Aunoo AI Getting Started Guide
Last updated
Last updated
Welcome to AuNoo AI, an app to collect, analyze, and model unstructured, qualitative OSINT data.
AuNoo AI is an advanced, AI-powered OSINT news and trend analysis platform designed to help organizations and professionals make sense of the overwhelming flood of information and intelligence they must make sense of each day. Our solution harnesses cutting-edge artificial intelligence and data science to streamline open-source intelligence collection, analysis, and visualization. With real-time data ingestion from news, social media, academic databases, and more, AuNoo AI empowers users to uncover emerging trends, monitor potential threats, and extract actionable insights—all from a single, intuitive interface.
There are some things you need to do and should have ready before you begin setting up AuNoo AI.
You will need the following API keys:
NewsAPI
AuNoo uses NewsAPI to search for news. NewsAPI offer a free developer Tier with up to 100 requests per day
Firecrawl
AuNoo uses Firecrawl to scrape websites. Firecrawl offers a free plan with a one-time 500 credits (or scrapes) and $16/month for 3000 scrapes per month. For the CuriousAI nwsletter, we use aprox. 200 per month.
OpenAI
AuNoo utilizes OpenAI LLMs to automate news analysis. NOTE - you need an API account, not a Pro subscription, as we require a Key to use the API.
You will be sent a personal URL to log on to.
Select "Advanced"
Then Select “Proceed to < IP address>." and continue to the login screen
The initial login credentials are:
User: admin
Password: admin
You will be asked to create a new password after first logging in.
At least 8 characters long
Must contain at least one number
Must contain at least one uppercase letter
st contain at least one special character
You can change your password at any time from the configuration options in the app. You can find these options through the top-level menu: Configuration -> Configuration -> Security.
AuNoo AI uses what we call Collectors—basically, processes and pipelines designed to fetch data into the AuNoo Knowledge Layer. The Collectors encompass a variety of tools such as APIs that retrieve data from web services, active agents that retrieve data from websites, and even agents that converse with other agents, presenting a novel and exciting landscape.
AuNoo AI also relies on several different AI and machine learning models. At a minimum, we need at least one LLM to drive the analyses and automation. Smaller models suffice for many applications like sentiment analyses or classification, but reasoning models will perform better at trend analyses and topic summarization.
We configure Providers and AI Models under Menu -> App Configuration
The first thing you must do is add the API keys that AuNoo needs to operate:
OpenAI is currently used for most analyses, with support for Anthropic Claude and others available.
A Note on Costs
You can generate and manage API keys at:
You can add different models to accommodate different use cases and for greater control over cost and accuracy. As far as OpenAI is concerned, you can use the same API key for different LLM models, but due to the cost differences, we make this user-definable.
Firecrawl
AuNoo uses Firecrawl to scrape website data.
An open-source library is available to use for free but lacks measures to deal with CAPTCHA challenges and similar challenges. So we have also opted to integrate the SaaS service. Firecrawl provides scraped data in markdown, a format easily processed by AI agents and ML models.
For testing, Firecrawl has a generous free plan that gives researchers one-off credit to scrape around 500 pages, which translates to the same amount of articles or reports. A commercial license for 3000 scrapes per month costs around $16.
Newsapi
AuNoo AI uses NewsAPI to search news feeds.
The service offers a very generous free developer tier, providing a 30-day historical search and 100 results per query, and 100 queries per day.
Unlike simpler and less powerful news analysis solutions, AuNoo's design applies principles and practices derived from future studies and strategic theory. AuNoo AI can be used to track, analyze, and model a variety of different scenarios that we call topics.
Topics are very flexible and can represent almost any collection of information you can think of:
A market, for example, Cloud Service Providers, EV Battery Suppliers, or Threat Intelligence Providers.
A scientific or knowledge field, for example, Neurology, AI, or Archeology.
A group of organizations or people, for example, AI researchers, competitors, or even your favorite sports team or band.
And what we call a scenario, a specific question, or a set of questions, for example, is AI hype? How strong is the Cloud Repatriation movement? Are we outcompeting our competitors for share of voice?
Navigate to Settings -> Scenario Topic Management
You can either select one of the included example topics or just create a new one by adding a new Topic Name
A typical topic has the following characteristics:
Topic Name
Description of the topic, could be a question, a market, a field or even a group of people.
How big is the cloud repatriation trend?
How much of AI is hype
What are our competitors doing?
Categories
A topic is composed of categories. Categorizing your data points will allow us to mine and analyze them better and will help us understand our topics intimately. For example, nuclear power seems critical to powering an AI revolution. Cloud providers earnings results seem relevant to cloud repatriation, and your competitors would also be something you want to track in detail.
AI in Finance
Cloud Quarterly Earnings
Ford Motor Company
Future Signals
Future signals are indicators for the direction a topic can take. For example, future signals for an AI hype model could be "AI is hype" or "AI is evolving gradually.". In the case of tracking a market, it could be "Market Convergence" or "Market Growth Stalling.". But we can also get more granular, for example "New Hire", or "New Feature."
AI will evolve gradually
Hypergrowth
New Customer Acquisition
Sentiments
We mean the sentiment towards the topic, for example, optimistic towards AI progress. The simplest form is: Positive, Neutral, Negative. AuNoo AI can go even deeper and ask if the tone of an article is mocking, critical, or hyperbolic.
Positive, Neutral, Negative
Critical, Skeptical
Hyperbolic, Optimistic, Pessimistic
Time to Impact
In what time frame is the impact is expected in, for example, immediate, short term (3-18 months), mid term (18-60 months), long term (5 years+)?
Immediate
Short term
Mid term
Long term
Driver Types
What effect does the data point have on the topic? For example, a lack of progress in the nuclear power supply chain build-out would be an inhibitor for a fast AI revolution. Or a new discovery in developing faster, cheaper GPU memory will act as an accelerator or even catalyst for other AI fields.
Accelerator
Delayer
Blocker
Initiator
Catalyst
We give you two models out of the box, a Competitor Model and a Hype Model. Play with the defaults and extend and amend them to work with your scenarios and markets.
We also provide examples you can just drag in to help you get started.
Need Help Developing your Topic?
We provide an analyst to help you during onboarding to develop your first topics.
At the heart of AuNoo AI's philosophy lies the insight that analysis, whether human or AI, needs good-quality data.
The simplest way to track your topics is using our automated Keyword Alert Dashboard, which you can find under Keyword Alerts in the menu.
To set your Keywords up, select Manage Keywords.
From the Keyword Monitor view, select New Group.
You can now create a new group using a descriptive name and assign the group to a topic, and select Create Group.
You should see your new group in the Keyword Monitor overview. Select Add Keyword.
Add your keyword
From the Keyword Monitor view, select Settings to configure the Automated Monitoring settings.
We automatically calculate a recommended polling interval based on the number of keywords used and the available daily requests, based on your NewsAPI license. The default is 100, based on the free tier.
Be conservative with the polling interval. You may also need some of your daily requests for ad-hoc analysis, and there are actually very few use-case where you need up-to-the-minute news updates.
When you have set up your keywords, navigate back to the Keyword Alerts page.
If you configured Auto-polling, verify the settings. You can also use the Check Now button to test everything. If all went well, you now see your first articles appear.
Each Keyword Group has its own panel, with an overview of relevant articles. From here you can:
Delete Articles by marking the article ID (the number in the circle). You can also bulk delete.
You can mark an article as read using the checkmark. Read articles are hidden from view, but not deleted, and can be unhidden using the "Show read articles" toggle.
You can send individual articles for analysis (the Microscope icon) or send them in bulk, similar to how we bulk-delete.
You can also bypass paywalls using 12ft.io and Archive.is if you need to see the content of a paywalled article.
Monitored versus Analyzed Articles
When we add an article to the Keyword Alert dashboard, it is a raw article. At this stage, we have not done any other analysis or enrichment other than searching news for keywords. We need to send articles for analysis and enrichment through our News Analytics Pipeline for that.
This distinction is important to note when you review the vcharts and other model visualizations, and especially when you write reports. You may want to only include enriched data points, so be sure to filter for analyzed articles.
Now that your first Keyword Alerts are configured, sit back and watch the news come in.
There are four other ways you can get news articles and academic reports into AuNoo. You can find these under the Research menu.
You can search for keywords or phrases to search for in the article title and body.
Some advanced search options are supported:
Surround phrases with quotes (") for exact match.
Prepend words or phrases that must appear with a + symbol. Eg: +bitcoin
Prepend words that must not appear with a - symbol. Eg: -bitcoin
Alternatively you can use the AND / OR / NOT keywords, and optionally group these with parenthesis. Eg: crypto AND (ethereum OR litecoin) NOT bitcoin.
Other options include:
Show: Defining how many articles to show in the feed. We have set no limit, but be mindful that too many will likely cause the app to become slower.
Delete: You can delete a monitoring widget. Caution! Right now we can’t restore them easily.
Hide: You can Hide uninteresting or miscatogrized articles
View: You can view any article based on the original URI
Bypass Paywall: You can send an article URL to archiv.is to bypass some paywalls. 12ft.io is another option.
Analyze: You can send an article directly to be analyzed using AI ready for saving.
Via Research -> News Search, you can conduct deeper ad-hoc news research.
Begin by selecting the Topic you are researching
Select a source. At this time, we support:
Newsapi: Search in Title, Description, or Article Content
Sort by Relevancy, Published Date and Popularity
Filter by Domain, Language, and Date range.
Supports keyword and phrase search with advanced options
Use quotes for exact phrases: "artificial intelligence"
Use + for required words: +bitcoin
Use - to exclude words: -cryptocurrency
Use AND/OR/NOT: crypto AND (ethereum OR litecoin) NOT bitcoin
Arxiv:
Search in Title, Abstract, Author, Comments, Journal Reference.
Filter by Category and Date Range.
Supports keyword and phrase search
By default, AuNoo displays 10 articles. This can be defined, but be aware that the free newsapi tier limits queries to 100 results.
As with theKeyword Alert Monitoring dashboard, you can view an article, bypass paywalls, or send it for analysis. In addition, you can select multiple articles and send them for analysis in bulk.
Article Submission
Bulk Article Submissio
Analysis capabilities can be found under Analysis in the app menu.
You can select a topic and filter articles by category, future signal, sentiment, tags, keyword, and date range. Articles can be selected and added collectively and rendered in Markdown.
Reports are rendered immediately and can be edited directly before being exported.
Report Analyses
Some additional analyses can be included:
Overview
Insert a short summary of article count and date range covered in the report
Report Markdown Configuration
Markdown output can be configured via a simple template, using a number of different variables:
Available variables:
{category},{title},{news_source},{url},{summary},{sentiment},{time_to_impact},{future_signal}
AuNoo AI allows you to review and edit articles, as well as compiling and summariing them into markdown. This is really useful if you are writing up reports, or even a newsletter. But the true value of N0rnAI lies in the integrated Hype Model.
TIP: The NornAI app includes a pared-down version of the Analytics Dashboard. A more comprehensive Analytics app is available as the AuNoo AI Scryer.
Begin by selecting a topic via the dropdown selector. You can filter based on individual categories and timeframes. The dashboard will show you the total count of articles based on your selection.
Charts are interactive and can be downloaded in PNG format
You can manage and edit articles stored in the database via Analysis -> Edit Articles
Begin by selecting a topic from the dropdown selector. You can filter based on Categories, Sentiment, Future Signal, Time to Impact, Driver Type, date range and also search article titles and summaries. Multiple choices are supported.
Articles can be deleted and edited
Articles can be grouped using Tags.
Annotating articles is on the roadmap.
The publication date is extracted using an LLM, so this can sometimes lead to halucinated dates.
When you first open the page, you will be presented with a “This connection is insecure” message., as we are using for the proof-of-concept phase.
Note that you will need ; the free and Pro licenses do not include this.
We used o1-mini throughout most analyses, using around $3 for upwards of 250 articles per month. You can also to avoid any unpleasant surprises.
, or scenario modeling, is a strategic approach used to explore and prepare for multiple future outcomes by building detailed, plausible scenarios based on current trends and uncertainties. It helps organizations identify potential risks and opportunities, enabling them to develop flexible strategies and contingency plans. By simulating various future states, decision-makers can proactively adapt to changes and navigate uncertainty more effectively.
AuNoo supports keyword monitoring of academic publications via arXiv. You also get an additional keyword newsfeed alert via to compliment the academic topic you are monitoring. We support one news and one academic paper column per topic, and these are created automatically for you.
