From transcripts to a decision, your way: a blueprint for Research Synthesis

You are the person a client calls when they have a decision to make and the answer is in what customers say. You run the interviews, or you read the transcripts someone else ran, and you hand back evidence a leadership team can act on. You have a method for it. It is in your head, in a coding frame you keep adapting, and in the standards you hold to without ever writing them down.

This page is a blueprint for a Flow Playbook that carries that method. It is not built. AI Consulting is a Playbook that exists today, and its launch story is the walkthrough for every step below. This blueprint is yours to take. Build it from your own know-how, put your name on it, and launch it as your Playbook. If you do, I would like to hear about it.

The opportunity

The insights industry is big and still growing. ESOMAR puts the world total at about $165 billion in 2025, up 6.4 percent. The growth is not even. In 2024, research software grew more than twice as fast as classic research services, 11.5 percent against 4.8. In the US, the Insights Association found the industry reached $89.3 billion in 2025, with research technology now close to half of it. The money is moving toward tools. The judgment still has to come from somewhere.

AI is already in every researcher’s hands. Qualtrics found that 95 percent of researchers use or experiment with AI, and that use of AI built into research software is rising while use of general chatbots is falling. Two in three research suppliers now put generative AI straight into what they deliver, according to GreenBook’s 2025 GRIT Business Outlook. The same report found fewer buyers expect their leadership to raise research budgets. Clients want more insight for the same money, and they want to know how the AI was used.

That is why the rules changed. In June 2025 the ICC/ESOMAR International Code got its biggest revision in almost a decade, with rules for AI, synthetic data and synthetic personas for the first time. A researcher who can show their method, their standards and their disclosure in one place has an answer ready. And the custom GPT many consultants used to package a method retires on December 11, 2026. A Playbook is plain files in your own GitHub. Nobody can retire it.

The signals

Each figure measures something narrower than it sounds. Surveys count who answered. Vendor research counts a vendor’s view. Stated plans are not adoption. Read them as a direction, not a forecast.

What your Playbook holds

The figure at the top of this page is the folder as it could sit on GitHub. Six Markdown files. Here is what each one does.

The README is the front page. It says who the Playbook is for, what a reader will have at the end, and the order to read the documents in. A stepped figure shows your method from transcript to decision. An isometric figure maps the path.

Synthesis Method is the heart of it. How you go from raw transcripts to codes, from codes to themes, and from themes to findings a client can act on. What counts as a finding and what is only a quote. A quality checklist a reader ticks before any claim reaches a client, kept as an Approval Card so the sign-off stays on record.

Standards and AI Rules is where you put the code points you follow, the way you disclose AI and synthetic data in a report, and the things you will not do. Each rule links to its source. What you have not settled yet is marked, and Flow counts the marks until you answer them.

Discussion Guide and Coding Frame holds the questions you ask and the frame you code answers with. A form lets a reader log one interview at a time. The frame is a table they can extend for a new study.

Decision Brief Template is the shape of what you hand back. What the client is deciding, the options, the evidence for each, and a recommendation with its sources. A Decision Brief Skill draws it. An Option Comparison puts the choices side by side on the facts that tell them apart.

Worked Example is one brief from a past study with names and numbers changed, and the choices explained. A reader learns more from one finished brief than from ten rules.

What Flow does for this work

Chat answers from your Standards, and says when they are silent. With the Playbook chosen, Chat searches your documents before it replies and links each fact to its file. Ask How do I disclose synthetic data in a report? and the answer comes from Standards and AI Rules, with the code point linked. If your rules do not cover a case, Chat says so. That is the honest answer a client would want.

A Form logs one interview at a time. The Discussion Guide ends in a Form. The questions you always ask, a day field, and a checklist of consent and recording steps. Its button is Submit, so each interview is recorded beside the document with the researcher’s name. The coding frame is a Table a reader extends for a new study.

A Skill draws the brief’s comparison. Select the options section of a Decision Brief and run Option Comparison. It puts the choices side by side on the facts that tell them apart, using only what the text says, and names what is missing instead of guessing. A Decision Brief Skill draws the brief’s own shape. Both wait in Review Changes until you keep them.

The client records the decision in the brief. A Form with the Decide act records which option the client chose and why, with their name and the day. The record stays beside the document. When you look back at a study a year later, the decision and its reason are there with the evidence.

A Job keeps your code of conduct current. Bring in the code page you follow with New from Web Page and choose Follow the source. When the association revises it, the next Jobs run brings the change into your copy where you have not edited. Your Standards document cites a current clause, not the one from the year you wrote it.

A client’s survey export comes in as a table. Drop in the Excel file and the rows stay rows. The import checklist in the Sources tab asks you to compare the table with its source and note what was left out before you rely on it. A Sources block on the finished brief lists everything it was made from, and marks a source that changed since.

Your agents can work from the Playbook. With Flow Pro, the Claude Code or Codex you run in Terminal can read the Synthesis Method’s reading order, search the Standards and propose a first pass at coding. The proposal lands in Review Changes under the agent’s name. The judgment call on each theme stays yours.

How you build it in Flow

The AI Consulting story walks every one of these steps on a real screen. Follow it with your own material.

1. Add an empty folder and choose it. Chat answers from the folder before any document exists. The walkthrough shows it at an empty folder, and Chat already in it.
2. Ask Chat for the README. Describe who the Playbook is for and what you want a reader to have at the end. Chat writes it in your voice and marks every claim it cannot stand behind. See a front page, in the author’s voice.
3. Bring in what you already have. Your coding frame, a past report with the client’s details removed, the code of conduct page you cite. New from Web Page turns a page or a shared AI chat into a document with its links kept. See an old AI chat became a reference.
4. Let Ideas pick a Skill. Press Suggest on your Method document. Ideas reads the sections and names a Skill for each, a Workflow Path for the steps, a Decision Brief for the template. A figure or a form waits in Review Changes until you keep it.

5. Ask Chat for the next document with your own pages as sources. The Standards document can be written from your Method and the code you follow. Repeat until the path is done. See the next document, from his own pages.
6. Review every change. When you merge two steps or rename a document, every page that pointed at it follows. See Review changed the plan, and the source followed.

Apply it to a client job

A Playbook is for using, not only reading. On a new study, open the Playbook, start a folder for the client and drop the transcripts in. Ask Chat to code them against your frame, and to flag every passage it is not sure about. The Method’s checklist tells you what to confirm before a finding goes in the brief. When the client pushes back on a theme, write what you learned back into the Method. The next study starts from what you learned.

With the Standards document open, you can answer the question every buyer now asks. How was AI used, and what did a person check. The answer is in your Playbook, dated, and the same for every client.

Transcript 01.mdCoded Table.mdFindings.mdDecision Brief.mdDecision Brief.mdDiscussion Guide and Coding Frame.md Imported · 2 to check3 claims to check1 change to review1 change to reviewDecided1 document changed

Northgate Grocers

Transcript 01

Proposed

Sources

Imported · 2 to check

Northgate Grocers

Coded Table

Proposed

Table

3 claims to check

Northgate Grocers

Findings

Proposed

Chart · Bar

1 change to review

Northgate Grocers

Decision Brief

Proposed

Option Comparison

1 change to review

Northgate Grocers

Decision Brief

Proposed

Form · Decide

Decide

Decided

Northgate Grocers

Discussion Guide and Coding Frame

Proposed

Change Summary

1 document changed

01Start the study folder02Code the interviews03Find the themes04Compare the options05Record the decision06Write the lesson back

Publish it, and keep it current

When the folder is ready, choose Publish and then GitHub Repository. Flow sends the files and nothing else. A reader brings the Playbook in with File, then New from GitHub, and the folder’s address.

When you refine the coding frame and publish again, every reader’s copy shows the update as a change they review. They keep their own edits. Nothing is replaced behind their back.

The same source can also become a GitHub Pages site, a PDF, an EPUB, or Word and PowerPoint files for the client’s team. Chat on the Playbook, and the figures a reader steps through, stay in Flow.

What it costs

Bringing any Playbook into Flow is free on Base. Writing with Chat, and Chat on a Playbook, need Flow Pro at $10 a month. Publishing to GitHub needs the Publish add-on too, another $10 a month. There is no fee per Playbook, so publish one or twenty for the same price. Any AI you connect follows the terms of that service. Publishing does not bring clients on its own. It gives the clients you earn a living copy of your method.

Start here

Read the walkthrough once, end to end. Then add an empty folder in Flow, name it, and describe your method to Chat in three sentences. The README it writes is the first document of your Playbook. If you want to talk it through first, the Playbooks page has one email address and four questions.