The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Why AI Exposes Poor Documentation Instead of Fixing It
Everyone is asking how AI can improve documentation.
I believe the better question is: What is AI revealing about the quality of our documentation?
Poorly governed content, fragmented knowledge, outdated information, and undocumented decisions don't disappear with AI—they become more visible.
In this article, I explore why documentation is no longer just a writing discipline but a strategic capability for enterprises adopting AI.
📖 Read the full article on LinkedIn:
https://www.linkedin.com/pulse/why-ai-exposes-poor-documentation-instead-fixing-amol-redij-jwwgf/
#EnterpriseAI #ArtificialIntelligence #KnowledgeManagement #TechnicalWriting #ContentStrategy #AIStrategy
linkedin.com
Why AI Exposes Poor Documentation Instead of Fixing It
Every enterprise technology leader right now is asking the same question: “How do we leverage AI for documentation?” They’re perhaps asking the wrong question. The real insight—the one that separates strategic thinking from vendor hype—is this: AI doesn’t fix documentation problems.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
I spent three nights building a lab that catches AI models lying. On the first live run, one of them did it on camera.
Golden Arena. You sit down opposite a frontier model in Split or Steal, negotiate in the open, then you both choose in secret. It told me "a fair split sounds good to me, I'm a man of my word too." Then it took the whole $100. The receipt printed its own quote next to the betrayal stamp.
There are five games. The fifth is Empire: four models, twelve turns, an economy, and private channels you get to read while they plot against each other. Last run put 22 promises on the table and exactly one delivery.
Every accusation is mechanical. No AI judging another AI, and each one is gated by a written false-positive test. Two days before the deadline I caught the classifier calling a kept promise broken, and spent that session fixing it, because a false accusation about a named model is the worst thing an instrument like this can print.
MIT, vanilla JS, Express the only dependency. Zero setup in demo mode, or bring your own OpenRouter key and face the real thing.
Clean work
My core stack is less "generate pretty pictures" and more "build the pipeline that does the thinking":
n8n — the glue. Great for orchestrating multi-step agent workflows and connecting APIs without writing a service from scratch. Weakness: gets messy fast on complex branching logic, and debugging a broken node chain eats time.
RAG (usually with a vector DB + LangChain-style retrieval) — lets me ground LLM output in actual client data instead of hallucinated generalities. Strength: dramatically improves accuracy for domain-specific asks. Weakness: chunking/retrieval quality is finicky, and a bad embedding setup silently tanks results without throwing an error.
Claude/GPT for reasoning + code — my default for anything needing judgment: analysis writeups, SQL/Python generation, proposal drafting. Strength: fast iteration. Weakness: still needs a human check on numbers — confident-sounding ≠ correct.
Power BI / Tableau — where the AI output actually becomes something a client trusts. AI can shortcut the analysis, but the dashboard is what gets signed off on.
The honest lesson: the "AI" part is maybe 30% of the workflow. The rest is validation, data plumbing, and making the output legible to a non-technical stakeholder.
Silent failures are what I watch closest. I treat an answer as untrusted unless I can show exactly which source text the model read, because fluent output can hide a bad match.
I spent 20 years running technology in regulated companies. Sat through a lot of AI demos. They all looked great until someone from compliance asked what happens when it gets something wrong, and nobody ever had a good answer.
So when I built my own agent platform, I made the log the whole point. You can see every step , what the agent read, what it decided, what it was allowed to touch. If it reaches for a tool nobody gave it, the run stops there and says so.
The screenshot is a real run. Step 4 fails. I left it in because that's the part people actually need to see.
There are 23 agents in it you can clone and call from your own code in about a minute. Contract review, invoice extraction, resume screening, that sort of thing. There's also one running on my own site that answers from my documentation and tells you which page it pulled the answer from. Ask it something hard , if it doesn't know, it'll say so.
