Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

What is Phocas AI Phocas AI gives you quick answers and insights by simply asking a question in your natural languagerelevant to your own business databases. This form of analysis is particularly helpful for new or occasional Phocas users and occasional users, as they are not yet , who aren’t familiar with the functionality of Phocas.

Currently, Phocas AI can only return results that can be found using the Analytics user interface. In other words, it can’t do things you can’t do in Phocas. However, it can make use of Custom mode on your behalf - a feature mainly used by more advanced users.

Period types are important. Uses first default period type (Day, Month or Year) in list when returning results, e.g. Year or Month. Sometimes one of these is not enabled in database. Supports Week and Quarter custom period types. Handles custom periods.

User database permissions and restrictions are respected, so only results that you have permission to view will be returned.

Can filter by selected entities

Use history as a baseline for similar questions. History is database-specific.

Benefit - You can ask a question in your terms and see the steps that were taken to get the results. Learn as you go.

Get started with Phocas AI

If you’ve been invited to use Phocas AI, you’ll see a welcome message on the right of your screen when you open a database in Analytics.

image-20240123-235350.pngImage Removed
  1. Click Let’s go to activate the AI feature.

  2. Type a question into the box and click Ask. Tip: You don't have to use a question word or question mark.

  3. Rate the response and ask more questions as required.

    Image Removed
Get image-20240206-193846.pngImage Added

Getting the most out of Phocas AI

starts by asking good questions

Phocas AI can’t read your mind , - it takes the question you ask and uses probability to infer what you mean. Start by asking good questions, as the less inference required, the greater the chance of a correct answer.

Here are some samples of the types questions to ask:

  • Show me the best selling product over the last 12 months

  • Sales reps whose sales value has increased by less than 5% over last 2 quarters

  • show me customers who bought more in 2022 than 2023

  • What are the top performing sales reps this year?

  • What regions are ahead of budget this quarter?

  • Who sold the most products in UK last month?

  • Cities with the highest sales between last Black Friday and the end of 2023. Use reporting value.

  • Sales in [region] this year.

  • top selling product for the supplier Acme by quantity last week

  • Plot sales for Engines onto a column chart by month for the last 5 months

Based on the samples above, here are some tips to think about when writing your questionquestions:

  • Remember to include a date range - Compare '. For example, compare "What are my sales?” vs “What What were my sales last quarter?. Besides the usual date types (3 days ago, last month, this year etc), we also understand any custom periods you may have definedThe latter question will yield better results.

  • Specify the stream, if applicable. For example, if you have three budget streams, it’s helpful to specify the one you are interested in.

  • Use terms from the database where possible - we understand . Phocas AI understands synonyms but they are less accurate that explicit than explicitly naming the data element of interest, particularly if when the term is ambiguous. e.g. If For example, if the dimension is called ‘Customer’ try not to use ‘Account’

  • Think about specifying the stream - if you have 3 budget streams then it would probably be helpful to specify the one you are interested in

  • Customer, don't use Account.

  • You can use wildcards, either * ' or '%’ - eg “code or %. For example, “code like PR3986* for August august 2023 sorted by cost price descending”descending”.

  • The Your question doesn’t need to be in English , - we’ve tested a bunch lots of languages with great success.

  • If you want to view the data in a pie chart or graph then , ask for one. Phocas AI supports all most of the standard charting optionstypes of charts, with more coming soon.

  • Don’t worry to too much about spelling unless it’s vital for the question - we know what you mean by ‘customer’, but ‘Amce’ probably won't resolve to ‘Acme’

Sample Questions

  • Show me the best selling product over the last 12 months.

  • Sales reps whose sales value has increased by less than 5% over last 2 quarters

  • show me customers who brought more in 2022 than 2023

  • What are the top performing sales reps this year?

  • What regions are ahead of budget this quarter?

  • Who sold the most products in UK last month?

  • Cities with the highest sales between last Black Friday and the end of 2023. Use reporting value.

  • Sales in [region] this year.

  • Which branch had the most sales in August?

  • top selling product for the supplier Acme by quantity last week

  • Plot sales for Engines onto a column chart by month for the last 5 months

Limitations of Phocas AI

  • Financial databases are not yet supported. For example, if you type Cutsomer, Phocas AI will know you mean Customer. However, if you misspell a customer name, Amce instead of Acme, Phocas AI probably won't recognize it.

  • You don't need to use perfect grammar - capital letters and question marks are not required.

Limitations of Phocas AI

Phocas AI is an extension of Phocas Analytics, a feature-rich tool with many capabilities and options. If you can’t do something in Analytics, Phocas AI can’t do it. Phocas AI supports many of the Analytics features now, with more coming soon.

Phocas AI is in Beta

We’re working hard on testing and improving Phocas AI. This means that sometimes we might make mistakes and comically do the wrong thing. Your feedback is important in helping us to improve.

Is my data safe?

Absolutely. We store your confidential data securely and handle it with great care. See our Security and technology page for more information.

Info

This feature is only available for Phocas Cloud customers.

On this page

Table of Contents
minLevel1
maxLevel2
outlinefalse
typelist
printablefalse