Stalled deal detection
Finds deals sitting in a stage far longer than usual with no activity, drafts a nudge that fits the stage, and escalates if they stay stuck.
Authored by Sid Chaudhary
Founder & CEO at Intempt
Agentic workflow
Coming soon5 steps Blu runs end to end. It drafts a plan and nothing runs until you approve it.
- 1
Measure how long it has sat
Coming soonBlu builds a step
- 2
Find the genuinely stuck ones
Coming soonBlu builds a step
- 3
Write a nudge per stage
Coming soonBlu builds a step
- 4
Draft it and chase the rep
Coming soonBlu builds a step
- 5
See what is really dead
Coming soonBlu builds a step
About this recipe
When to use it
A deal sitting in a stage past its typical age with no recent activity is either dead or forgotten, and nobody's forcing that decision. This surfaces it with a re-engagement draft so reps can revive it or honestly close it.
What it delivers
Detects deals stuck in a stage longer than typical for that stage's median age with no recent activity, and surfaces them with AI-drafted re-engagement nudges so reps can revive or honestly close-lost.
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
“Finds deals sitting in a stage far longer than usual with no activity, drafts a nudge that fits the stage, and escalates if they stay stuck.”
recipe.md preview
Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.
Inputs & outputs
What the recipe needs before it runs, and what it leaves in your workspace.
Inputs
- 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.
- 01Measure how long it has satCreate an AI-derived attribute 'days_in_current_stage' on the Deal object, refreshed daily. Compute: (a) calendar days since the deal last changed stage; (b) percentile of this age within the stage's historical median for similar deals (size, segment, rep). Flag deals where age is in the top quartile (75th+ percentile) for that stage. Also compute 'Days since last activity' (any meeting / email reply / task completion on the deal).
- 02Find the genuinely stuck onesBuild a segment 'Stalled deals' capturing open deals where (a) days_in_current_stage is in the top quartile for that stage AND (b) Days since last activity >= 14 days. Excludes deals where the rep has manually set a 'paused' flag (legitimate pause, coming back next quarter, etc.). Refreshed daily. Use the result of "Measure how long it has sat".
- 03Write a nudge per stageGenerate an AI-drafted re-engagement email template. The AI picks angle based on stalled-stage: (a) Discovery stalled (re-ask the qualifying question that wasn't answered; (b) Demo stalled) offer technical deep-dive or POC; (c) Proposal stalled (surface that pricing pushback usually means decision-maker isn't bought in, offer to align; (d) Closing stalled) explicit clarity-ask about timeline + remaining blockers. Personalized to last meeting summary if available. Tone: direct, low-pressure, honest. The rep reviews and sends: not auto-send. Use the result of "Measure how long it has sat", "Find the genuinely stuck ones".
- 04Draft it and chase the repCreate a workflow firing daily for newly-stalled deals (deals that crossed into stalled-segment in the last 24 hours). Step sequence: (1) compose AI nudge draft using the asset template + deal context; (2) create a task for the deal owner labeled 'Review and send: stalled deal nudge' with the draft pre-attached; (3) post Slack DM to the rep with deal name + draft preview + 'review' button; (4) escalate to manager via Slack if same deal is still stalled 14 days after first nudge task (signal: deal should probably be closed-lost). Don't auto-send the email: rep must review. Use the result of "Measure how long it has sat", "Find the genuinely stuck ones", "Write a nudge per stage".
- 05See what is really deadCompose a stalled-deal dashboard: count of stalled deals by stage and rep, total ARR at risk (sum of stalled deals' values), median age of stalled deals, recovery rate (stalled deals that re-engaged and moved stage forward), and dishonesty rate (stalled deals that should have been closed-lost: measured as deals that stay stalled 30+ days before eventually being marked lost). Manager view: which reps consistently let deals stall vs. honestly close-lost. Use the result of "Measure how long it has sat", "Find the genuinely stuck ones", "Write a nudge per stage", "Draft it and chase the rep".
Install Intempt and run it
- 1
Sign up
Create a free Intempt workspace.
- 2
Connect your data
Add the sources this recipe reads from.
- 3
Ask Blu
Type /stalled-deal-detection in Blu once this recipe is live there.
- 4
Review and approve
Blu builds each step and waits for your OK before anything goes live.
