(Not that all of us ever found it boring.)
Documentation is critical to building institutional knowledge at any organization. It’s the ledger of your org’s impact, history and DNA: whether that’s an internal written policy, technical documentation, annual report, style guide or something else entirely.
Documentation is also often the last thought in the technology process. It’s that task you know you should do, may even try to do, but usually don’t get around to because it simply isn’t priority.
So we just tell ourselves that as long as the info lives in somebody’s head, our orgs will be fine.
Enter AI, which presents a new and unique opportunity for all of us to do better. First, AI can be great for getting new documentation done at all. Generative AI can help produce thorough & useful reference material for your org, with the right prompting and human review.
p.s. Those last two pieces are super important/can be its own blog post. Because without them, AI can also do the reverse: produce ample, even excessive amounts of useless material for your org that masquerades as helpful.
But going further, AI can also help you decipher and act on existing documentation. Put another way, docs can provide pre-baked context that can take your prompting to the next level.
For those who don’t know, context is the information/memory/data that AI uses to generate relevant responses. Anything you type into an AI chat directly, or the files you link in a chat/project/knowledge base/wherever, all act as context that tells the AI what it needs to know.
And for processes that could benefit from AI-led automation, docs can form the base for creating instructions for those AI agents. Technically a separate work stream, but with the same potential.
So don’t think of your org’s docs only as institutional weight. Start treating them as a strategic well of context for your chosen AI. And if your org’s doc maintenance is top notch, then you can start to see how the utility potential really ramps up.
The better your org’s documentation muscle, the more tailored & usable AI becomes.
Before you go dumping all of your docs into ChatGPT..
Or Claude, Perplexity, or whatever your team’s AI tool of choice is these days!
Like with all prompts, consider your data-sharing agreements when deciding what information to give to AI.
For example… if your team’s data may be used to train models, then you likely don’t want to share intellectual property or other proprietary info about your org. (In this scenario, you also don’t want to enter anyone’s personal or sensitive data either – out of respect for their data privacy. )
You also want to consider the relevance of the information you’re sharing. AI won’t know that an aspect of your process is out of date, or that one of the programs outlined in your onboarding manual is slated to retire, or that you no longer use certain language when referring to constituents. Yet it’s going to deem whatever information you give it as relevant, because you’re giving it that info.
Think about it like onboarding a new coworker, but giving them outdated information about your organization. At best, it’s not useful. At worst, it can be harmful to your work.
How AI makes existing documentation more useful
The list below is not exhaustive. There are probably many, distinct ways that you – or another person at your org – can extract unique value by applying AI to your org or team’s docs.
But the examples below are meant to give a varied taste, and they all share the same efficiency benefit. Using documentation as context 1) saves time with our AI prompts AND 2) contributes to more relevant AI outputs.
Think about your experience in an AI chat. Each time, you provide contextual info to focus the output: details like what you want to see, the format, and the background info that needs to be considered in relation to performing that task correctly.
Documentation, when incorporated into your AI use, can spare you some of that initial explanation or post-output corrective prompting. This helps with efficiency and consistency.
And I should note, these benefits are in service of supporting human staff. The items below are not replacements for the work your people do, nor should AI be used to make final decisions driving each use case. Because AI will never know your org like your people do, and no amount of stellar documentation changes that.
That said, on to the examples.
6 Distinct Ways to Leverage Docs with AI
1) Reproduce tone, style & branding
If your org has a blog, impact report or even a style guide that breaks down “how” your org presents itself to the world – this can provide the base for creating useful instructions that AI can run with when generating new content – like external reports slide decks, or whatever else. (A real person should still hold final responsibility for reflecting your org’s brand & voice in materials.)
2) Optimize processes & workflows
This has been one of my favorite, new ways to experiment with AI. Workflow diagrams are incredibly useful for visualizing the steps in a process and seeing them in relation to the whole. You can always use AI to build these if it’s too daunting to do yourself, but you can also use AI to examine those diagrams and explore ways to optimize. In your prompt, provide extra narrative on which steps in that flow tend to cause bottlenecks or issues – or where you want to see different results – and see what AI has to offer.
3) Optimize data/tech architecture
Similar to the last point – data model diagrams, data dictionaries, dev philosophies or any other technical documentation can be good fodder for an AI-assist on your tech approach. (But let your trusted tech person be the final judge on how actionable those recs really are.)
4) Unearth follow-up tasks
If there’s one thing that’s harder to get around to than creating docs, it’s updating them! So if you’re not sure which policies could use a refresh, or whether it’s time to update aspects of your org strategy or research, AI could provide useful recs and structure – including what to tackle and a plan to help you execute those updates.
5) Translate reports or SOPs to new AI-driven processes
We briefly covered this in the previous section. For processes that make sense to automate with generative AI (not all of them will!), docs can provide a helpful base for creating specific, AI-friendly instructions. You can then plug into your Claude Skills, Gemini Gems or any of the other LLM equivalents.
The point of having these instructions is so you can call them into your future prompts, and they run on their own. For repeatable generative tasks, this is a great timesaver so that you’re not writing out the instructions yourself every single time.
6) Use AI to document AI
Documentation is an important driver of accountability. So if we’re adding new technology to the stack – one that currently creates more work/management for us – then AI might as well help lighten the load.
You can obviously use AI to generate any text you choose (which again needs human review). But for understanding AI use around a specific task – especially programmatic ones involving stakeholders – you can also prompt it specifically for recaps of your chats. Depending on how you choose to structure those, you could build an ‘AI log’ process that helps your org document when AI was used and where exactly it provided guidance. Then save those to your main folders as part of the record.
Wrapping Up + Tips
AI is giving the documentation process some new life. If you ever needed a reason to be diligent about documenting your processes, technology and org artifacts, that reason has arrived.
So if you’re sold on getting started, start small. First, audit those considerations I mentioned above – like your doc relevance and data-sharing agreements – before anything else.
Next, pick a document or specific task you want to try. When you’re just starting out, the best AI experiments are your low-hanging fruit: tasks that don’t carry much risk if they go wrong, don’t require a ton of upfront lift, but do carry a tangible benefit if done well.
And if you’re strapped for time, set a timer for how long you’re willing to give AI a chance to show what it can do. It’s easy to get sucked in to prompting and re-prompting as you engage in “conversation” with your AI chat (part of the design of these tools, unfortunately). Constraining your time in a single sitting helps keep you honest — and doesn’t mean you can’t set another session trial for another time.
Leave a Reply