Stalled-deal nudger

Every few days an agent finds deals sitting in a stage past its expected dwell time, checks what changed since the last contact, and drafts a tailored follow-up per stalled deal — then lands one approval where you approve each follow-up before it is sent and the deal is updated.

Saves you ~2.3 h / week

How it works

Trigger
On the “Stalled-deal sweep” schedule.
Job
Scan for stage stalls, research what changed, draft per-deal follow-ups.
Outcome
A prioritized deal queue with tailored follow-ups ready for approval.

What it installs

Agents 2

  • Deal Rescue Agent

    Keeps deals from dying quietly by spotting stage stalls early and drafting context-aware follow-ups for human approval.

  • Stalled-deal nudger Quality Reviewer

    Checks primary evidence, domain controls, deliverable completeness, and communication quality, stopping the run when the work is wrong, unsupported, incomplete, or uncertain.

Teams 1

  • Stalled-deal nudger quality team

    The delivery agents produce the work while an independent quality reviewer checks each workflow handoff against explicit evidence, domain, and communication requirements before the run can continue.

Workflows 1

  • Stalled-deal nudge cycle

    Scan for stage stalls, research what changed, draft per-deal follow-ups, approve each send, then send and update the records.

Documents 2

  • Stage dwell times & nudge rules

    How long a deal may sit in each stage before it counts as stalled, and the rules every follow-up must respect.

  • Stall patterns & nudge outcomes

    A living log of which stages stall most, which nudge angles get replies, and which convert — updated after each cycle.

Goals 1

  • No deal stalls silently

    Every deal past its stage's expected dwell time gets a context-aware nudge or a deliberate human decision, every cycle. Success looks like: Each cycle ends with every stalled deal either carrying an approved, sent follow-up with the record updated, or a logged human decision (wait, re-stage, close-lost) — and the stall-pattern document showing which stages stall and which nudge angles convert.

Skills 3

  • stalled-deal-detection

    Flag stuck, stale, overdue, and single-threaded deals, separate genuinely stalled deals from naturally slow ones, and rank nudge candidates by close date, deal size, stage, activity, and risk. Adapted from anthropics/knowledge-work-plugins/pipeline-review.

  • context-aware-nudging

    Research first, rank hooks — trigger events over mutual connections over role-based pain — and draft AIDA follow-ups that give a dark deal a new reason to reconnect, on a 3-5 touch cadence where every touch adds a new angle; drafts only. Adapted from anthropics/knowledge-work-plugins/draft-outreach. Adapted from coreyhaines31/marketingskills/cold-email (sequence guidance).

  • stall-pattern-tracking

    Record every cycle's stall counts and nudge outcomes in the living document, and surface repeat patterns — which stages stall, which nudge angles convert — with evidence.

Schedules 1

  • Stalled-deal sweep

    Scans for stalled deals and drafts follow-ups every two to three days. ## Professional quality control Objective: complete the recurring Stalled-deal nudger operating cycle and deliver a review-ready, evidence-backed result rather than merely report that the schedule ran. Start by fixing the review period, reading the current source records and prior run, confirming required access, and listing missing or contradictory inputs. Execute the bundle's full authored method in order, retaining source, calculation, command, or before/after evidence for load-bearing findings. Separate facts from interpretation, apply supplied policy without inventing thresholds, and stop any branch that requires missing authority or an unconfirmed human rule. Produce the complete named deliverable plus an evidence record, assumptions, exceptions, unresolved questions, and concrete next actions with owners where the method calls for them. Run the workflow's independent verifier checks and fix failures before requesting approval. The task is done only when every requested section and quality criterion passes or a blocker is explicit; silence, inaccessible data, or polished prose is not proof of completion. Verify ICP fit, trigger evidence, contact lineage, conversation state, offer and policy limits, and every personalization detail. Outreach must sound like one informed person writing to another, without generic AI phrasing, fake familiarity, filler, hype, manipulative urgency, or reusable template lines disguised as research. The human retains authority over publication, sending, spend, signing, merging, deployment, and other consequential external actions.

Connectors pick at least 1 of 2

  • HubSpot

    HubSpot

    Connects to HubSpot so the agent can read deal stages and activity, spot stalled deals, and update records after an approved send.

    Open the HubSpot connector
  • Attio

    Attio

    Connects to Attio so the agent can read deal stages and activity, spot stalled deals, and update records after an approved send.

Folders 1

  • Stalled deals

Requirements

  • Browser access to your CRM — The agent works in your CRM through its web interface in your browser to read deal stages, activity history, and contacts, and pauses for your approval before any follow-up is sent or any record is updated. Until you connect it, it works from attached exports (deal and activity CSVs) and the relevant documents.

Setup guide

How to Nudge Stalled Deals

A practical guide to finding deals past their stage dwell time and drafting context-aware follow-ups with approval.

Read the setup guide

Don't see your workflow? Describe it.

A sentence or two about a recurring job is enough. We design the playbook that runs it and show you exactly what it saves.

* What keeps taking time you don't have? *



Takes a minute · no account needed