One of the biggest challenges I face as a content expert is repurposing my written blogs for social media. Before now, I had to ask AI for summarie...
For further actions, you may consider blocking this person and/or reporting abuse
The right link made me reach to the right blog. LOL
btw, this looks good. I will try posting on X.
You tried it! 😁
Glad to see it worked.
The discord function can't work for you though, as it's currently hard coded.
But v2 is rolling out soon, and it'd be better.
I'm not going to use the discord one anyway. I've no personal community to share within. LOL
Great work btw.
The repurposing problem is so real writing the blog is only half the work, then you have to rewrite everything for Twitter, LinkedIn, Instagram separately. The fact that you actually built a tool to solve your own problem instead of just complaining about it is the best kind of developer thinking. Curious does the tool adapt the tone for each platform automatically, or do you give it platform-specific instructions each time?
Yeah, great to have actually built a tool for it. peak content engineer moment.
I gave it platform-specific instructions in the agent_instruction.md file.
Thank you so much.
Sounds promising! We're also building our own internal tool for writing, image generation, posting on our site and sharing on social media. It's all part of the main repository, so the AI agents have full context on planning, specifications, code, and public content.
That sounds amazing!
Giving agents full context of the repo is the context infusion any internal tool that needs company centric context needs.
I’m currently focusing on the 'content-out' flow, but I can see how having the planning specs in the context window would make the social media strategy even more targeted.
Are you using a RAG-based approach for the repository context, or just feeding it in via the long context window?
No special equipment is involved. This is all basically done in Cursor. Just a few project rules so that the model knows where to find things.
Ah. This is nice!
A feature suggestion, although I understand that this is an internal tool and that's why some things are hardcoded: make the social media selector dynamic. Such that someone can put in their own social media and post on it.
Watch out for V2!
Author update: A few people here asked about using response_mime_type to eliminate the JSON sanitisation regex — turns out that was the right instinct. I went down that rabbit hole for v3 and benchmarked Gemini's responseSchema against Claude 3.7 Sonnet on four constraints specific to this pipeline. The 11.5% JSON adherence gap between the two models is what sealed the decision. Full write-up if you're curious.
just tried it. great work Dumebi! 🔥
I think the best way to improve this would be to give users (or yourself) the option to choose whether they want the agent to create posts using a default style or allow them to attach a few sample posts for each platform (linkedIn, x, discord). The agent could then use those as prompt context and generate posts in the same style.
by the way, where have you hosted this? 😂 deployment platforms use such weird names these days instead of the actual project name.
The JSON sanitization middleware for Gemini output is smart — ran into the same code-block wrapping issue with Claude and ended up building a similar regex strip layer.
Yaaay. I didn't understand it initially, but I've understood it a lot better now.
Love this — the JSON sanitization middleware for Gemini output is the kind of unglamorous detail that makes or breaks a production AI tool. I've run into the same markdown-in-JSON issue with Claude outputs. The instinct to vibe-code internal tooling is underrated; there's no better way to tighten your own workflow than shipping something quick and iterating on it. Curious what the next bottleneck is now that you've freed up 4 hours — usually clearing one constraint just surfaces the next one.
The HITL architecture choice is the most important thing here, and I'm glad you called it out.
I've seen the opposite pattern fail badly — people build fully automated content pipelines, ship garbage for two weeks, then wonder why engagement tanked. The METR study showed developers think AI makes them 24% faster but actually measure 19% slower. The perception gap is real, and it applies to content too: AI-generated social posts feel right but often miss nuance that only the author would catch.
The Gemini Pro choice over Flash for strict JSON enforcement is smart. Structured output is where cheaper models fall apart first — they hallucinate keys, skip required fields, return markdown when you asked for JSON. That validation layer probably saves you more debugging time than the cost difference.
Curious: do you have any automated checks on the generated posts before they hit the approval queue? Even simple things like length limits or keyword blocklists can cut the review burden significantly.
In the agent_instruction.md, I have blockers for specific keywords.
I love the framing of agency over automation. The moment you said it reads your actual articles, builds a campaign, then waits for you to audit and approve, it felt like you actually understood the real failure mode of most content tools. They produce output, but they do not carry your context or your standards.
The audit step is the whole thing. If you can see what it is about to post and why, you can keep your voice intact and avoid accidental nonsense.
One thought that might level it up even more is making the tool show its receipts. Like a view that points back to the exact paragraphs it pulled from your article, so you can spot drift instantly. Same with a simple way to flag phrases it is not allowed to use, or claims it must never invent.
How are you handling voice consistency over time. Are you feeding it examples of your past posts, or do you keep a small style guide inside the tool so it does not gradually flatten you into generic content tone.
Love this. Internal tools are where AI-assisted development shines because the cost of bugs is low and the iteration speed matters.
I've taken this approach to the extreme — my AI engineering agent (TARS) builds internal tools autonomously. This week alone:
The trick I've found: give the agent a very specific, self-contained task with clear acceptance criteria. "Build a QR code generator on localhost:5555 with custom colors and logo upload" → done in one session. "Improve the product" → chaos.
The 4 hours you saved compounds. Once you have the internal tool, your AI agent can use it too. My agents now use the tools that other agents built. That's when the real acceleration kicks in.
This is the part most people underestimate. AI becomes much more valuable when it’s used to reduce workflow friction instead of just generating output. The tools that actually last are usually the ones that make repeated work simpler, not just faster once.
Looks like worth enough to try it.