ZeroTwo for consultants
Prompts for consultants
The work consultants actually hand over: cited briefs, interview synthesis, defensible exhibits, proposals and the monthly report that runs again next cycle. Open one to start it in ZeroTwo with the prompt already written.
- Your sources stay attached
- Gaps flagged, not filled
- You keep the recommendation
Prompts for consultants
How do I check an AI research summary is accurate?
Verify every citation resolves to a real, retrievable source on the first run, then sample after that.
- Brief_v4.docx
What should I do when two sources disagree?
Show the disagreement and judge credibility. Averaging two conflicting figures produces a number nobody will defend.
How do I know what the evidence cannot tell me?
Ask for the unknowns explicitly, or they get quietly filled in with inference.
How do I write a consulting research brief?
Keep fact, inference, unknown and recommendation strictly separate — that separation is what makes the brief defensible.
- Market_assessment.pdf
- Industry_report.pdf
How do I prepare for a client pitch quickly?
Brief yourself on the business, what changed recently, and the questions they will open with.
How do I synthesise stakeholder interviews?
Theme them with verbatim quotes and speaker roles attached, and keep their vocabulary rather than translating it into yours.
- Interviews_01-12.md
How do I find the contradictions in my interview notes?
Ask for them as their own list and leave them unresolved — the disagreement between stakeholders is usually the finding.
- Interview_notes.md
Which discovery questions did the research actually answer?
Check the evidence against the questions you went in with, before you start writing the deck.
- Discovery_brief.docx
How do I check a dataset before putting it in a client deck?
Find the gaps, duplicates and small base sizes first, and ask honestly whether the data supports the argument.
- Survey_export.xlsx
What should a chart footnote include?
Source, base, date and method — plus a label on any segment too small to stand on its own.
- Segment_data.xlsx
Apply our house chart conventions
Reformat exhibits to your firm's standards without touching a single number.
- Brand_standards.pdf
How do I turn discovery call notes into a proposal?
Mirror the client's problem in their own words, then phase the scope and make the exclusions explicit.
- Call_notes.md
- Proposal_template.docx
How do I write a scope of work that protects me?
A proposal persuades; a scope of work defines. The exclusions and acceptance criteria are what stop the project drifting.
- Proposal_final.docx
How do I plan a client's first 90 days?
A 30-60-90 plan, the information you need from them this week, and an agenda for the kickoff.
- Signed_SOW.pdf
How do I review a deliverable before the partner sees it?
Get a prioritised issue list rather than a rewrite, and flag anything you could not defend in the room.
- Draft_readout.pptx
How do I stop re-explaining the project to AI every session?
Write the standing context once — client, question, method, evidence standard, what is ruled out — and reuse it.
How do I regenerate a monthly client report without rebuilding it?
Keep the reporting contract from last cycle, update the evidence, and surface what changed.
- Last_cycle_report.docx
- This_month.xlsx
Where is my delivery margin actually going?
Compare delivered hours against the scoped estimate, project by project, with a table you can check.
- Timesheets.xlsx
Prompts are starting points. Filenames shown are placeholders — attach your own.
In short
ZeroTwo is an AI workspace for consultants who have to turn scattered client context into a defensible deliverable. It handles the mechanical part of the work — gathering, extracting, synthesising and formatting — while keeping every claim tied to its source, surfacing contradictions instead of averaging them, and leaving the recommendation to you.
How a prompt becomes a deliverable
A prompt starts the work; it is not the work. Every card above runs the same four beats, and stops in the same place.
Inputs, as they are
Transcripts, exports, the client's own documents, last cycle's deck. No re-typing or restructuring first.
A plan you can adjust
ZeroTwo shows what it intends to do. You set the source boundaries before it starts.
Assembly, with sources kept
Claims stay tied to the line they came from. Gaps and conflicts are surfaced, not smoothed over.
A first-review artifact
Complete enough to review against a written standard. Not a signed deliverable.
ZeroTwo stops at the judgment
The approval boundary is a product feature, not a disclaimer. ZeroTwo does the assembly. You keep the part the client is actually paying for.
ZeroTwo does
- Gather and organise the inputs
- Extract, theme and cross-reference
- Keep every claim tied to its source
- Surface gaps and contradictions
- Format to your conventions
You do
- Set the source boundaries
- Resolve the contradictions
- Verify the arithmetic
- Write the recommendation
- Sign it and send it
Against what you are doing now
| Approach | Where it works | Where it breaks on a deliverable | ZeroTwo's difference |
|---|---|---|---|
| General chat assistant | Fast answers, flexible, already paid for | Stops at a draft. consultants own the path across files, slides and sheets, and re-explain the project every session. | Context and sources persist across the whole engagement |
| Specialist point tool | Deep fit for one format or step | Work fragments across the rest of the process; each tool holds a different half of the context. | One accountable path from inputs to artifact |
| Doing it by hand | Trusted method, clear accountability | Senior time goes to production and cleanup; recurring work restarts from memory each cycle. | The second run reuses the first run's method |
| A contractor | Human judgment, flexible capacity | Lead time and context transfer exceed the window when the deadline is days away. | Available at the moment the brief lands |
Questions consultants ask first
Will the output actually be client-ready?
It is a complete first-review artifact, not a signed deliverable. Each workflow states its acceptance criteria up front, so you can check the output against a written standard rather than a feeling.
Can I trust the citations?
Claims stay tied to sources you can open, and the citation check is the first acceptance gate. Verify all of them on the first run, then sample. One fabricated source should end your trust, so the workflow is built to be checkable.
Do I have to start with client data?
No. Run the first pass on public, synthetic or sanitised inputs. For interview synthesis in particular, confirm your recording consent covers processing before real transcripts go anywhere.
Will it understand our method?
Your brief structure, evidence standard and chart conventions are saved as project context and reapplied. The point is that the second and third run cost less than the first.
Does this replace the analyst?
It removes the extraction and formatting, which is the part that delays the thinking. Judgment, source boundaries and the recommendation stay with the person whose name is on the work.
How does pricing work for real workloads?
Plans are credit-based, so a long research run and a one-line question do not cost the same. See the pricing page for current tiers and monthly credit allowances.
Takeaways
- ZeroTwo takes a consulting deliverable from scattered inputs to a reviewable artifact, not to a draft.
- Claims stay attached to sources, and contradictions are surfaced rather than averaged away.
- Each workflow ships a written definition of done you can review against.
- Judgment, source boundaries and the recommendation stay with you by design.
Where this runs
The surfaces consultants use most once a prompt is running.
Run the prompt against 60+ models in one thread
Work agentHand off a multi-step task and watch the plan
AI workspaceProjects, files and context that persist between runs
Document analysisAsk questions across a folder of PDFs and exports
Agent platformApproval gates, tool access and model choice
Data analysisTurn a dataset into a checked, footnoted exhibit
Further reading
Worked examples of this kind of delivery, written up in full.
Build a sourced packet with an explicit review loop.
Client content calendarTurn approved themes into a reviewable production plan.
Executive readout sprintPackage research into a source-linked client readout.
Feedback revision planTranslate client comments into controlled revisions.
DeepSeek delivery harnessEvaluate model use inside a client-delivery quality gate.
ZeroTwo for
Cited briefs and defensible exhibits
Fractional executivesProposals, SOWs and monthly reports
MarketingCampaign packs and client reporting
SalesAccount research and pitch responses
Start with the last deliverable that ran late.
Open a prompt above, run it on inputs you are comfortable sharing, and judge it on the artifact.