I created an idea engine that finds trending topics and provides them in the buffer

I use Buffer to post on LinkedIn about the tools and technical updates that support my work as a full-stack engineer. The scheduling, the queuing, the publishing – it all works great for me. But there was always that one moment in the workflow where I got stuck.

I opened Buffer, navigated to Create Space and just stared at a blank screen.

It’s not that I don’t have anything to say. But if I sit there and think about what I should actually post (what’s trending right now? What are people around me paying attention to this week? What topic is even worth writing about?), I would be going in circles. There are many topics. That was never the problem. The problem was choosing one, finding the right angle, and getting it into the shape I wanted to publish.

So I created a web app called Buffer Ideas extension This comes before Buffer’s Create Space workflow. It asks a few questions about who you are and what you’re working on, generates structured content ideas based on the actual trends in your field, and pushes the ideas you like directly into Buffer via the API.

Here’s why I built it and how it all works.

Why I decided to build the Ideas Extension

Every idea generator I tried had the same problem: it didn’t know anything about me. I would get the same general suggestions regardless of who I am or what I do: “Provide a behind-the-scenes look at your process,” “Post a tip that your audience would find helpful.”

Prompts like these are a good starting point, but they have no bearing on what’s actually happening in my industry today. They don’t know my niche, they don’t know my audience, and they definitely don’t know what’s hot in my field.

I wanted a tool that knew something about me before it tried to help me. So I built it.

The concept was pretty simple: what if, before generating a single idea, the tool first asked a few questions (your industry, the topics you’re interested in, who your target audience is) and then actually used that information to research every time? So the ideas it gives you are tailored to you.

Since I’m a software developer, I drew on that experience when developing the app. For the technical folks, I used an Nx monorepo with a NestJS backend and an Angular 19 frontend as the stack. And even if you’re not tech-savvy, you can still accomplish much of the same thing.

This is how the Buffer Ideas Extension app works step by step

When you first log in, the Ideas Extension will ask you three questions:

• What industry are you in?
• What topics interest you in this industry?
• And who is your target group?

That’s it. You go through three screens and it takes about 30 seconds to complete. These answers will be saved to your profile and will be included in every idea generation request from that point on. The model relies on the context of who you are or what is important to you to generate ideas.

When I toured with Tami from Buffer’s content team, she chose creative as her industry, photography, writing, and video as her areas of interest, and early-to-mid-career professionals as her audience. Every idea the app generated came back filtered through this lens and based on what was actually trending in the creative space that week.

It’s really simple for the user, but there’s a lot more under the hood.

What happens when you click generate?

After you enter your information and click “Generate Ideas,” the app goes online in real time and searches for trending topics related to your industry and interests over the past 72 hours or so.

I use a single OpenAI Responses API call per request with web search enabled and a strict JSON schema for the output. The prompt asks about current trends and returns five ideas for each.

But that’s only part of what the app offers. I didn’t want the app to return vague one-liners. When I plan a post, I need to know the angle, the hook, the points I’m going to make, and the call to action (CTA).

So each idea is returned as a complete package with a title, hook, body outline, call to action, key discussion points, suggested format, hashtags, recommended platforms, the trending topic it’s linked to, and a source URL if the search finds one. You get something you can sit down and design straight away.

I’ve also added rich text formatting, which allows you to bold or italicize text, add bulleted lists, links, etc., all while using Unicode to preserve formatting on platforms like LinkedIn. I always format my LinkedIn posts with bold and bulleted text and wanted to be able to do this without leaving the app.

Push ideas directly into Buffer using the API

Everything up to this point, from the onboarding to the hooks and hashtags, would be useful in its own right. But that would also mean that I’m still manually copying and pasting things into Buffer, and it’s all about removing friction in the workflow, not just moving it around.

So the final step was to connect directly to Buffer using the GraphQL API.

In the app settings, add your personal access token from Buffer. Once connected, you can go to your dashboard, select one or more ideas, click “Post to Buffer” and they will land in your “Create a Space” section. The app marks which ones you have already pushed so that you don’t lose track.

My goal in building the Ideas extension wasn’t to replace Buffer – I just wanted to make sure I came to Create Space with something waiting for me to work with.

What has changed in my content creation process?

I can’t show you a proper before and after, but I can tell you what has changed in the way I work.

The most obvious improvement is that I post more because there is a lot less friction. My ideas are also much higher quality and I think web search is the reason for that. Because search is included in the same process as idea generation, the ideas are usually related to current events. And since every idea comes with a hook, talking points, CTA, and hashtags already attached, I’m no longer starting from scratch.

Even the smaller features ended up being more important than I expected. The viral hooks and hashtag suggestions sound like “nice-to-haves,” but in practice they made the difference between stopping at a rough draft and having something I wanted to publish.

Those little moments of “What do I open with?” and “Which hashtags do I actually use?” I’ve been eating for longer than I realized.

And then there is the confirmation that this problem goes beyond me. The reactions from people at Buffer, from other developers on LinkedIn, and from being involved in public relations showed me that the gap I was trying to fill was the right one.

Ready to build?

If you’re interested in trying out Buffer’s API, we have resources to get you started. Our developer docs cover the GraphQL schema, authentication flow, and quickstart examples. The Buffer MCP server documentation will guide you through connecting to Claude or another MCP-compatible AI agent.

If you need practical help, our support team is at your disposal. Alternatively, you can join our Discord server and chat with other people working with the API.

We’d love to hear what you do. Find us in Discord, or @buffer on all major social channels.