Get started with Prism

How to get a useful verdict, how to read it, and how to get better ones over time.

6 min readUpdated November 2026Prism v0.7

In short1Bring a choice between options, not an open question.2Give it the few facts the decision depends on: prices, clients, capacity.3Read the main risk and what would change the verdict, not only the verdict.4Do the first action within 48 hours, then write down what actually happened.
01

Bring a decision, not a question

Prism works on a choice between options, with something at stake. Open questions get an answer about what Prism can do, not a council.

"How do I find more clients?""For the next 3 months, should I post on LinkedIn twice a week or ask my past clients for referrals?"
"Is my pricing right?""Should I raise my day rate from €600 to €750 for new clients, or keep it and add a premium package?"
"What am I missing in my business?""Should I drop my training offer to focus on Notion setups?"

Two or three options are enough. If your options aren't clear yet, Prism asks one question to get them.

02

Give it your context

Keep dated facts current

Facts older than three months get a re-check prompt before the council runs with them.

03

Read the verdict

Every run ends with one of four outcomes.

VerdictA clear call between the options you gave it.
Top 3No clear winner: the three strongest paths, ranked.
Not yetMissing facts matter more than opinions here. Prism names what it needs.
EscalateOutside Prism's lane: legal, tax, or a decision that needs a professional.

Three lines matter more than the verdict

For a client-facing decision, the verdict also includes an objection to prepare for: the pushback you're most likely to hear.

What a verdict looks likeFormat example

Prism: {your decision}

Verdict: {the call}

Why: {the reasoning in one or two lines}

Main risk: {what could make this wrong}

Objection to prepare for: {the likely pushback}

What would change this: {the fact that would flip it}

Do first: {the one next action}

04

Look behind the verdict

Ask "show the council" to see:

This is where disagreement between advisors shows up, and it's often more useful than the verdict alone.

05

After the verdict

  1. Do the "Do first" action within 48 hours, before the decision loses momentum.
  2. Add the result to your context document, dated, once you know it.
  3. Keep a short log of what you decided and what happened. Prism can write the entry for you.

Store outcomes, never verdicts

Don't paste Prism's past verdicts back into your context document. Past verdicts bias the next council; outcomes don't.

06

When it goes wrong

The verdict feels generic

It likely ran with low context. Add the 2 to 4 facts the decision actually depends on and ask again.

It didn't run the council

Your platform may not support the independent-advisor pipeline. Use Claude Code for the full council.

The result says "Reduced Prism"

The council ran in sequence instead of independently, because the platform couldn't parallelize it. The verdict still stands, with less diversity between advisors.

It's slow, or uses a lot of my limit

Five advisors plus two reviews and a check is a real workload. Save it for decisions worth that cost, not everyday questions.

Is it advice I can rely on?

It's a structured second opinion, not a professional one. Legal, tax, and similarly regulated questions get escalated rather than answered.

Ready for your first decision?

Download for ClaudeAbout Prism Feedback

Writing, not deciding? Plume writes in your voice.