Skip to main content
Intempt
Coming soon

Win loss analysis

Breaks closed deals into won and lost by lead source, deal size and the stage they died at, so the pattern is visible.

Authored by Sid Chaudhary

Founder & CEO at Intempt

Agentic workflow

Coming soon

1 step Blu runs end to end. It drafts a plan and nothing runs until you approve it.

  1. 1

    Break down wins against losses

    Coming soon

    Blu builds a step

About this recipe

When to use it

"We're losing on price" is usually a guess unless you've actually broken losses down by source, size, and stage. This does that breakdown directly from real deal data, so the actual pattern in wins and losses becomes visible.

What it delivers

Breaks down won and lost deals by lead source, deal size, and the stage at which losses occurred, surfacing real patterns in what's converting and what isn't.

How you prompt this

Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.

Tell Blu Agent what you want

“Breaks closed deals into won and lost by lead source, deal size and the stage they died at, so the pattern is visible.”

recipe.md preview

Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.

Sign up to read the full recipe.md and run it with Blu Agent.

Sign up to see the full recipe

Inputs & outputs

What the recipe needs before it runs, and what it leaves in your workspace.

Inputs

  1. Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.

Outputs

    How the recipe runs

    Blu follows the steps in order and shows you each one before anything goes live.

    1. 01Break down wins against lossesCreate an Insights report called "Win-Loss Analysis". Series A: Event "Deal won", aggregation: Count, label: "Won" Series B: Event "Deal lost", aggregation: Count, label: "Lost" Series C: Computed: Series A / (Series A + Series B) × 100, unit: %, label: "Win Rate" Series D: Sum of deal amount for won deals (revenue won) Series E: Sum of deal amount for lost deals (revenue lost) Breakdown: By Users.UTM source (lead source attribution via the deal's primary_user_id) Time range: Last 6 months of closed deals Compare: Previous period (prior 6 months) Chart type: Side-by-side bar chart for won vs. lost counts with win-rate % annotations, plus a separate breakdown by deal-size bucket (small <$10K, mid $10K-$50K, enterprise >$50K) Also include a parallel "stage-at-loss" view: - For Deal lost events, what was the previous_stage just before loss? Distribution shows whether deals die early (qualification mismatch) or late (close-stage objections) Annotations: - Flag the source with the highest win rate AND volume: the channel to scale. - Flag the source with the lowest win rate but high volume: the channel with leakage; investigate ICP fit. - Flag any deal-size bucket where win rate is below 25% (typically signals a sweet-spot mismatch: deals too big or too small for current sales motion). - Highlight the dominant "stage at loss": late-stage losses suggest closing/competition issues; early-stage losses suggest qualification/ICP issues. - Surface the average deal size of won vs. lost deals: if won deals are systematically smaller, the team is winning easy ones and losing hard ones (qualification or pricing strategy issue). Use case: the canonical sales-team retro report. Most teams track pipeline and revenue but rarely systematically analyze why deals died. This recipe makes loss patterns visible. Taxonomy notes: - Deal won and Deal lost both have amount, primary_user_id, stage, close_date, owner_id, currency. - Deal lost.previous_stage (or the last Deal stage changed before Deal lost) gives stage-at-loss. - Source attribution via the user's UTM source on the Users object linked through primary_user_id.

    Install Intempt and run it

    1. 1

      Sign up

      Create a free Intempt workspace.

    2. 2

      Connect your data

      Add the sources this recipe reads from.

    3. 3

      Ask Blu

      Type /win-loss-analysis-report in Blu once this recipe is live there.

    4. 4

      Review and approve

      Blu builds each step and waits for your OK before anything goes live.

    Related recipes

    Sid ChaudharyDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Sid ChaudharyPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Sid ChaudharyReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    More recipes by Sid Chaudhary

    Discovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Post demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Return rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    Got a play worth sharing?

    Publish it to the Intempt Collective Marketplace and earn when other teams run it.

    Submit a recipe