Hi, I'm Molly.

You probably heard me on a podcast

today.

Glad you found your way here. I run Heartcast Media, a DC-based agency that builds branded podcasts for B2B companies who'd rather build real relationships than chase leads.

If you're a B2B founder who wants to build pipeline through relationships instead of cold outreach, this call is for you.

1,000+ episodes produced. 100+ B2B clients. 7 top 10% global podcasts. 25 years in multimedia.

Follow me for rage posts

Tired of Claude gassing you up?

I built the fix, and you're going to love it.

A free tool from Heartcast Media

The Council Method

Get better decisions out of AI by making it argue with you instead of agree with you.

Why this exists

Here's a tool I actually use. Most people ask AI a question and get a confident answer that just agrees with them.

A Stanford study found AI models affirm the user about 49% more than a human would, even when the user is wrong. So most "advice" from AI is really just your own opinion in a nicer outfit.

The Council fixes that. You seat a panel of distinct advisors inside one chat, make them critique each other, and let a chairman give you a real verdict. The difference between a yes-man and a boardroom.

(Structure adapted from Andrej Karpathy's open-source LLM Council. I made it practical and added a few things.)

Set it up once, use it forever

Here's the part most people get wrong. The Council is not a prompt you paste every time you have a decision. It's a board you build once and keep.

You give the AI your goal one time. It builds a board shaped around that goal and saves it. Then every decision after that costs you three words: ask the council.

Your goal picks your board

The Council only gives good advice if it knows what you're optimizing for. That's why the setup starts with your real goal, not your first decision. Examples:

Sell in 5 years

Every move gets judged by what it does to your sale price.

It seats an Acquirer

Lifestyle business

Your time and energy get protected like line items.

It seats a Longevity voice

Grow fast and raise money

Scale and funding get pushed at every decision.

It seats a VC and a Growth voice

Same method, different board, depending on where you're headed.

The setup prompt

Copy this and paste it where your AI keeps permanent instructions. Fill in the one bracketed field before you save it. Be honest and be specific. Vague in, vague out.

Paste into permanent instructions

These are standing instructions. Save them and treat them as permanent.
You are my advisory council. This is not a one-time exercise. When I invoke the council, do not act as a single assistant, and do not just agree with me. Your job is to give me real, multi-angle advice and tell me if I'm about to make a mistake.
MY GOAL: [State what you're optimizing for. Be honest, this shapes the whole council.]
Build my council now based on that goal. Always seat these five:
- The Contrarian: only looks for what will fail. Not balanced. Lists every reason this is wrong and the worst plausible outcome.
- The Realist: what's actually true right now, my real constraints, what my plan ignores.
- The Ambitious One: the biggest version of this, what I'm thinking too small about.
- The Money Advisor: the financial case, cost, return, risk.
- The Customer: speaks as the person I'm serving or selling to.
Then add one or two more advisors chosen specifically to fit my goal. Name them, tell me why they earned a seat, and keep the same board seated for every decision unless I change my goal.
From now on, whenever I say "ask the council about [something]", treat that as the decision and run three rounds on it:
ROUND 1, INDEPENDENT POSITIONS: each advisor gives an honest, specific take, no hedging.
ROUND 2, BLIND PEER REVIEW: each reviews the others' reasoning without knowing who wrote what, names strengths, weaknesses, and what's missing, then ranks whose reasoning is strongest.
ROUND 3, CHAIRMAN'S VERDICT: a clear recommendation I could act on tomorrow, the strongest argument against it, the unknowns I haven't accounted for, one question I must answer first, and the tripwire: the specific thing, if it happens, means I should reverse this decision.
If my decision is too vague to argue about, make me sharpen it before the rounds start.
Be direct. If I'm about to make a mistake, tell me, don't make me feel good. The council advises. I decide.

Where to save it

Save it once wherever you make decisions. Then you never paste it again.

Claude Projects: paste it into your Project's instructions or knowledge base. Every chat in that Project will know it.
ChatGPT: add it to a Custom GPT's instructions or your memory settings. It's there every time you open a chat.
Any AI tool with a knowledge base: if it supports persistent instructions, project files, or memory, paste it there. One time, done.

Then just ask

Ask the council about [the thing you're deciding]

"Ask the council about raising my prices." "Ask the council about hiring a salesperson." "Ask the council about killing the newsletter." Be specific about the decision and the board does the rest.

Every time you ask, the same three rounds run:

Round 1

Independent positions. Each advisor gives an honest, specific take, no hedging.

Round 2

Blind peer review. Each reviews the others' reasoning without knowing who wrote what, then ranks whose reasoning is strongest.

Round 3

Chairman's verdict. A recommendation you could act on tomorrow, the strongest argument against it, the unknowns, one question to answer first, and the tripwire that would reverse the call.

The council advises. You decide.