emails that went out is not a check, it is a post mortem. The line has already landed with the person who can falsify it.

The builder checks their own work

You read the output for what you meant it to say. That is not a character flaw, it is what writing the instruction does to you, and swapping is the entire fix.

The sample is drawn from rows that did nothing

Twenty random rows are mostly blanks and easy yeses. The expensive mistakes live in the confident positives, and a random sample barely touches them.

!
Caution

Getting their own company wrong

A line that is wrong about the reader's own business is the mistake outbound does not recover from. They know it is wrong in the time it takes to read it, and the more specific you were, the more certain they are that nobody checked.

Do this instead
No line ships without a quoted source line and a link. Both fields empty means the row does not send.

Key takeaways
4 points
  • 1 Automate a step only if a person could answer it by pointing at a line.
  • 2 Ask for four things back: the answer, the line, the link, the date.
  • 3 Make "nothing found" a permitted answer, in writing, or you get a sentence.
  • 4 Check lines rather than emails, and check the confident yeses first.

FAQ

Questions founders ask

Can I automate prospect research without the emails sounding like a robot wrote them?
Yes, and the sound is not the problem. Automate the finding and the fetching, then write the sentence yourself from the line the step handed you. What gets an email deleted is rarely the phrasing. It is a fact that is wrong, generic, or about a different company.
How do I know if the AI made up a fact about a prospect?
Open the link it gave you and search that page for five words of the quoted line. If those words are not there, the row is wrong however well it reads. If the step handed you no link and no quote at all, you cannot know, and that is the thing to fix first.
What should an automated research step actually give me back?
Four things: the answer, the line it came from, the link, and the date. A paragraph is a summary of work you now have to redo. A row is the work with a receipt attached, and it is the only shape you can check at volume.
How many rows should I check by hand?
Fewer than you think, but the right ones. Check the confident positives and the rows actually going out this week. A random sample is mostly rows that found nothing, so it reassures you about the part of the column that was never going to cost you anything.
Why do my personalized lines all sound the same even though they are true?
Because the fact is true of everybody in the segment. Hunter made the point in February 2024: lines like these "would apply to a thousand other prospects with a similar job title and location", which makes them the opposite of personalization. Put a competitor's name in and read the line again. Still true means it is saying nothing.
My tool cites a source. Is that enough?
No. A cited source is a claim about a source. The BBC and the European Broadcasting Union, in October 2025, found cited pages that did not contain the claim, and links to pages that never existed. Treat the link as a place to look, not as proof that somebody looked.
Kshitij Maheshwari, co-founder of Real Good GTM
About the author
Kshitij Maheshwari

Co-founder of Real Good GTM. He has been the first business hire and Chief of Staff at seed-stage B2B startups, building outbound pipeline before any playbook existed. He writes and checks these research columns every week, and this post is the shape he makes them hand back before anything they wrote is allowed to send.

Connect on LinkedIn

Keep going

The questions on either side of this one

How much research to do before this page starts, what the data layer underneath owes you, and the other check a line has to pass.

Want a research layer you can actually check?

Book a fit check. We'll look at what your columns are being asked to answer, what they hand back, and whether the volume you are planning is a volume anyone could check.

Book a Fit Check

No hard sell. No fake numbers. Real good work speaks for itself.