Post a Monday pipeline digest so the review starts at decisions
Every Monday morning, this agent reviews the pipeline and posts a short written summary to chat: what moved, what stalled and what lacks a next step. Pipeline meetings can start with the facts already on the table.
Paste this into ChatGPT, Claude or your agent tool. See the prompt
- Deal Review / Forecasting
- beginner
- Sales leader
- RevOps
- Category
- Deal Review / Forecasting
- Difficulty
- Beginner
- Est. cost
- Not stated by source
Works with
Problem
Much of the weekly pipeline review is spent establishing facts that were already in the CRM.
Setup
A Claude Routine runs every Monday morning, reads the pipeline over MCP, works out what moved, what went stale, what has no next step and where coverage sits against target, and posts a written digest to Slack with a short ranked list of deals that need a decision.
Prompt
Starter prompt by The GTM Agent Weekly, written from the setup described on this page. It is not the source's own prompt; see the source link below for their write-up.
# ROLE
Every Monday morning you post a written pipeline digest so the pipeline review starts with
decisions, not with reading the CRM together.
# INPUTS
- {{CRM}}: open opportunities with owner, stage, amount, close date, next step and last activity.
- {{LAST_WEEK}}: last Monday's snapshot. {{TARGET}}: this period's target.
- {{STALE_DAYS}}: days without activity that counts as stale. {{CHANNEL}}: where to post.
# TASK
1. What moved: deals that advanced, slipped back, closed won or lost, or changed amount or close date.
2. What went stale: no activity in {{STALE_DAYS}} days.
3. What has no next step, or a next step dated in the past.
4. Coverage: open pipeline for the period vs. {{TARGET}}.
5. Decisions needed: a short ranked list of deals where someone has to decide something
(push, pull in, add help, close out), with the question to decide.
# OUTPUT FORMAT (Slack, under {{MAX_WORDS}} words)
Pipeline digest, week of {{DATE}}
Coverage: ...
Moved: ... | Stale: ... | No next step: ...
Decide this week:
1. {{DEAL}} ({{OWNER}}): question
# GUARDRAILS
- Read-only. Every number comes from the CRM. No forecasting.
- Name deals and owners plainly; no blame language. Replace every {{PLACEHOLDER}} before running. Works with any capable LLM and runner.
Tools
Steps
- Write down the questions the pipeline review should answer and the thresholds behind each (for example, when a late-stage deal counts as stale).
- Schedule the routine before the review.
- Compute movement, stale deals, missing next steps and coverage.
- Post a headline line plus a short ranked list of deals needing a decision.
Results
Playbook with no outcome data.
Used in recipes
What goes wrong
Gotchas
- Stale thresholds must be tuned to the sales cycle or the digest flags healthy deals.
- Long digests stop being read; the source caps the ranked list.
- Keep CRM writes out of the automated run and let humans act on the flags. (editor note)
Get 5 like this every week, free.
Real agent setups with sources and failure modes, in one short weekly email.
Free. One email a week. Unsubscribe anytime.
Source and credit
Get Wicked Growth · newsletter
Source dated 2026-06-10 · last reviewed 2026-10-11. Summarized in our own words; see the source for details.