Agentkitevals Directory

The evaluation-first directory for AI agents, automation blueprints, and verified GTM playbooks.

Agentkitevals curates the top-performing agent evaluations and automation stacks so builders can ship trustable agents faster. Operators subscribe for unlimited access; creators join to monetize their most battle-tested loops.

Explore the directoryGet listed

Featured directory listings

Every listing is vetted for documented eval runs, automation fit, and distribution assets. Start with a blueprint and launch the same day using Supabase-native scaffolding.

salesConversion +18% • Setup <2 days • Live installs 42

Pipeline Readiness Radar

Benchmark qualifying agents across your inbound channels and deploy the top performers directly into Salesforce or HubSpot.

Revenue operationsDemand gen agencies
  • Supabase worker scores every handoff and tracks conversion velocity
  • Discord alerting when agents dip below SLA thresholds
  • One-click exports into Airtable, Notion, and CSV for manual reviews
$59/mo operator access$129 creator listing + performance rev-share
View qualifying benchmarks
growthNPS 68 • Retention 92% • Adoption 3 teams/week

Agent PM Copilot Loop

End-to-end product management cycle that pairs autonomy tests, roadmap drafting, and release notes summarization in one kit.

Product opsFractional product strategists
  • Supabase cron runs nightly story validation and regression sweeps
  • Linear, ClickUp, and Jira integrations pre-mapped
  • Stakeholder digest emails generated via GPT evaluation scores
$59/mo operator access$129 creator listing + performance rev-share
Download sprint templates
complianceAudit ready • PII safe • Live deployments 16

Risk Desk Monitor

Compliance-focused directory entry that keeps regulated businesses inside trusted guardrails while experimenting with agent-led decisions.

Fintech risk teamsHealthcare compliance leads
  • Supabase row policies isolate PII across evaluations
  • SOC2-ready audit exports generated automatically
  • Alert routing into PagerDuty with on-call auto escalation
$59/mo operator access$129 creator listing + performance rev-share
See compliance scores

How the monetization engine works

Operator Subscription

Operators pay $59/mo for full search, benchmark downloads, and team seats that sync to Supabase.

Creator Listing Fee

Creators pay $129 to launch a listing, unlocking trust badges, analytics, and featured placement slots.

Referral Rev-Share

Agentkitevals routes deployments to creators and pays 20% recurring rev-share on sourced conversions.

See full pricingPartner with Agentkitevals

High-signal templates ready to deploy

Copy the blueprints operators actually trust. Each template includes documented eval runs, automation highlights, and Supabase tables so you can plug it directly into your stack.

Deal Desk Evaluation Hub$59/mo operator access

Centralize LLM call scoring, deal intelligence, and human override workflows so revenue teams can prove ROI on autonomous agents.

B2B SaaS revenue opsRevOps consultantsGrowth agencies

Automation highlights

  • Supabase row level security for playbook-level access control
  • Daily eval score aggregation with webhooks to HubSpot and Salesforce
  • Auto-generated trust reports explaining agent decisions for legal sign-off

Signal metrics

  • Median win-rate lift: +14%
  • Time-to-approve deals: -38%
  • Average CSAT on agent interventions: 4.6/5
View template
Support Agent Benchmark Ring$59/mo operator access

Run rotating benchmarks across multiple AI support agents, routing best performers live while logging hallucinations for rapid patching.

Customer support leadsAI support platformsCX automation partners

Automation highlights

  • Supabase edge functions assign tickets to highest scoring agent each hour
  • Automated regression suites evaluate tone, accuracy, escalation triggers
  • Slack and Linear sync keeps human agents in the loop when anomalies spike

Signal metrics

  • First response time: -47%
  • Containment rate: +32%
  • Weekly hallucinations per 100 tickets: <3
View template
Compliance Agent Verification Loop$59/mo operator access

Qualify finance, healthcare, and legal automation agents against regulator-aligned benchmarks before they ever see production data.

Governance teamsAI compliance firmsEnterprise innovation labs

Automation highlights

  • Policy ingestion pipeline with Supabase storage versioning
  • Guardrail harness runs HIPAA/GDPR/FINRA scenario packs nightly
  • Escalation lattice routes risky outputs to on-call counsel instantly

Signal metrics

  • Policy coverage: 96%
  • Escalation SLA: <15 minutes
  • False positive rate: 2.1%
View template

Signals operators can trust

  • Live install counts, benchmark deltas, and churn flags rendered from Supabase analytics
  • Policy, security, and compliance tags verified by our moderation team
  • Direct handoffs into Slack, Linear, and Notion for instant adoption by ops teammates
Book a directory tourView API response