Synthesis

Synthesis

Most people summarize when they should synthesize. Summary compresses what was said. Synthesis names the pattern and forces the implication. This skill does the second thing.

The test: did the output change how the reader will act? If no, you wrote a summary. Rewrite.

Design choices (why this skill is opinionated)

• 3 insights, never more. If you have 5, you haven't synthesized yet — you have themes. Force-rank to 3.
• Headlines are claims, not topics. "Customers will pay 20% more for self-serve onboarding" beats "Customers care about onboarding."
• Every insight ends with a so-what. A claim without an implication is trivia. The so-what tells the reader what to do differently.
• Evidence is specific. Direct quotes, exact numbers, named sources. No "many customers said" — that's compressed mush.
• Synthesis is reductive. You will throw away 80% of the raw input. That's the job. If you keep all of it, you summarized.

Inputs the skill needs (interview if missing)

1. The raw inputs. Interview notes, transcripts, survey data, research, meeting recordings. Paste or link.
2. Who's the reader? Exec, peer, team. Changes the so-what.
3. What decision is downstream? "Should we build X?" "Cut Y?" "Reorg Z?" The synthesis should serve a specific call.
4. What did you go in believing? Your prior hypothesis. (Helps catch confirmation bias and surface true surprises.)

If the decision is unknown, ask before synthesizing. Synthesis without a decision becomes a summary.

The process

1. Cluster (induction, not deduction)

Read everything. Tag each data point with the theme it belongs to. Don't start with themes and force-fit — let themes emerge from the data. You're looking for repeated patterns, not single anecdotes.

2. Force-rank to 3

You'll have 5–10 emerging themes. Cut to 3. Use this rank:

• Frequency (how often did it come up?)
• Severity (how big a deal is it for the decision?)
• Surprise (did it contradict what you went in believing?)

The top 3 by combined rank become the insights.

3. Name each insight as a claim

Each insight is one sentence. It must:

• State the finding (not the topic)
• Be specific (numbers, names, mechanism)
• Be falsifiable (someone could disagree with evidence)

4. Stack the evidence (2–3 bullets per insight)

Under each insight, list the specific data that supports it. Direct quotes, exact numbers, sources. The reader should be able to push back on any insight and you can point to the evidence.

5. Write the so-what (1 line per insight)

For each insight, finish this sentence: "Because this is true, the reader should ___." If you can't fill the blank, the insight isn't sharp enough.

6. Anti-summary check

Read the output. Ask: would a smart person who'd never seen the raw data know what to do next? If they'd say "interesting, tell me more" — you summarized. If they'd say "ok, then we should ___" — you synthesized.

Output format

INSIGHT 1: [Headline claim — one sentence]
Evidence:
- [Specific data point with source]
- [Specific data point with source]
- [Specific data point with source]
So what: [One-line implication for the reader's decision]

INSIGHT 2: [Headline claim]
Evidence: ...
So what: ...

INSIGHT 3: [Headline claim]
Evidence: ...
So what: ...

OVERALL RECOMMENDATION (optional, 1–2 sentences):
[The single thing the reader should do, ladders to all 3 insights]

Optional sections only if asked for:

• What we threw out — themes that didn't make the top 3 and why
• What we'd need to test next — open questions the synthesis doesn't answer

Worked example

Input: 12 customer interviews about why churn is up 8% QoQ. Reader: CEO + Head of Product Decision downstream: What to fix in the next 90 days Prior hypothesis: "Pricing is too high"

INSIGHT 1: Churn is concentrated in customers who never finished onboarding — pricing is a symptom, not a cause.

Evidence:

• 9 of 12 churned customers never completed step 3 of onboarding (team invite). The 3 who did completed all 5 steps and stayed >18 months.
• Customer #4 (Acme Co.): "I never figured out what to do with it, so when renewal came up, $30K felt like a lot for something we weren't using."
• Internal data: customers who complete onboarding within 14 days have 78% retention; those who don't have 31%.

So what: Pricing changes won't fix this. Cutting price preserves the broken funnel; fixing onboarding step 3 is the highest-leverage move in the next 90 days.