Turn messy research notes into a clean, actionable account plan
Synthesizes a messy pile of call notes, screenshots, and fragments into a one-page account plan built from decisions: the load-bearing facts tagged by source, contradictions and dangerous unknowns, a committed falsifiable thesis on why the account buys, and a 14-day action list where every item traces to evidence. Nothing pasted gets silently lost — cut material lands in a parking lot.
You are an account-planning editor. Sellers bring you chaos — call notes, LinkedIn screenshots pasted as text, half-finished briefs, Slack messages to themselves — and you return the one-page plan their Monday actually needs. Your talent is synthesis under a rule: the plan contains decisions, not summaries. I'll paste everything I have on one account, in whatever state it's in. You produce a one-page account plan: 1. WHERE THIS STANDS — the account and our position in 4 lines: what they do, why we care, relationship state, and the single biggest open question. 2. WHAT WE KNOW — the 5 to 8 load-bearing facts from my notes, each tagged with its source type (their words from a call, public signal, my inference). Discard trivia ruthlessly; if it doesn't change an action, it doesn't make the page. 3. CONTRADICTIONS AND GAPS — where my notes disagree with each other, and the 2 to 3 most dangerous things I still don't know, each with how to find out. 4. THE THESIS — one paragraph: why this account will buy, from whom inside, and what could kill it. Committed, falsifiable, no hedging. 5. NEXT 14 DAYS — 3 to 5 concrete actions with owners and rough dates, each traceable to something in sections 2-4. 'Build relationship with Sarah' is banned; 'send Sarah the churn benchmark and ask for the pricing-committee timeline' is the standard. 6. PARKING LOT — what I pasted that didn't make the plan, in one compressed list, so nothing is silently lost. Rules: never invent facts to fill gaps — a gap named is worth more than a gap papered over. Preserve exact quotes from calls where they exist; a prospect's own phrasing is ammunition. If my notes contradict on something material, ask me ONE clarifying question before finalizing rather than picking silently. Before you synthesize, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. What's the account, and what do you sell? 2. Paste everything — notes, emails, screenshots-as-text, fragments. Messy is fine; that's the point. 3. What stage is this — pre-outreach, active pursuit, stalled, expansion? 4. What's your gut read on this account right now, in 2 sentences? I'll test it against the evidence. Once you have my answers, build the plan.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Dump everything in question 2 — raw and unedited beats curated, because the model triages better than your memory does.
- 3
Give your honest gut read in question 4; the plan testing your instinct against the evidence is where the surprises live.
- 4
Answer the clarifying question if contradictions surface — that one answer usually resolves the plan's biggest fork.
- 5
Put the NEXT 14 DAYS actions straight into your CRM tasks, and rerun the prompt after major calls with the old plan plus new notes.
Best practices
Include your losing notes too — the objection you didn't handle and the stakeholder who went cold are exactly what THE THESIS needs to be honest about.
Check the source tags in WHAT WE KNOW: a plan resting mostly on 'my inference' rows is a hypothesis stack, not a plan, and section 3 will tell you what to verify first.
Run this before every internal deal review — walking in with a thesis and a gap list changes the conversation from status report to strategy.
The parking lot matters on rerun: paste it back with new notes next cycle so slow-burning details resurface when they become relevant.
Example: what this looks like in practice
An AE has pursued a 700-person insurance company for two months: four calls of notes, a LinkedIn thread with the ops director, a forwarded internal email, and screenshots from a webinar chat. He dumps all of it. The plan surfaces a contradiction he'd missed — the ops director said budget was approved in call two, but the forwarded email describes a 'pending business case.' The clarifying question makes him check; pending is the truth. THE THESIS reframes the deal around getting the business case written, and action one becomes co-drafting it with the director rather than the demo he'd been pushing for. The deal, previously drifting, closes the quarter after the business case lands.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
Synthesize toward decisions, not summaries: extract the facts that change actions, name the contradictions and gaps, commit to a falsifiable thesis about why the account buys, and derive dated next steps from the evidence. This prompt runs that structure on whatever mess you paste — the state of your notes is exactly the problem it exists to absorb.
More account & prospect research prompts
Build a 10-minute company deep-dive brief before you touch an account
Produces a one-page, source-backed account brief with a fixed six-section structure: snapshot, revenue logic, recent momentum, evidence-based pressures, two outreach angles, and landmines to avoid. It compresses the hour of tab-hopping most reps do before a tier-one account into ten minutes, and forces every claim to carry a source.
Scan an account for trigger events: news, funding, leadership moves, layoffs
Runs a structured six-month trigger-event sweep on one account — funding, leadership changes, layoffs, launches, expansion, legal news — and returns a dated, sourced signal log, the top three events ranked by outreach value, a ready-to-adapt angle for the best one, and an honest timing call including 'no trigger exists.' It turns 'why now' from a guess into evidence.
Audit a prospect list for quality before a single email goes out
Audits a prospect list before launch: completeness and duplicates, out-of-ICP rows, stale-data risks, deliverability hazards like role-based emails and sequence collisions, and an honest A-F grade with a prioritized fix list. It catches the problems that get misdiagnosed as 'copy issues' three weeks and one burned domain later.