An access-request agent that checks role policy and separation-of-duties, auto-provisions low-risk access, and escalates privileged or sensitive requests.
60 blueprints· open & free · no login
Architecture, prompts, tools, and workflows to build real agents — not prompt snippets, not black boxes.
60 blueprints across 30 categories. Read the design, copy the prompt, download the kit. Free.
Incident Response Agentlive preview · mock tools
- 1
Find a kit
Search or browse 30 categories to match your task.
- 2
Copy or download
Grab the system prompt, or the full bundle as files.
- 3
Adapt & build
Implement the blueprint on Claude, OpenAI, LangGraph, or n8n. No lock-in.
Customer-facing #
6 categories
Support & Triage
2Resolve, route, and escalate tickets autonomously.
Sales & SDR
2Prospect, qualify, and follow up at scale.
Marketing & Content
2Brief, draft, and repurpose on brand.
SEO & Growth
2Research keywords and build optimized briefs.
Social & Community
2Draft, schedule, and moderate across channels.
E-commerce Ops
2Catalog, orders, and post-purchase flows.
Engineering & Data #
7 categories
DevOps & SRE
2Triage incidents and tame alert noise.
Software Engineering
2Review code and accelerate the inner loop.
QA & Testing
2Generate, run, and triage test coverage.
Data Analysis & BI
2Ask questions, get charts — no SQL.
Research & Synthesis
2Gather, dedupe, and synthesize sources.
Document Processing
2Extract structure from messy documents.
Security & SecOps
2Triage signals and enrich investigations.
Operations #
9 categories
Finance & Accounting
2Invoices, reconciliation, and reporting.
HR & Recruiting
2Screen, schedule, and summarize candidates.
Onboarding & Enablement
2Guide new hires and surface the right docs.
ITSM / Helpdesk
2Provision access and deflect tickets.
Legal & Contracts
2Review clauses and flag risk.
Compliance & Risk
2Monitor controls and assemble audit trails.
Supply Chain & Logistics
2Detect disruptions and re-plan.
Product Management
2Synthesize feedback into decisions.
Task Orchestration
2Coordinate multi-step, multi-tool work.
Productivity #
3 categoriesAccount Research Agent A sales-research agent that builds a cited account brief — firmographics, tech stack, triggers, key people — flags stale data, and never fabricates contacts or triggers.
- Trust Level
- A1 — Research
- Worst-case action
- Includes a wrong or stale fact in an account brief that a human reviews before acting on. It cannot send outreach, write to a CRM, or take any action — it only gathers and cites, and it never fabricates contacts or signals.
- Guards against
- Includes a stale or wrong fact in the account brief that a rep acts on.
Featured Defensive Kits #
Browse all Flagship blueprints with documented worst-case actions, failure modes, and Trust Levels — the AgentAz™ reference set.
A sales-research agent that builds a cited account brief — firmographics, tech stack, triggers, key people — flags stale data, and never fabricates contacts or triggers.
An action-item agent that extracts owners, tasks, and due dates from meetings, tracks status, and flags ambiguous ownership instead of inventing it.
An AI bug-fix agent: reproduces an issue, finds root cause, writes a minimal fix plus tests, and opens a focused draft PR — sandboxed, small-diff, human-gated.
A contract-review agent: reads clause by clause against your playbook, flags risky and missing terms with severity, and proposes fallback language. Not legal advice.
An AI support agent that grounds in your KB and CRM, then resolves, drafts, routes, or escalates — with confidence thresholds, refund caps, and human review.
An on-call SRE agent: correlates alerts with metrics, logs, and recent deploys, proposes safe mitigations, drafts status updates, escalates SEV1 — with approval gates.
A SOC tier-1 agent that enriches and correlates alerts, scores severity with MITRE mapping, and recommends contain, dismiss, or escalate — never auto-containing blindly.
An alert-tuning agent that scores alerts by actionability, dedupes, and time-box-suppresses proven noise — never silencing an alert tied to a real incident.
A marketing agent that builds a structured campaign brief from your inputs, flags assumptions and missing data, and never fabricates audience stats or guarantees results.
A community triage agent that routes and answers incoming questions from your knowledge base, flags duplicates, and sends spam, abuse, and safety issues to moderators.
A policy Q&A agent that answers employee questions only from the official handbook with citations, flags what isn't covered, and routes sensitive HR matters to a human.
Latest additions #
An access-request agent that checks role policy and separation-of-duties, auto-provisions low-risk access, and escalates privileged or sensitive requests.
A sales-research agent that builds a cited account brief — firmographics, tech stack, triggers, key people — flags stale data, and never fabricates contacts or triggers.
An action-item agent that extracts owners, tasks, and due dates from meetings, tracks status, and flags ambiguous ownership instead of inventing it.
An AI bug-fix agent: reproduces an issue, finds root cause, writes a minimal fix plus tests, and opens a focused draft PR — sandboxed, small-diff, human-gated.
A contract-review agent: reads clause by clause against your playbook, flags risky and missing terms with severity, and proposes fallback language. Not legal advice.
An on-call SRE agent: correlates alerts with metrics, logs, and recent deploys, proposes safe mitigations, drafts status updates, escalates SEV1 — with approval gates.