Sales
Sales supervision
Reviews CRM activity, flags pipeline risk, and drafts coaching for sales leaders against governed pipeline data.
In short
An always-on agent that reviews each sales rep's pipeline against historical patterns, flags deals at risk, and drafts coaching messages for the manager — sourced from the company's CRM and a governed semantic layer of revenue metrics. The agent never writes to the CRM without approval; it produces evidence-backed recommendations a sales leader can act on.
Sales leaders cannot inspect every rep's pipeline every week. The work that does happen is reactive, late, and skewed toward the loudest reps.
The Sales supervisor agent runs every weekday morning, reviews each rep's open opportunities and recent activity, and produces a short, sourced coaching note for the manager: which deals slipped, which look stuck, and what one specific intervention would change the trajectory.
The agent reads the CRM and proposes evidence-backed actions: every claim resolves to a source row. Only after manager approval does it send coaching to the rep and write authorized notes to the CRM, within the agreed permissions. It does not send customer-facing messages or decide a forecast number on its own.
What this case fixes
In typical mid-market sales orgs, pipeline review is weekly, conversational, and uneven. Managers focus on the deals reps surface; risk in the rest of the pipeline accumulates silently. By the time a stalled deal is noticed, the recoverable window has often closed.
Generic AI tools either summarize CRM activity (low signal) or suggest forecast numbers (no auditability). Neither helps a manager run a coaching cadence with evidence behind it. What the org actually needs is a governed agent that knows the team's pipeline schema, applies the same risk heuristics every week, and produces decisions a manager can defend.
Who it's for
- Mid-market and enterprise B2B sales organizations
- Outbound and channel sales teams
How it runs
This reference pattern runs in five steps. Read access is scoped to the required CRM and governed metric data. Sending coaching and writing CRM notes require manager approval before execution.
- DataIngest CRM and semantic layerPulls the rep's open opportunities, last 30 days of activity, and the headless semantic layer's win-rate / cycle-length curves by segment. Read-only.
- AgentScore and explainThe supervisor agent applies a fixed risk policy: stage age vs. segment median, missing decision-maker, no activity in N days, decreasing meeting cadence. Each flag links back to the source rows.
- AgentDraft coachingFor each flagged deal, the agent drafts one specific, evidence-backed coaching action (e.g., 'Schedule executive sponsor intro by Friday — the last one closed in 21 days'). No generic advice.
- PersonManager review and approvalThe manager sees the digest in the Xophia console (or via Slack). They approve, edit or dismiss each recommendation. Only approved items proceed.
- AutomationApply and logApproved coaching is sent to the rep through the existing channel (Slack/Email) and a note is written into the CRM as the manager's user. Every step — read, decision, approval, write — is logged in the immutable audit trail.
Systems it connects
- HubSpot / Salesforce / PipedriveCRM (system of record)
- Headless semantic layerGoverned metrics (win rate, cycle length)
- Slack / Microsoft TeamsManager channel
- Email gatewayOutbound channel
- Xophia audit logCompliance and reconciliation
Reference targets
| Metric | Before | Target |
|---|---|---|
| Reps reviewed weeklyCount of distinct rep IDs that received an agent-generated coaching digest, divided by total active reps. | ~30% (top + loudest reps) | 100% of reps, every week |
| Time-to-first-touch on stalled dealsFrom the moment a deal trips a stall heuristic in the agent, to the moment a coaching action is approved by the manager. | 11 days median (post-stall) | ≤ 2 business days median |
| Coaching evidence rateAudit-log check: every coaching item must reference at least one CRM record id and one semantic-layer query. | Anecdotal (no source) | 100% of recommendations link to source rows |
| Manager review timeSelf-reported via the Xophia console; cross-checked against approval timestamps. | 60-90 min weekly per rep | ≤ 15 min weekly to triage agent digest |
Values from an illustrative scenario, not customer results.
Illustrative execution trace
A synthetic example of how an execution could be recorded. Names, identifiers, volumes, costs and outcomes are fictional; the sequence is illustrative, not a customer result.
Rep MR-014 has 12 open opportunities. The agent identified three at risk and drafted coaching for two; one was dismissed by the manager.
| Tool | Input | Output |
|---|---|---|
| crm.list_open_opps | owner_id=MR-014, status=open | 12 records, fields: stage, amount, last_activity_at, decision_maker_present |
| semantic.win_curve | segment=mid_market, stage=proposal, cycle_to_date=33d | median_to_close=27d, p75=44d → flag if cycle_to_date > p75 with no DM contact |
| semantic.activity_baseline | segment=mid_market, stage=proposal | expected meetings/wk=1.6, observed for opp_id=O-9112=0.4 → flag |
| agent.draft_coaching | opp_id=O-9112, signals=['stale_cycle','low_activity'] | Suggest scheduling executive sponsor intro by Fri; reference 3 prior won deals at 21-day cycle in same segment. |
| console.publish_digest | manager_id=MGR-04, items=3 (2 drafted, 1 informational) | digest_id=D-2026-05-08-MGR-04 awaiting review |
Manager approved 2 coaching items at 09:14 UTC. Approved items written to Slack and to CRM activity feed. Audit row D-2026-05-08-MGR-04 closed. Total agent cost: $0.043; latency p95: 6.2s.
Does this module fit?
In 20 minutes we review how it would look on your systems.