Research Report AI workflow template: A sourced answer to one question.

The ConvOps Research Report template makes your AI answer one research question with a sourced report: state the question precisely, scope the sub-questions, gather findings with sources and reliability, then synthesize an answer that separates fact from inference. You approve the scope before gathering and the report before it is shared.

6 steps · 2 approvals · 1 loop back

Research Report · example runyour AI client
  1. 01Question
  2. 02Scopewaits for approval
  3. 03Gather
  4. 04Synthesize
  5. 05Final Reviewwaits for approval
  6. 06Completeclosing note
task created · workflow attached

example · the steps are this template's real steps

in short

What does the Research Report template do?

For founders, analysts and marketers who research markets, competitors or options and need every claim tied to a source.

Research Report is stored in ConvOps as six steps, and your AI client receives them one at a time. A Research Report run holds at Scope and Final Review until an explicit approval is given.

  • Research a market and write up the findings with sources
  • Compare competitors and summarize what matters for a decision
  • Investigate an option and lay out the evidence both ways
step by step

How does the Research Report workflow run?

The 6 Research Report steps in order, each with the instruction your AI receives there as Research Report stores it.

Question
Scopeapproval
Gather
Synthesize
Final Reviewapproval
Completeclosing note

A report that answers one question, with each finding's source and reliability recorded and fact kept apart from inference.

  1. 01

    Question

    the agent works

    State the research question precisely before anything else.

    Capture:

    • The question: the specific thing this report must answer
    • Why it matters: the decision or need behind it
    • The audience for the report
    • Any constraints: depth, deadline, sources to use or avoid

    A fuzzy question produces a fuzzy report. If the operator's ask is broad, narrow it with them before advancing.

    Save the question and its context as a task note with task_notes_add. The next step (Scope) reads this note.

  2. 02

    Scope

    waits for your approval

    Read the task notes with task_notes_list: the note from the Question step contains the question and its context. Work from it.

    Scope the research. What good looks like:

    • The sub-questions that, answered, answer the main question
    • What is in scope and explicitly out of scope
    • The kinds of sources you will use
    • The shape of the final report: sections and depth

    Save the scope as a task note with task_notes_add. Then ask the operator to approve the scope before gathering begins. This is a checkpoint: scope drift wastes the most time in research, so the AI cannot advance until you approve.

    no rejection path · the run moves on only when approved

  3. 03

    Gather

    the agent works

    Read the task notes with task_notes_list: the note from the Scope step contains the sub-questions and boundaries. Work from it.

    Gather evidence against each sub-question. For every finding capture:

    • The finding itself, stated plainly
    • The source: a link or citation
    • How reliable the source is and any caveat
    • Which sub-question it answers

    Stay inside the approved scope. Note where evidence is thin or conflicting rather than papering over it.

    Save the gathered findings and sources as a task note with task_notes_add. If it exceeds 10,000 characters, split across notes or store where the operator keeps documents and record the location. The Synthesize step reads this note.

  4. 04

    Synthesize

    the agent works

    Read the task notes with task_notes_list: the Gather note holds the findings and sources, and the Scope note holds the sub-questions to answer. Work from them.

    Write the report:

    • A direct answer to the main question up front
    • Each sub-question answered with its evidence and sources cited
    • Conflicting evidence and uncertainty stated honestly
    • A short conclusion and, if asked for, a recommendation
    • Sources listed so claims can be checked

    Do not assert beyond the evidence. Distinguish fact from inference.

    Save the full report as a task note with task_notes_add. If it exceeds 10,000 characters, split across notes or store where the operator keeps documents and record the location. The Final Review step reads this note.

  5. 05

    Final Review

    waits for your approval

    Read the task notes with task_notes_list: the Synthesize note holds the report, the Gather note holds the sources, and the Question note holds what was asked. Work from them.

    Review the report:

    • It answers the original question directly
    • Every claim is backed by a recorded source
    • Uncertainty and conflicting evidence are surfaced, not hidden
    • It stays within the approved scope and matches the planned shape

    Ask the operator to approve the report. This is a checkpoint: once shared the report informs decisions, so the AI cannot advance until you approve. If you reject, the workflow returns to Synthesize.

    rejected → back to Synthesize

  6. 06

    Complete

    closes with a note

    The research report is approved and ready to share. Confirm the final report, with its sources, is saved as a task note, then close out the task. This note is the named input for a Decision Memo workflow if a decision follows.

reach for it when

  • One precise question needs an answer someone will rely on.
  • Every claim has to point to a source.
  • Scope creep is a risk, so the sub-questions should be agreed first.

something else fits when

  • You already know the facts and need to choose: Decision Memo.
  • The question is open curiosity with no reader waiting for the answer.
  • A quick lookup will do.
example · pharmaceutical market accessenterprise

Reimbursement rules in five EU markets

The question is which markets reimburse a new therapy class. The team lead approves the five-country scope, the agent records each finding with its source, and the final report marks two answers as uncertain.

Scope and Final Review approvals

where approval is required

Where do you approve in Research Report?

Research Report holds at Scope and Final Review until an explicit approval is given, recorded with the account that gave it.

step 2

Scope

Scope drift wastes the most time in research. You approve the sub-questions, the boundaries and the shape of the report before gathering begins.

what you review

  • The sub-questions that, answered, answer the main question
  • What is in scope and explicitly out of scope
  • The kinds of sources you will use
  • The shape of the final report: sections and depth

no rejection path · approve to continue

step 5

Final Review

Once shared, the report informs decisions. The AI checks it answers the question and every claim has a recorded source. Reject it and the run returns to Synthesize.

what you review

  • It answers the original question directly
  • Every claim is backed by a recorded source
  • Uncertainty and conflicting evidence are surfaced, not hidden
  • It stays within the approved scope and matches the planned shape

reject → back to Synthesize

gates the engine checks without you

  • Complete closes Research Report only when your AI leaves a closing note, saved on the task.
what you need

What do you need to run Research Report?

make it yours

How do you customize Research Report?

Once installed, Research Report is a workflow in your workspace. Ask your AI to change Research Report in plain words; the edit lands on the one step that needs it.

ChatGPTexample

new chat

In Gather, only use primary sources: official docs, filings and pricing pages.
workflow_step_update · Research Report
Done. Research Report in your workspace now has the change, and every new run follows it.

more example prompts

  • "In Gather, only use primary sources: official docs, filings and pricing pages."
  • "Add a one-page executive summary to Synthesize."
  • "After Complete, start a Decision Memo with this report as its input."
the difference

Research Report: without a workflow vs with it

  • The research wanders, balloons in scope, and answers a question nobody asked
  • The report states conclusions with no sources, and nobody can check the claims
  • You research for an hour, close the chat, and lose every source and note you collected
  • The Research Report process lives in a prompt, and each run follows it a little differently
  • The AI pauses at a Scope checkpoint so you approve the question and boundaries before any gathering starts
  • The AI drives a Gather step that records each source, so every finding traces back to where it came from
  • The AI saves the scope, the sources, and the synthesis as notes, so a later session resumes the research with nothing lost
  • Your AI receives the 6 stored steps one at a time, and the run holds at Scope and Final Review until an explicit approval is given
questions

Research Report template FAQ

What is the ConvOps Research Report template?

The ConvOps Research Report template makes your AI answer one research question with a sourced report: state the question precisely, scope the sub-questions, gather findings with sources and reliability, then synthesize an answer that separates fact from inference. You approve the scope before gathering and the report before it is shared.

How does it handle weak or conflicting evidence?

In ConvOps, the Gather step records each finding with its source, how reliable that source is and any caveat, and notes where evidence is thin or conflicting rather than papering over it. Synthesize then states uncertainty honestly, distinguishes fact from inference and stays within the evidence, and Final Review checks that every claim is backed by a recorded source.

Does the AI browse the web?

ConvOps holds the question, the scope, the sources and the review; the agent does the research with its own tools, in your AI client or in an isolated run. Whatever tools that agent has, such as web search or documents you share, supply the findings, and the Question step records any sources to use or avoid. Every finding is saved with its source.

What happens after the report?

The ConvOps Complete step confirms the final report, with its sources, is saved as a task note, then closes the task. That note is the named input for a Decision Memo workflow if a decision follows, so the evidence travels with the decision instead of being retyped. Both templates ship together in the Chat Essentials kit.

Why is there an approval at Scope?

Scope drift wastes the most time in research, so the ConvOps Scope step holds the run until an explicit approval is given for the sub-questions, what is in and out of scope, the kinds of sources to use and the shape of the final report. Gathering starts only after that, and the Gather step stays inside the approved scope.