Ingest Pipeline

Aggregates CRM/MAP data, cleans records, and prepares forecast-ready pipeline views.

Published by @gtmagents·from gtmagents/gtm-agents·0 agent reads / 30d·0 saves·Updated June 14, 2026

Command: ingest-pipeline

Inputs

timeframe – forecast period (Q1, Q2, FY, rolling-90).
segments – comma-separated list of segments or regions.
detail – summary | full output verbosity.
filters – optional stage, product, or owner filters.
refresh – optional flag to force data refresh vs cached snapshot.

Workflow

Data Extraction – pull CRM opportunities, bookings actuals, MAP signals, and enrichment fields by timeframe.
Normalization & QA – dedupe, enforce stage definitions, check close dates, align currencies, and flag missing data.
Scoring & Cohorting – compute coverage, velocity, win rate assumptions, and stage-based risk scores.
Segmentation – split pipeline by segment, region, product, partner, and channel.
Packaging – output structured tables + dashboards for forecast architect + finance partner review.

Outputs

Pipeline dataset (CSV/Sheets) with commit/upside/sandbag buckets.
Data quality log detailing issues resolved or pending.
Snapshot summary (coverage %, attainment, risk flags) per segment.

Agent/Skill Invocations

revops-analyst – runs extraction + QA steps.
forecast-modeling skill – provides scoring templates and coverage math.
variance-analysis skill – tags known risk cohorts for later tracking.

More on the bench

Draft Response

Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue.

customer-success+2

Design Clinical Campaign

Produces clinical-grade campaign brief with targeting, creative guidance, and review plan.

marketing-growth-copy+2

Vendor Review

Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.

Sharebench · Public bench

Connect via MCP.

Add the public bench to any AI tool. Your agents read every artifact you see — no signup needed.

1Pick your tool

# Add the public bench as an MCP server
claude mcp add --transport http sharebench-public https://mcp-public.sharebench.ai

# Settings → MCP → Add new MCP server
{
  "mcpServers": {
    "sharebench-public": {
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}

# Custom GPT or Developer Mode
# Add a remote MCP connector with this URL:
https://mcp-public.sharebench.ai

# Append to ~/.codex/config.toml
[mcp_servers.sharebench_public]
url = "https://mcp-public.sharebench.ai"

2Ask your agent for an artifact

Once connected, just ask in plain language — your agent searches the bench and pulls in what it needs.“Pull the brand voice from sharebench and rewrite this draft.”