# Send AI Agent Manager Playbook to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "afrexai-agent-manager", "name": "AI Agent Manager Playbook", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/1kalin/afrexai-agent-manager", "canonicalUrl": "https://clawhub.ai/1kalin/afrexai-agent-manager", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/afrexai-agent-manager", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-agent-manager", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/afrexai-agent-manager" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/afrexai-agent-manager", "downloadUrl": "https://openagent3.xyz/downloads/afrexai-agent-manager", "agentUrl": "https://openagent3.xyz/skills/afrexai-agent-manager/agent", "manifestUrl": "https://openagent3.xyz/skills/afrexai-agent-manager/agent.json", "briefUrl": "https://openagent3.xyz/skills/afrexai-agent-manager/agent.md" } } ``` ## Documentation ### AI Agent Manager Playbook Your company deployed AI agents. Now what? This skill turns you into the person who actually makes them productive — the Agent Manager. ### What This Does Gives you a complete framework for managing autonomous AI agents across your organization. Role definition, performance metrics, escalation protocols, governance, and team structure. ### The Agent Manager Role Based on Harvard Business Review's Feb 2026 research: companies deploying AI agents without dedicated management see 60%+ failure rates. The ones that assign Agent Managers see 3-4x better outcomes. ### Core Responsibilities Agent Portfolio Management — Which agents run, which get retired, which get built next Performance Monitoring — Task completion rates, accuracy, cost per action, escalation frequency Escalation Design — When agents hand off to humans, how, and what context they pass Governance & Compliance — Ensuring agents operate within policy, legal, and ethical boundaries ROI Tracking — Proving agent value in hours saved, revenue generated, errors prevented ### Agent Performance Scorecard Rate each agent monthly (1-5 scale): DimensionWhat to MeasureTargetReliabilityTask completion without errors>95%SpeedAvg time per task vs human baseline<30% of human timeCost EfficiencyCost per action vs manual equivalent<20% of manual costEscalation Rate% tasks requiring human intervention<10%User SatisfactionInternal user NPS for agent interactions>40 NPSCompliancePolicy violations or audit flags0 ### Phase 1: Discovery (Week 1-2) Audit all manual processes across departments Score each by: volume × time × error rate × cost Rank by automation ROI — top 5 become agent candidates Document current process with decision trees ### Phase 2: Build & Test (Week 3-6) Define agent scope: inputs, outputs, decision boundaries Build with guardrails: rate limits, approval gates, kill switches Shadow mode: agent runs alongside human, outputs compared Acceptance criteria: 95% accuracy over 100+ test cases ### Phase 3: Deploy & Monitor (Week 7-8) Gradual rollout: 10% → 25% → 50% → 100% of volume Daily monitoring dashboard (first 2 weeks) Weekly reviews (ongoing) Escalation paths documented and tested ### Phase 4: Optimize (Ongoing) Monthly performance reviews against scorecard Quarterly ROI assessment Agent retirement criteria: <80% reliability for 2 consecutive months Expansion criteria: >95% reliability + positive ROI for 3 months ### Escalation Protocol Design Level 1: Agent handles autonomously (target: 90%+ of volume) Level 2: Agent flags for human review before executing (5-8%) Level 3: Agent stops and routes to human immediately (1-3%) Level 4: Agent shuts down, alerts on-call manager (<1%) ### Escalation Triggers Confidence score below threshold Financial amount exceeds limit ($X) Customer sentiment detected as negative Regulatory/compliance topic detected Novel situation not in training data Contradictory instructions received ### Small Company (1-50 employees) 1 Agent Manager (often the CTO or ops lead) Managing 3-8 agents Time commitment: 5-10 hours/week ### Mid-Market (50-500 employees) 1 dedicated Agent Manager 1 Agent Engineer (builds/maintains) Managing 10-30 agents Budget: $120K-$180K/year fully loaded ### Enterprise (500+ employees) Agent Management Team (3-5 people) Head of AI Operations Agent Engineers (2-3) Agent Compliance Officer Managing 50-200+ agents Budget: $500K-$1.2M/year ### Agent Registry Every agent must have: Unique ID and name Owner (human accountable) Scope document (what it can/cannot do) Data access permissions Escalation protocol Last audit date Performance scorecard link ### Monthly Agent Review Pull performance data for all agents Flag any below threshold Review escalation logs for patterns Update scope documents if needed Retire underperformers Propose new agent candidates ### Quarterly Board Report Total agents active Hours saved this quarter Cost savings vs manual Incidents/compliance flags ROI per agent category Next quarter agent roadmap ### Common Mistakes No kill switch — Every agent needs an off button. No exceptions. Set and forget — Agents drift. Monthly reviews are minimum. Too much autonomy too fast — Start with shadow mode. Always. No escalation path — If the agent can't hand off to a human, it will fail silently. Measuring activity not outcomes — "Agent processed 10,000 tasks" means nothing if 40% were wrong. One person owns all agents — Bus factor of 1 = organizational risk. ### ROI Calculator Monthly Agent Cost = (API costs + infrastructure + management time) Monthly Human Cost = (hours saved × avg hourly rate) Monthly ROI = (Human Cost - Agent Cost) / Agent Cost × 100 Example (Customer Support Agent): - API + infra: $800/month - Management overhead: $400/month (5 hrs × $80/hr) - Hours saved: 160/month (1 FTE equivalent) - Human cost: $8,000/month ($50/hr fully loaded) - Monthly ROI: ($8,000 - $1,200) / $1,200 = 567% - Payback period: <1 month ### Industry Applications IndustryTop Agent Use CasesAvg ROISaaSCustomer onboarding, ticket triage, usage analytics400-600%Financial ServicesKYC checks, transaction monitoring, report generation300-500%HealthcareAppointment scheduling, prior auth, patient follow-up250-400%LegalDocument review, contract extraction, research500-800%EcommerceOrder tracking, returns processing, inventory alerts350-550%Professional ServicesTime entry, invoice generation, proposal drafts300-450%ManufacturingQuality inspection reports, maintenance scheduling200-400%ConstructionPermit tracking, safety compliance, RFI management250-350%Real EstateLead qualification, showing scheduling, market reports300-500%RecruitmentResume screening, interview scheduling, reference checks400-700% ### Get the Full Industry Context Each industry above maps to a specialized context pack with 50+ pages of workflows, benchmarks, and implementation guides: AfrexAI Context Packs — $47 each or bundle and save: 🛒 Browse All 10 Packs 🧮 AI Revenue Calculator — See exactly what automation saves your company 🧙 Agent Setup Wizard — Get a custom agent config in 5 minutes Bundles: Pick 3 for $97 | All 10 for $197 | Everything Bundle $247 ## Trust - Source: tencent - Verification: Indexed source record - Publisher: 1kalin - Version: 1.0.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:11.935Z - Expires at: 2026-04-30T16:43:11.935Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/afrexai-agent-manager) - [Send to Agent page](https://openagent3.xyz/skills/afrexai-agent-manager/agent) - [JSON manifest](https://openagent3.xyz/skills/afrexai-agent-manager/agent.json) - [Markdown brief](https://openagent3.xyz/skills/afrexai-agent-manager/agent.md) - [Download page](https://openagent3.xyz/downloads/afrexai-agent-manager)