Messy Ledgers In, a Flagged Earnings Draft Out
Thread AI Editorial · June 15, 2026
Before a private equity firm or corporation buys a company, the buyer needs to know how much of that company’s profit is real and will last. Analysts manually go through financial records, often spread across several systems, before any analysis begins.
With Lemma, a Worker handles the groundwork. It sorts through the records and drafts a first-pass report, flagging the costs worth a closer look. Analysts start from a draft instead of raw data, and a specialist signs off on every adjustment before it counts.
What Lemma delivers
Fewer analyst hours per engagement
As the team starts by reviewing flagged first-pass reports.
A faster draft quality-of-earnings report
Enabling earnings issues to surface while there’s still time to act.
More engagements from the same team
As deal teams spend less time on data prep and more on judgment calls.
The Challenge
When a private equity firm or corporation buys a company, it typically hires an external firm to run a quality-of-earnings review, which shows how much of the company’s reported profit is high quality and will last.
The review starts with the company’s full transaction record, often spread across several accounting systems that categorize expenses differently. Analysts must first merge everything into one format, then comb line by line for costs that distort the picture, like an owner’s personal expenses or a one-time legal settlement.
Under deal deadlines, most of the team’s time goes to finding these issues by hand, which is slow, expensive, and hard to scale.
The Solution
The diligence team built a Worker on Lemma that pulls transaction records from each of the company’s accounting systems and merges them into one format. The Worker then flags costs that may need adjusting, like one-time items, and links each flag to the transactions behind it so analysts can check it quickly. The team added a human-in-the-loop step so that nothing goes into the review until someone approves it.
Analysts now start with a draft of flagged adjustments instead of raw data, and the firm can take on a company built from many acquisitions without needing to staff up the engagement.
Lemma Capabilities
Clean data from messy systems.
Code, not AI, converts each accounting system’s export into one format, then checks the result against the company’s own totals.
The AI never supplies a number.
The model identifies which transactions belong to each flagged item and explains why, citing the evidence. Every dollar figure is calculated in code from the company’s actual records, so no total can be invented.
Built-in data checks.
At each step, checks confirm that no transaction was dropped, double-counted, or made up, and that everything the draft cites actually exists. If any check fails, the run stops instead of producing a flawed report.
Required sign-off.
A specialist reviews every flagged item before the final report exists, correcting pre-filled entries rather than starting from scratch. Every decision is logged, giving the team a record to defend each adjustment in negotiation.
What’s Next
With the groundwork handled, the firm’s analysts can spend their time on the judgment calls that shape a deal, and every adjustment they bring to the negotiating table comes with the transactions to back it up. Buyers get a clearer read on a company’s earnings earlier in the process, while there’s still room to act on what they find.
Does this sound familiar?
Your data lives in several systems, and none of them label things the same way.
Every new project starts with days of cleaning and merging spreadsheets.
Your most experienced people spend hours hunting for problems in the data before they can weigh in.
Taking on a bigger project means adding more people.