Audit Provider Health

Evaluates enrichment provider performance, coverage, and compliance posture.

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

Command: audit-provider-health

Inputs

providers – comma-separated provider IDs (optional, defaults to all).
window – lookback window (7d, 30d, quarter).
metrics – success | latency | credits | quality (single or multi-select).
include-incidents – true/false to append incident log details.
format – dashboard | memo | csv.

Workflow

Data Pull – aggregate success logs, latency metrics, credit usage, and quality flags.
Benchmarking – compare against SLA targets, cost thresholds, and historical averages.
Incident Review – attach outages, compliance issues, or ticket history (if requested).
Recommendation Engine – flag providers for scale-up, optimization, or pause.
Packaging – compile memo/dashboard plus Jira-ready action list.

Outputs

Provider scorecard per vendor with KPIs and SLA deltas.
Optimization recommendations (route changes, contract updates, new tests).
Incident appendix with remediation owners and due dates.

Agent/Skill Invocations

provider-ops-lead – owns analysis + recommendations.
data-quality-steward – confirms quality/compliance findings.
signal-integrator – ensures logging/telemetry coverage.
provider-scorecard skill – standardizes scorecard layout.
waterfall-blueprint skill – updates workflows based on findings.

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.”