Skip to main content
The Human Bit
← All playbooks

Practical playbook · comfortable · 20 minutes

Research a topic with reliable sources

Turn a broad question into a bounded, source-linked briefing you can open up, check and argue with.

This is for you when
You need more than a quick answer, and you want to see which claim came from which source rather than take a tidy summary on trust.
What you will leave with
A focused briefing that keeps its links, its disagreements, its gaps and your next questions all in view.

The Human Partnership

Use the capability. Keep the part that needs a person.

Research becomes useful when it changes the quality of a decision. A long report is not evidence of good research unless the scope, sources, disagreements and remaining uncertainty are visible.

AI contribution

Choose a capability for a real job.

Each capability removes a different kind of effort. Its value depends on the human context beside it.

01 · capability

Editable research planning

Deep research features can turn a broad question into a proposed plan, source strategy and sequence of subquestions that the person can review before a long search begins.

The person contributes
The person corrects the decision being supported, the geography, time period, definitions and source priorities before the plan hardens around the wrong question.
Do not assume
A comprehensive plan can still be precisely aimed at the wrong decision, especially when the original request contains hidden assumptions.
02 · capability

Web, file and connected source retrieval

Research can combine public web material with selected files or connected services such as Drive, Gmail or approved internal repositories, allowing external claims to be tested against organisational context.

The person contributes
The person chooses which systems may be searched, distinguishes authoritative records from convenient context, and protects information that should not be included.
Do not assume
Access does not equal authority. A connected file may be outdated, informal or written for another purpose, while important paywalled or offline evidence may remain invisible.
03 · capability

Citation linked synthesis

AI can group claims, compare sources, surface disagreement and produce a report with links so the reader can move from summary back to evidence.

The person contributes
The person opens the load bearing sources, decides whether the evidence applies locally, and separates a source statement from the tool's inference about it.
Do not assume
A citation can exist and still fail to support the sentence beside it, and multiple tools may repeat the same weak source rather than provide independent confirmation.

Human expertise

The resources already inside the work.

Experience, relationships, definitions and accountability are inputs to the workflow, not a final check after AI has finished.

Decision framing

You know what action the research must support, which uncertainty is blocking progress, and what level of confidence is sufficient for the consequence involved.

Source and domain judgement

You can recognise primary evidence, conflicts of interest, outdated guidance and definitions that sound similar but mean something different in your field.

Local applicability

You know whether published evidence fits your organisation, population, jurisdiction, systems, budget and operating reality.

Shared workflow

See where the work changes hands.

The useful pattern is not one prompt followed by one check. The person and AI shape the work at different moments.

  1. 01 · person

    Turn the topic into a decision

    State what must be decided, what is already known, the time and geographic boundaries, and which source types should carry the most weight.

  2. 02 · ai

    Propose the research route

    Research planning and source selection controls

    Generate a research plan, candidate questions and source strategy for review before using deep research, web search, uploaded files or connected sources.

  3. 03 · together

    Interrogate the emerging evidence

    Refine the search when terms are ambiguous, important viewpoints are absent, or early evidence suggests the original framing was too narrow.

  4. 04 · decision

    Decide what the evidence earns

    The person decides which conclusions are supported, which remain provisional, and whether more evidence, a subject matter expert or a real world test is required.

  5. 05 · verification

    Open the claims that carry the decision

    Read the most important sources directly, check publication dates and jurisdiction, trace quotations and numbers, and record what the search could not find.

The decision stays human

Someone must be able to stand behind the result.

The person decides whether the evidence is credible, relevant and sufficient for the real decision. AI can assemble and challenge a case, but it cannot set the organisation's evidence threshold or accept the consequence of being wrong.

Verification required

  • Open every citation that materially changes the recommendation or conclusion.
  • Check whether the source is primary, current, independent and relevant to the correct jurisdiction or population.
  • Separate sourced facts, the tool's own inferences, unresolved disagreement and information that could not be found.
  • Look deliberately for evidence against the emerging answer and for sources outside the easiest searchable material.

Failure to watch

The main failure is false confidence through volume. A long, cited report can hide a poor research question, repeated secondary sources, missing evidence and conclusions that travel further than the sources allow.

Skill strengthened

Evidence judgement

Used well, the workflow strengthens question framing, source evaluation, uncertainty handling and the discipline of matching the strength of a conclusion to the strength of its evidence.

Worked example

Watch the judgement change the draft.

The first pass is useful. The human correction is what makes it specific, appropriate and worth using.

01 · Input

The honest starting point

Research heat-pump options for a small Melbourne office before a lease renewal. Prioritise official efficiency guidance and installer-independent sources.

02 · AI draft

A useful first pass

Briefing: three system categories, likely building constraints, links to government guidance, and a short list of assumptions about floor area and existing electrical capacity.

03 · Human correction

Context changes the answer

The reviewer opens each citation, drops one that was written for a different climate zone, adds the building's real electrical limit, and marks installation cost as unknown until quotes come in.

04 · Final result

The version a person can stand behind

A two-page decision briefing with verified official guidance, the building-specific unknowns named plainly, and five questions to put to qualified installers.

Try it on your work

Start with the real material.

Remove anything you cannot share, fill in the brackets and keep the decision and verification steps visible.

  • When you need one current fact, go straight to the authoritative source instead of commissioning a whole briefing.
  • Do not trust a citation until you have opened it, because the longer the report runs the easier it is for an invented source or a link that does not back the claim to slip through.
  • Treat one of these reports as a fast parse of what is already published, not new insight: it skews toward whatever is easy to find, so anything paywalled or off the beaten path simply never makes it in.
  • Watch for a briefing that agrees with the answer you clearly wanted, and remember that two tools agreeing is weak comfort when they were trained on much the same material.

Research [topic] to help me decide [decision]. Focus on [country/industry] and information from [time period]. Prioritise primary sources and credible independent analysis. Compare the strongest options, disagreements and unknowns. Link every material claim. Finish with what the evidence supports, what it does not support and five questions I should investigate next.

Tools that can support this

Pick the tool after the job is clear.

These are evidence backed starting points, not universal winners. Open a guide or ask Bit to help you weigh the fit.

Keep going

Build the next useful skill

Reviewed
Review by
Owner
The Human Bit editorial

The Human Bit Weekly

The useful changes, not every launch.

One short issue every Monday. What changed, what it means for your work, and the part that stays yours.

The Human Bit records when and how consent was given. Subscription is confirmed only after the email provider accepts the request.