Research Report

Answer a research question with a sourced report. The AI drives Scope, Gather, Synthesize, and a review checkpoint.

Universal 6 steps 2 checkpoints Human approval Self-correcting
Use this workflow

Free to start · runs with your own AI

Workflow steps

Runs inside your AI conversation · the orchestrator drives

"Research the market for AI note-taking tools and write it up"

you — in any AI chat

  1. 1

    Question

    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. 2

    Scope

    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.

    The AI pauses here and waits for a human to approve before the conversation continues.
  3. 3

    Gather

    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. 4

    Synthesize

    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. 5

    Final Review

    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.

    The AI pauses here and waits for a human to approve before the conversation continues.
    If rejected → returns to synthesize
  6. 6

    Complete

    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.

  7. Workflow complete — outcome delivered, every step on record.

Why this workflow?

Without a workflow

  • 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

With ConvOps

  • 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

Related workflows

Ready to automate?

Stop re-explaining your process. Pick a template, start a task, and let the AI drive the work through your workflow.