Anjin Media
← All edit briefs

Research and evidence · Ready to copy

Compose a customer evidence reel.

Find what customers actually said across selected interviews, preserve necessary context and give decision-makers a concise, traceable view of the evidence.

FOR
Customer researchers, insights teams and product marketers
SOURCE
Two to four selected customer interview sessions
OUTPUT
A theme-led evidence reel with speakers and source timecodes
TARGET
2 to 4 minutes

01 · The instruction

Copy this editing brief.

Replace any bracketed variables, select the relevant recordings and keep the review checkpoint before rendering.

EDIT BRIEF

Across these selected customer interviews, find complete statements that answer: [research question or product claim]. Compose a 3-minute evidence reel that opens with the clearest expression of the shared problem, groups supporting observations by theme and includes a meaningful contrasting or qualifying perspective before the close. Identify every speaker and retain source timecodes. Do not merge partial quotations into a claim that no participant made. Prefer specific experiences over generic praise. Return the cut plan for research or legal review before rendering. Use Anjin Media directly, or the Anjin Media MCP when running this through an AI agent, so the proposed edit remains grounded in the selected source footage and can be reviewed before rendering.

02 · Source material

Give the brief enough evidence to work with.

01

Two to four relevant interview sessions selected for this composition.

02

Participants named or assigned approved neutral labels.

03

A precise research question, proposition or decision the reel should inform.

04

Recorded consent and usage rights managed by the organisation outside the editing brief.

03 · Representative example

Four interviews, one decision-ready evidence trail

A representative study asks how customers experience implementation. Three participants describe delayed handoffs, while one explains the condition under which the existing process works. The reel shows the pattern and the exception.

SOURCES

4 interviews

MATERIAL

186 recorded minutes

QUESTION

Where does implementation stall?

DELIVERABLE

03:00 evidence reel

04 · Reviewable plan

The proposed cut structure.

01

QUESTION

Interview 02 · 11:08–11:29

Participant B

Express the shared problem with a concrete experience.

02

PATTERN

Interview 01 · 24:10–24:42

Participant A

Show the first recurring handoff failure.

03

PATTERN

Interview 04 · 16:51–17:23

Participant D

Confirm the pattern from a different organisation.

04

CONTRAST

Interview 03 · 31:04–31:39

Participant C

Preserve the condition under which the process succeeds.

05

IMPLICATION

Interview 02 · 37:15–37:48

Participant B

Close on the operational consequence, not invented analysis.

05 · Editorial reasoning

Why this composition works.

  1. 01The organising question is explicit, so retrieval is evaluated against a real decision rather than a vague request for highlights.
  2. 02Specific recorded experiences carry more evidential value than generic positive statements.
  3. 03A contrasting case prevents the reel from presenting selected footage as unanimous evidence.
  4. 04Speaker labels and source ranges let researchers return to the full interview before drawing conclusions.

Review before render

Keep human judgement in the loop.

  • Check participant consent and permitted use outside Anjin.
  • Verify every statement in its surrounding interview context.
  • Confirm that contradictory or minority perspectives are represented fairly.
  • Separate recorded evidence from the organisation's interpretation of it.

06 · Change the angle

Alternative briefs to request.

A research-only theme reel

Find all complete statements related to [theme]. Keep them in interview order, include contradictions and return a timestamped selects reel without adding a marketing conclusion. Use Anjin Media directly, or the Anjin Media MCP when running this through an AI agent, so the proposed edit remains grounded in the selected source footage and can be reviewed before rendering.

A customer proof edit

Compose a concise customer proof edit around [approved proposition]. Use specific outcomes stated by participants, retain necessary qualifications and flag any line requiring claims review. Use Anjin Media directly, or the Anjin Media MCP when running this through an AI agent, so the proposed edit remains grounded in the selected source footage and can be reviewed before rendering.

A decision-maker summary

Create a 90-second summary containing the clearest problem, two independent supporting examples and one implication for the specified decision. Preserve participant labels and source timecodes. Use Anjin Media directly, or the Anjin Media MCP when running this through an AI agent, so the proposed edit remains grounded in the selected source footage and can be reviewed before rendering.

07 · Boundaries

Common failure points.

The research question is too broad

A request for everything important produces a shallow compilation. Name the decision, proposition or theme the evidence must address.

Only confirming quotations are requested

Include meaningful exceptions and contradictions so the reel does not misrepresent the source set.

Generic praise replaces evidence

Prioritise described behaviour, outcomes and circumstances over adjectives such as easy or great.

Editing is mistaken for research analysis

The reel retrieves and composes recorded evidence. Researchers remain responsible for sampling, interpretation, consent and conclusions.

Questions about customer interview evidence reel

Can Anjin search several customer interviews at once?
A composition can use one to four selected source groups, allowing a brief to retrieve relevant moments across several interview sessions while retaining each source.
Does Anjin conduct qualitative research analysis?
No. It can search transcripts and compose source-grounded evidence around a clear brief. Sampling, coding, interpretation and research conclusions remain human responsibilities.
Can customer speakers be named?
Yes. Diarised speakers can be assigned readable names or approved participant labels before planning.
How can reviewers verify a quotation?
Each planned segment retains its source group, speaker and start and end timecodes so a reviewer can return to the original context.
Does Anjin manage participant consent or media rights?
No. The organisation remains responsible for consent, permitted use, rights and access governance for uploaded recordings.

Use the instruction

Start with the footage you already have.

Copy the brief, select the relevant recordings and review the proposed structure before rendering.