In short:
ak-playruns a marketing playbook (a product launch, a campaign, an idea check) step by step, with approval gates and goals. Each step goes to the skill or agent the template names. It does not write content itself, it orchestrates.
Disclosure: I maintain AgentKit and have an affiliate relationship with it: the AgentKit link in this post is an affiliate link; buying through it gets you 30% off.
Summary
Use it when you want to launch a product, run a campaign or check whether anyone needs your idea, without keeping track yourself of which step comes first. Note: ak-play does not write content itself. It coordinates and hands each step to the right skill or agent.
flowchart LR
A["Idea, campaign, launch"] --> B["ak-play create"]
B --> C["ak-play next, step by step"]
C --> D["The step's skill or agent"]
D --> C
C --> E["Gate: you approve or reject"]
E --> C
C --> F["No steps left: playbook done"]It revolves around 4 things:
| Thing | Question | Example |
|---|---|---|
| Playbook and template | Which script do you follow? | Template product-discovery: market evidence, positioning, demand test, decision |
| Steps and dependencies | Which step can run now, which must wait? | Positioning is only ready once the opportunity comparison is done; redo a step and later steps become stale |
| Quality gates | Where must a person decide, so the machine cannot pass on its own? | The demand test stops at gate-pending; nothing is posted, sent or paid for until you approve |
| Goals and suggestions | What next moves the weakest number? | New signups sit at 36% of target, so steps that affect signups top the 3 suggestions |
The most important stop is the gate: a gated step stops at gate-pending and blocks later steps until you approve. State lives in the playbook's manifest, so you can stop halfway and pick up again later.
Sample prompt for checking a product idea:
/ak-play create <product name> --template product-discovery| Flag | What it is for | Since ak |
|---|---|---|
--template | Pick the template up front when creating a playbook | 1.0.0 |
--browse | Browse community templates | 1.0.0 |
Below is the full guide: how it runs, 6 situations with prompts, each flag explained, the change history by ak release, and common pitfalls. The full guide and the visual page are for subscribers. Your agent can also find them through the portal's MCP.
Opens when your account has subscriber access
This guide is for subscribers
Once your account has access, the full piece, the interactive visual and the agent call all open.
- Sign in or create a modernEngineer accountReading access belongs to your account email.
- Choose a plan on the pricing page1, 3 or 12 months, paid by VietQR bank transfer. Access opens about a minute after the money arrives.
- Or redeem a Facebook subscriber codePeople supporting the page on Facebook get an activation code by message each month.
Already a subscriber? Sign in to read.
Use this piece in your agent
Get an API keyCopy the text below and paste it into Claude Code, Codex or whichever agent you use. The agent reads the piece and checks it against the repo you have open.
Read "ak-play: run a marketing playbook step by step, with approval gates" on modernEngineer and apply it to this repo.
1. Call the content_get tool of the modernengineer MCP server with locale "en", slug "ak-play". If the modernengineer MCP server is not connected, stop and walk me through connecting it from https://modernengineer.dev/en/mcp.
2. Summarize the main steps of the piece and point out which apply to this repo.
3. Propose concrete changes and ask me before editing any file.Connect MCP in Claude Code (once)
claude mcp add --transport http modernengineer \
https://api.modernengineer.dev/mcp \
--header "Authorization: Bearer <API key>"Reading the full piece over MCP needs an API key from a subscriber account or one that bought this guide. Without access, the agent only gets the opening.
- Version
- v1.0.0
- Updated
- 22/10/2026
- Licence
- All rights reserved
- Slug
- ak-play
