opsmarshal
Workflow 01 — Pipeline Creation

Signal-Orchestrated Outbound Engine

Most "AI SDR" builds automate the send. This one automates the decision before the send: fusing intent, hiring, tech-stack, and funding signals into a play selection — which sequence, which persona, which angle, and whether to reach out at all. A human approves the play; the agent handles the mechanics; every disposition writes back to CRM.

At a glance

Signal-Orchestrated Outbound is a governed agent workflow that fuses intent, hiring, tech-stack and funding signals into a play recommendation — which sequence, which persona, which angle, or whether to reach out at all — that a human approves before any message sends. It is one of fifteen workflows in the Enterprise GTM Agent Stack, an Opsmarshal series on AI enablement and agentic workflows.

Owned by
SDR Manager + RevOps
Writes back to
CRM, Engagement platform, Audit log
Held to
2–4× — Reply rate vs. volume baseline
Gate
Permission → Evidence → Approval → Audit
Selects the play, not just the lead Writes to: CRM + engagement platform Approval: SDR before first send
Business Pain

Volume automation burned the channel

The status quo

Teams bought AI email tools, 10x'd volume, and watched reply rates collapse while domains got flagged. The bottleneck was never sending capacity — it was knowing which account deserves which motion this week, and having proof for why.

What this workflow changes

Signals stop being a column in a spreadsheet and become the input to a routing decision. A funding event at an ICP-fit account with a fresh VP hire triggers a different play than lone website intent. Low-conviction accounts get suppressed — deliberately doing nothing is a valid, logged output.

Architecture

Signal fusion → play selection → gated execution

Signal Sources
Intent datatopic surges, review-site activity
Hiring signalsjob posts, leadership changes
Tech-stackinstall/removal detection
Funding & filingsrounds, expansions, 10-K language
1st-partysite visits, content, product usage
Agent Layer
Signal Fusion Agentdedupes, time-decays, scores conviction per account
Play Selectormaps signal pattern → play from an approved playbook library
Message Composerdrafts within play template boundaries; cites the triggering signal
Governance
Gate: permission → evidence → approval → auditplays only from approved library · SDR approves first touch · suppressions logged with reason
Systems of Record
CRMplay, signal evidence, and disposition on the account
Engagement platformsequence enrollment with play metadata
Audit logevery selection, suppression, and approval
DecisionChoiceRationale
Plays are a curated library Agent selects; humans author The agent never invents a motion. Marketing and sales leadership own the playbook; the agent's job is pattern-matching signals to it. This keeps message quality governable.
Suppression is an output "Do nothing" is logged with a reason The costliest outbound failure is burning a future buyer with a bad touch. Below-threshold conviction produces a logged suppression, reviewable in the same audit trail.
Signal conviction decays Time-decay per signal class A funding round is warm for 90 days; website intent for 7. Fusion scores decay on class-specific half-lives so stale signals can't trigger fresh sends.
First touch is human-gated SDR approves message 1; follow-ups auto-run The highest-risk moment is the first impression. Gating only that touch keeps throughput high while keeping a named human accountable per account.
Live Demo

Feed signals, watch the play selection

Toggle the signals observed for a sample account. The fusion agent scores conviction, the selector picks a play — or suppresses — and the gate rail logs the full decision.

Play Selector — account: Meridian Logistics (ICP fit: 82/100)

SUPPRESSED · conviction 0/100

No signals observed. Suppression logged — this account stays untouched, and that decision is auditable.

Governance audit log

[ready] fusion agent idle — toggle signals to run
Eval Metrics

What this workflow is held to

2–4×
Reply rate vs. volume baseline
measured per play, not blended — blends hide dead plays
≥ 60%
Play precision
SDR accepts the selected play without overriding it
0
Off-library sends
hard invariant — any breach is a sev-1 on the gate
100%
Disposition write-back
every touched account carries play + outcome in CRM
Operator Control Panel

Someone has to run this thing

Agents don't remove operators — they change what operators watch. This is the console spec: who owns it, what they check on what cadence, what pages them, and how they pull the plug.

Outbound Engine — Ops Console

Owner: SDR Manager + RevOps

Daily monitors

  • Approval queue depth — first-touch drafts awaiting SDR review; SLA 4 business hours
  • Signal feed health — per-class volume vs. 30-day baseline (±40% alerts)
  • Deliverability — bounce and spam-complaint rates per sending domain

Weekly reviews

  • Play scoreboard — reply/meeting rate per play; auto-benched plays reviewed with their author
  • Suppression sample — 10 random suppressions audited: was doing nothing right?
  • Override analysis — where SDRs changed the selected play, and why

Alert thresholds → who gets paged

  • Off-library send detected → sev-1, RevOps lead, immediately
  • Approval rate >95% at <5s each → SDR manager (rubber-stamp pattern)
  • Reply rate <50% of baseline for any active play, 7 days → play author

Manual controls

  • Pause per play / per segment — without stopping the whole engine
  • Account-level do-not-touch — instant, overrides every signal
  • Kill switch — halts all sends, preserves queue state, logs the halt as an audit event
Failure Modes

How it breaks, and what catches it

Signal-vendor drift

Intent providers change taxonomies; a topic rename silently zeroes a signal class. Mitigation: per-class volume monitors alert when a signal source deviates ±40% from its 30-day baseline.

Conviction inflation

Correlated signals (funding → hiring → press coverage) triple-count one underlying event. Mitigation: fusion agent clusters signals by root event before scoring; one event contributes once.

Approval fatigue

SDRs rubber-stamp first-touch approvals at volume, hollowing out the gate. Mitigation: approval-rate telemetry — if an SDR approves >95% in under 5 seconds each, the sample rate of required reviews increases and the pattern is surfaced to the manager.

Playbook staleness

The agent keeps selecting a play whose reply rate quietly died two months ago. Mitigation: per-play performance floors — plays under threshold for 30 days are auto-benched and flagged to their human author.

Opsmarshal builds workflows like this one inside client stacks — see AI enablement and agentic workflows and revenue operations, or book a call to walk through your own.

opsmarshal

Revenue Operations and AI Agentic Workflows for B2B companies in transformation. We build the machine. You run the company.

Services

Company

© 2026 Opsmarshal. All rights reserved. Privacy  ·  Terms