Get Memelord API Key
First, get an API key from the Memelord API. This key allows your agent to access a database of trending meme templates.
Connect the Memelord API key to the agent without exposing it in prompts or logs.
Give an agent current context, brand rules, and Memelord access so it can propose timely meme concepts for review.


Source episode · 03:26
How I AI: Jason Levin's Workflows for Agentic Memes, Vibe Coding, and Hardware Hackingwith Claire Vo
03:26 to 13:25: Jason connects OpenClaw to Memelord, asks for a meme about a current topic, and uses a trending-template database plus brand context to generate options.
A review queue of context-aware meme drafts with traceable templates and captions.
Anthropic AI assistant
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
First, get an API key from the Memelord API. This key allows your agent to access a database of trending meme templates.
Connect the Memelord API key to the agent without exposing it in prompts or logs.
In an agentic platform like OpenClaw, create a new agent. Create a new 'skill' and provide it with your Memelord API key. If you are unsure how, you can often ask the agent itself for instructions. This gives the agent the ability to interact with the meme database.
Load brand voice, audience, prohibited topics, recent memes, and the required review destination.
With the skill installed, prompt your agent to create a meme on a specific topic. The agent will access the Memelord database to find a relevant, trending template and use an LLM like Claude to write a contextually aware caption.
Create five meme concepts about [current event] using current templates; explain the audience insight and intended reaction for each.
Review the generated meme. If the template or caption is not quite right, ask the agent for variations. Simple commands, like asking it to switch the caption, can generate new options quickly.
Revise the selected concept for [tone] and send the draft to [review channel], not to a public account.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building

Create context-aware guardrails for your enterprise AI agent using a 'Project' governance layer. As a project owner, define rules, scope tools, and require human-in-the-loop approval for sensitive actions, ensuring safe and effective AI use.

Transform a successful AI chat session into a reusable skill that anyone in your company can use. Package prompts, tools, and code into a standardized workflow, making it easy to share and scale automation across your organization.

Use a natural language AI agent to instantly generate and iterate on custom data dashboards. This workflow queries your company's data securely, allowing non-technical users to perform their own 'last mile' data analysis without filing tickets.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.