CONTEXT(CLONE)
Sign in

Forecast deals challenged against their own evidence

For: Chief revenue officer or sales operations lead preparing the quarterly forecast call

Pattern: Adversarial reviewNeeds a connectorDesigned for 20 to 400 agents
Get early accessSign in to use

The pain today

Every deal in the commit column has a confident owner. The evidence, last buyer contact, a named decision maker, an agreed next step, is in notes and emails that nobody checks deal by deal.

The ask

“For every deal in this quarter's commit and best-case columns, read the connected notes, emails and call summaries. Have one side argue it closes this quarter and the other argue it slips, using only what is recorded. Show me the deals whose case does not survive.”

Plain words, as you would say it to a colleague. Edit it to fit your case before you send it.

What you attach or connect

  • Open deals with stage, amount and close date
  • Activity notes and emails per deal
  • Call summaries
  • Stage exit criteria from the sales process

The unit of work

One worker task per one open deal with its recorded history.

Why a swarm fits

Deals are independent and each has a small history. Arguing both sides per deal, with different families on each side, tests the record rather than the owner's confidence.

Not for

A short pipeline: the sales manager can ask each owner directly.

The decision tree

5 typed decisions, each with an action for every answer

At fixed moments in a run, the engine puts one narrow question to a decision model. The decision model never writes text: it answers yes or no with a probability, picks from listed options, or gives a score, about a small slice of the material. The engine then does exactly what this tree says, which is what makes the run auditable. The thresholds are the template's design values, not measured results.

  1. Planner, while planning

    Scope checkYes or no, with a probability

    Before work starts on a unit

    Does this deal have any recorded activity inside the quarter, so that there is a record for either side to argue from?

    Sees only: The deal's dated activity list

    Why: Deals with no record are reported as too thin to judge instead of being argued from nothing.

    • Yes: 0.60 or higherthenAccept
    • Unsure: 0.30 up to 0.60thenAccept
    • No: below 0.30thenMark unresolved

  2. After workers, the judge checks

    Evidence checkYes or no, with a probability

    After a worker answers

    Does the quoted record show the buyer, in their own words, confirming the step the exit criterion requires, such as a named signatory or an agreed signing date?

    Sees only: The quoted record with author and date, and one exit criterion

    Why: The seller's summary of buyer intent is the very thing being tested.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenMark unresolved
    • No: below 0.50thenReject and retry

  3. Evidence checkYes or no, with a probability

    After a worker answers

    Does the dated record show what the slip side claims, such as the buyer's last reply being older than the agreed next step, rather than a gap in logging?

    Sees only: The slip side's cited records and the deal's activity dates

    Why: A deal should not be challenged because someone forgot to log a call.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenMark unresolved
    • No: below 0.50thenReject and retry

  4. Reconciler, while merging

    Conflict checkA choice among options

    While reconciling

    On the verified evidence from both sides, which exit criteria for the deal's current stage are met?

    Sees only: Both sides' verified evidence and the stage's exit criteria

    Why: The output is evidence for and against, never an invented probability.

    • All met with buyer-side evidencethenAccept
    • Some rest only on the seller's summarythenMark unresolved
    • None are met on the recordthenAccept

  5. Accountable person, before anything is settled

    Person decidesYes or no, with a probability

    Before anything is reported as settled

    Is this deal in the commit column while its case to close this quarter failed or stayed unresolved?

    Sees only: The deal's forecast category and the ruling

    Why: The revenue leader owns the forecast and the conversation with the deal owner.

    Accountable: The revenue leader owns the forecast number; the challenge informs the talk with the deal owner, not their evaluation.

    • Yes: 0.30 or higherthenAsk a person
    • Unsure: 0.10 up to 0.30thenAsk a person
    • No: below 0.10thenAccept

The fleet: who does what

Model tiers by role, not brands: you choose the models. Strong reasoning models plan and reconcile, small fast models do the wide work, and the judge is a decision model from a different family, so it does not share the workers' blind spots.

  1. Planner

    A strong reasoning model turns the stage exit criteria into the evidence each side must produce.

    Decisions here:1. Scope check

  2. Workers

    Paired workers from two different families argue close and slip for each deal, citing dated records only.

    Designed for 20 to 400 agents, one worker task per one open deal with its recorded history. Each worker receives only its own unit.

  3. Judge, from a different model family

    A decision model from a third family rules which cited evidence actually meets each exit criterion.

    Decisions here:2. Evidence check3. Evidence check

  4. Reconciler

    A strong reasoning model lists deals whose case failed, the missing evidence, and deals with too little record to judge.

    Decisions here:4. Conflict check

  5. Accountable person

    The revenue leader owns the forecast number; the challenge informs the talk with the deal owner, not their evaluation.

    Decisions here:5. Person decides

Checked before anything is accepted

  • Both sides may cite only recorded activity, with dates
  • Claims about buyer intent must quote the buyer, not the seller's summary
  • Deals with no recent recorded buyer contact are flagged whatever the argument
  • No close probability is invented; the output is evidence for and against

What comes back

  • Deals whose case did not survive, with the missing evidence
  • Deals supported by buyer-side evidence
  • Deals with too thin a record to judge
  • Questions for each deal owner

What to measure

  • Challenged deals that slipped
  • Unchallenged deals that slipped
  • Forecast review time
  • Cost per deal reviewed

Names of measures only. No result is claimed for this template.

Templates open in the workspace chat with the ask filled in. Nothing runs until you send it.

Get early accessSign in to use

More in Sales and marketing

A quarter of sales calls mapped to objections

For: Sales enablement lead or revenue operations manager explaining why deals are lost

The loss reason in the pipeline is a dropdown picked by the seller.

Pattern: Map, verify, reduceNeeds scale5 decisionsDesigned for 40 to 800 agents

Competitor pricing and product page watch

For: Product marketing manager or competitive intelligence lead keeping battlecards current

Battlecards are accurate the week they are written.

Pattern: WatchtowerNeeds a connector5 decisionsDesigned for 10 to 300 agents