You've just wrapped a two-week sprint of expert network calls. Fifteen calls through GLG or AlphaSights, a mix of former operators, industry analysts, and supply chain specialists. The calls were excellent. The insights were sharp. And now they're sitting in a shared drive, scattered across six different analysts' note documents, slowly becoming irrelevant as the deal deadline approaches.
This is the standard story at most private equity firms, strategy consultancies, and corporate development teams. Expert network calls are treated as an input to a conversation, not as structured data. The result is that a £15,000 investment in primary research gets summarised by whoever wrote the first draft of the deck, filtered through memory and recency bias, with no reliable way to verify that what ended up on slide twelve actually reflects what fifteen experts collectively believed.
There is a better way, and it doesn't require more time. It requires a different approach to how you handle the output.
The synthesis problem in one sentence
The calls are almost never the problem. The synthesis is.
When fifteen experts have each said something interesting, the question is not "what did any one of them say?" — you already know that. The question is "what did they collectively say, where did they agree, where did they diverge, and which divergences actually matter?" That question is impossible to answer reliably by reading notes sequentially and writing a summary from memory.
This is the problem Skimle solves for expert call programmes.
Getting your calls into Skimle
The starting point is your call notes or transcripts. Skimle accepts both: if your team records and auto-transcribes calls (via Otter, Fireflies, or the native transcription in Zoom or Teams), you can import the full transcripts. If your analysts write structured call notes, you can import those as documents instead. Both work.
If you're running a programme across multiple analysts, it helps to agree on a basic note structure before the calls begin: expert profile, key topics covered, three to five direct quotes, and a brief synthesis statement per call. This doesn't need to be elaborate. The goal is to ensure each document is readable by Skimle as a coherent account of a single conversation. The practical interview setup guide covers the transcription and import workflow in detail if you're starting from audio.
Once your call notes or transcripts are in Skimle, the analysis can begin.
How Skimle reads across the full call set
Once imported, Skimle reads all the documents and builds a theme structure from the bottom up. It does not start with a list of categories you've defined in advance. It discovers what topics the experts actually discussed, across the full set of calls, and organises them into a coherent structure.
For a typical commercial due diligence call programme, the themes Skimle surfaces might include competitive dynamics, customer behaviour and switching costs, pricing pressure, operational risks, management quality, regulatory environment, and technology differentiation. But it will also surface things you weren't explicitly asking about. A cluster of experts mentioning a specific distribution risk, a pattern of concern about a particular customer segment, a regulatory development that came up in three calls but wasn't on your question list.
This is the part that manual synthesis consistently misses. When you're reading notes sequentially and writing a summary, you find what you were looking for. Skimle finds what's actually in the data, including the things you didn't know to look for. The thematic analysis guide explains the methodological basis for this; for a call programme, the practical result is that you surface the full picture rather than the picture shaped by your existing hypothesis.
Exploring what experts collectively said
Once the themes are identified, you can interrogate the dataset properly. Skimle shows you, for each theme, which calls it appeared in and what was said. You can see where there is genuine consensus across the call set, and where views diverge.
Divergence is often the most interesting signal. When six experts express concern about competitive pressure but four are relaxed about it, the question is why. Skimle shows you the specific language each group used, which makes it possible to understand whether the divergence is driven by different time horizons, different customer segments, different geographies, or something else entirely. That level of nuance is simply not available when your synthesis is built from a narrative summary.
You can also ask Skimle specific questions about the data: what did experts say about management quality? What was the range of views on pricing? For each question, Skimle shows you the relevant passages from the source documents, not a generated summary. You're reading what the experts actually said, organised by topic, rather than a paraphrase of a paraphrase.
The transparency model matters here. When an investment committee asks "where does this claim come from?", you can show the specific call notes and quotes, not just cite "the expert call programme." Every finding in Skimle is traceable directly to source material.
Preparing the deliverable
Most expert call programmes end in a section of a CDD deck, a briefing memo, or an investment committee presentation. Skimle generates a structured report across the call set that covers the main themes, the distribution of views, and the key supporting quotes. This is a working document for the analyst, not a polished client output, but it gives you the structured foundation from which the final deliverable is written.
The difference from the conventional approach is that you're writing from a complete, organised picture of the data rather than from memory and selected notes. Claims in the deliverable can be traced back to specific calls. Divergent views are explicitly represented rather than silently averaged away.
For a high-stakes deliverable like an investment committee presentation, it is worth including an appendix with the full call programme summary: how many experts, what types, what they collectively addressed. This gives reviewers the context to assess the weight of evidence, and it demonstrates methodological rigour in a way that vague references to "expert interviews" do not. The board meeting preparation guide covers how senior audiences engage with evidence-based claims and what they typically push back on.
What this looks like in practice
A PE analyst running a fifteen-call programme on a software business in the logistics sector imports all call transcripts into Skimle at the end of the first week of calls. Skimle structures the themes across the ten calls completed so far. The analyst reviews the theme view, adds five more calls over the following week, and Skimle updates the analysis with the new material.
By the time the call programme closes, the analyst has a structured view of what fifteen experts said across twelve distinct themes, with every view traceable to a source call. The cross-call synthesis that would normally take a full day of reading and writing takes a couple of hours of review and editing. The findings are more complete, more defensible, and more useful to the partners reviewing the work.
This is not a different methodology. It is the same methodology, executed with the discipline that the volume and value of the material requires.
If you're working with expert calls alongside other document types, such as management presentations, data room documents, or industry reports, the import and export workflows guide covers how to bring multiple source types into a single Skimle project and analyse them together.
Ready to get more from your expert call programmes? Try Skimle for free and see how structured theme coding and cross-call synthesis can turn your call notes into a queryable research asset. Or read more about how Skimle supports consulting and due diligence workflows.
Related reading: How to summarise expert interviews | Thematic analysis: a complete guide | How to analyse interview transcripts
About the authors
Henri Schildt is a Professor of Strategy at Aalto University School of Business and co-founder of Skimle. He has published over a dozen peer-reviewed articles using qualitative methods, including work in Academy of Management Journal, Organization Science, and Strategic Management Journal. His research focuses on organisational strategy, innovation, and qualitative methodology. Google Scholar profile
Olli Salo is a former Partner at McKinsey & Company where he spent 18 years helping clients understand the markets and themselves, develop winning strategies and improve their operating models. He has done over 1000 client interviews and published over 10 articles on McKinsey.com and beyond. LinkedIn profile
Frequently asked questions
How do I get my call notes into Skimle if my team uses different note formats?
Import them as-is. Skimle reads each document independently and builds themes from the content, so inconsistent note formats across analysts don't prevent the analysis from working. That said, consistent notes produce richer results: if some analysts capture detailed quotes and others write bullet summaries, the theme analysis will be better-supported for the detailed notes. A brief team alignment on note structure before the programme starts is worth the ten minutes it takes.
How do I handle calls where the expert covered very different ground from the others?
Leave them in. Skimle's theme discovery accounts for the full range of topics across all documents. An expert who raised something no one else mentioned will surface that topic as a theme with a single source document. That's not a problem to fix — it's the data telling you something that came up once. You decide whether it's a signal worth pursuing or a one-off that doesn't affect the overall picture.
Can I add calls to the project as the programme is still running?
Yes. You can import documents incrementally and Skimle updates the theme analysis to reflect the new material. In practice this means you can review a preliminary theme view after the first ten calls, spot any gaps in coverage, and adjust the remaining calls accordingly before the programme closes.
How do I use Skimle's output when writing the final deliverable?
Use the theme view and the report as your working document, not as the final output. Read the structured summary of each theme, check the source quotes, and write the deliverable section from that organised picture of the data. The advantage over conventional synthesis is that you're writing from a complete view of the call set rather than from memory and selected notes, so your claims are grounded in the full evidence rather than the most recent or most memorable calls.
How does Skimle handle non-English call transcripts?
Skimle analyses documents in multiple languages and applies consistent theme coding across them. For a cross-geography call programme where some experts were interviewed in English and others in German or French, you can run the full programme as a single project and get a unified theme view across all calls. The multi-language analysis guide covers this in more detail.