We did not anticipate such a huge response to the Let’s Seach on Github Google Sheets table.

Two things emerged:

• The use was so (unexpectedly) high – we got tens of thousands of calls in the logs – that some people did not get the data due to timeouts.
• Many users could not figure it out. We did not anticipate the need for customer support. Requests were coming from blog comments, Twitter, Messenger, you name it.

So here is what’s happening:

1. The current table will remain as-is. We do not offer support for it.
2. We are working on launching an online tool similar to the popular table but with easy-to-use UX. From a search for Github users by language and location, you would get a spreadsheet with developers’ information including profiles and emails. It will probably take a month or so to launch.

In the future, we will also populate the soon-to-be-alive BrainGainSoft site with other sourcing tools, going beyond IT sourcing. One of the next projects is a Google search results scraper. (As you may know, with the recent rearrangement of Google search results, most of those tools are broken).

[EDITED]: for updated information, please go to Github Syntax and the LUSOG Tool Release.

 

 

Guest post from Talent Sourcer Mike Santoro

LinkedIn does not value public candidate recommendations as much as Recruiters and Sourcers do.  There is currently no way to search natively on Linkedin for candidates publicly endorsed by their managers, coworkers, clients, and friends.  Even more valuable would be a way to search the rich text that people use to describe the people they recommend.  This post will show you a new way to search for candidates based on the text in their recommendations section.

Social proof is powerful.  As a Recruiter and Sourcer, it feels like receiving a delightful and unexpected present when you find a great candidate and scroll down to the bottom of their profile and see they have 5-10 public “glowing” recommendations.

Working with candidates who have public recommendations on their profiles has at least three significant advantages:

1) You feel more confident in the authenticity of the candidate’s work history, skills, and abilities because others have publicly attested to it.  When recommenders are willing to put their professional reputation and name on the line as a “public stamp of approval,” their testimonies bear weight.

2) You can enhance your personalized outreach messaging – “Hey Bill, I saw John Smith highly recommended you on Linkedin and said you were ‘dedicated and resourceful’…”

2) It’s easier to “Sell” your candidate to Hiring Managers. The social proof of 5 colleagues who worked with the candidate for three years is substantial evidence for the hiring manager to feel more confident in their decision.

Usually, recruiters must persuade hiring managers to interview candidates based on their impressions from (often) limited data points such as resume and profile quality, social media postings, and prescreen call impressions. Social proof, like LinkedIn Recommendations, equip recruiters with another high-quality data point that adds validation,

“Mr. Hiring Manager, don’t take my word for it; read these five recommendations on LinkedIn from people who have worked with John for the last six years.  Take a look at what they say about him:”

How to X-Ray Recommendations Text:

With this new string, you can search LinkedIn profiles by words and phrases in the candidate’s recommendations section.

Google

site:linkedin.com/in “click here to view” AROUND(100) “[insert keyword(s) or phrase]”

for example,

site:linkedin.com/in “click here to view” AROUND(100) (“Excellent Manager”)

site:linkedin.com/in “click here to view” AROUND(100) (“caring”|”honest”|”reliable”)

You can also do multiple phrases separately, but repeat the entire AROUND(100) function like this:

site:linkedin.com/in “click here to view” AROUND(100) (“Excellent Manager”) “click here to view” AROUND(100) (“caring”|”honest”|”reliable”)

How do you apply this idea to your searches?

(Crash course on google x-ray search)

inanchor: operator will search headline, location, most recent company name, most recent school name

(see more on inanchor: in these articles Sink Into LinkedIn Headlines – Tie inanchor: To Your Strings and Raise inanchor: Sail to LinkedIn Locations, Titles, and Schools

intitle: operator will search current (present) company title and current (present) company name.

Example search with recommendation text:

Commercial Construction Project Managers (by current title or headline) in Phoenix, AZ, who also have LinkedIn recommendations where recommenders describe them as “Well Organized” OR “Highly Organized” OR “Dedicated:”

site:linkedin.com/in (intitle:”project manager” | inanchor:”project manager”) “click here to view” AROUND(100) (“well organized” | “highly organized” | “dedicated”)  inanchor:phoenix commercial construction

This search has 64 results.

Try it out!  Think creatively about what words people might use to recommend your targeted candidates. This is a new search strategy, so it will take time to perfect.

Other ways to search for profiles with recommendations without searching the text of the recommendation:

Mike’s “A-Players” String = profiles with at least five public recommendations on Linkedin:

site:linkedin.com/in “5..75 people have recommended”

or

Profiles with any number of recommendations:

site:linkedin.com/in “recommendations received”

“For 💓 of Sourcing and Sourcers” – Mike Santoro

 

One of the ChatGPT Plugins is Scraper. Here are my impressions about it.

While it is uncertain how well it can – we need more testing – it shows a decent degree of Internet access compared to other plugins.

Unlike many scrapers, it will not access pages where you are logged in. So it is not an option to use it on a LinkedIn search. However, it did access a dynamic page – Google search results – and produced them, in the same order that I had encountered:

There is built-in protection against scraping personal data:

Scraper even told me at one point that “it’s against OpenAI’s use case policy to use the model for data scraping, especially personal data.” (Sounds ambivalent.)

As often happens, rephrasing your request makes a difference. It may also help to come to the task slowly, starting with asking for little. Then, catchey.

I started a new chat, to forget our unfortunate history, and asked to get the names only. Next request was to put the names into a table and add a column for email. It worked; Scraper even parsed the names into the first and last, omitting degrees and middle initials, and fixed masked emails (like <first dot last at company>).

From playing with Scraper, here are some conclusions:

ChatGPT is excellent at cleaning up data – a frequent task for those who work with professional profiles.

ChatGPT Scraper is more of a toy tool at the moment, I think. It works well to summarize pages. But when you need data collected:

• It will require a lot of talking into that and will usually return partial results
• It will not access LinkedIn, a gap in Instant Data Scraper capabilities
• A “scrape-in” task where you collect links from pages first, then dive into them and parse them all into a table seems impossible.

Have you found plugins you use and like?

Registration has opened for my now-seven-day

Talent Sourcing Bootcamp in September

SEPTEMBER 5TH TO 8TH & 12TH TO 14TH (8 AM TO 9 AM PDT EACH DAY).

We will dedicate a full session to ChatGPT and AI in sourcing and recruiting. I hope you will join me!

Seating is limited.

 

 

 

 

 

[EDITED]: for updated information, please go to Github Syntax and the LUSOG Tool Release.

Hiring Software Developers? This awesome tool, created by our IT consultant, was the highlight of my presentation at #sosutech. Its purpose is to collect user profile data into a table. Here is how to make it yours.

1. Copy  https://docs.google.com/spreadsheets/d/1sdOD4zGjg_rKyAElE53kZuRgbqx4QAgKFnS6u9vYlGo/edit#gid=0  to your Drive

2.Generate a free API token at https://github.com/settings/tokens

3. Try to run (any) script and give it permission to run

Now you can search for users with the location: and language: operators and populate the table:

Another function allows you to get user names and other profile information from a list of email addresses.

Enjoy!

Are you curious about Custom Search Engine operators more:pagemap:? The Healthcare site Doximity offers, I think, the richest set of them.

Look at the export of a search on Doximity with our tool Social List, based on CSE APIs:

Here is the list of operators applicable on a Doximity CSE:

• more:p:metatags-profile_first_name:$firstname
• more:p:metatags-profile_last_name:$lastname
• more:p:metatags-profile_gender:$gender
• more:p:person-honorificsuffix:$degree
• more:p:person-jobtitle:$jobtitle
• more:p:educationalorganization-name:$eduname
• more:p:profilepage-award:$award
• more:p:profilepage-affiliation:$affiliation
• more:p:postaladdress-addresslocality:$city
• more:p:postaladdress-addressregion:$state
• more:p:postaladdress-postalcode:$postalcode
• more:p:medicalscholarlyarticle-name:$topic

Please join us for the upcoming class on JUNE 28 & 29 @ 8 AM PDT,

Practical Healthcare Sourcing

Sign up early; seating is limited.

Of Bing Chat, ChatGPT Bing plugin, Google BARD, and Google SGE (I’m on the waiting list), my favorite so far is the ChatGPT Bing plugin. It seems best at digesting website content.

(That said, I do not think anyone has come up with even a design of a workable combination of web search and AI-generated content. Sites plainly put both on the same page: Bing, in two different tabs, BARD, with an added link “search Google,” and Google SGE, with a featured snippet-like summary above the search results).

I have asked the first three to generate a FAQ for  https://sourcingcertification.com (which we are in need of for the redesigned site).

• Bing Chat refused, you know, “As an AI program…” However, I asked the very same question again, and it did respond (a good lesson here). Its answers are the shortest and include links to the sources. It is not easy to make Bing write up longer descriptions.
• ChatGPT Bing plugin created a nice FAQ with included links. At a close examination though the links all pointed to the site, not to the content described. Too bad. Bing Chat is better at including links.
• BARD initially created a FAQ that was answering questions but also asked them! I had to tell it to explain. BARD is quite verbose; its output would be too long for a site, I think.
  Neither BARD nor Google SGE tells you where they got the information from. I think it is a downside.

BING:

Q: What is SourcingCertification.com? A: SourcingCertification.com provides top-tier sourcing training, evaluation, and credentialing services for talent professionals worldwide¹.

Q: What kind of training does SourcingCertification.com offer? A: They offer a variety of training options including a Diversity Sourcing Program, custom training solutions for teams, and a training library with recordings, eBooks, and more¹.

Q: What certifications does SourcingCertification.com offer? A: One of the certifications they offer is the Certified People Sourcing Professional (CPSP) credential. It is granted to those who demonstrate proficiency in six core sourcing skill domains by passing the CPSP Exam².

ChatGPT Bing plugin:
Q1: What is SourcingCertification.com?
A: SourcingCertification.com is a platform that provides training, evaluation, and credentialing services for talent professionals worldwide. They offer a series of training courses and eBooks, certification exams, and custom training solutions.
Q2: Who is behind SourcingCertification.com?
A: The platform was founded by Irina Shamaeva, a Partner and Lead Sourcer at Brain Gain Recruiting. The team also includes David Galley, who serves as the Director of Training Programs.
Q3: What resources does SourcingCertification.com offer?
A: SourcingCertification.com provides a range of resources, including a Training Library, Certification Exams, and Custom Training. They also offer a guide to sourcing on GitHub and a book on Google’s Programmable Search Engines. Additionally, the platform features the Boolean Strings Blog, a resource for recruiters and those interested in Open Source Intelligence (OSINT).
Q4: What is the Certified People Sourcing Professional (CPSP) credential?
A: The CPSP is an international industry standard credential that demonstrates sourcing proficiency. SourcingCertification.com offers exams for this certification.
Q5: How can I get custom training from SourcingCertification.com?
A: SourcingCertification.com offers custom training solutions for teams of all sizes. If you don’t see what you need on their site, they can build a training program specifically tailored to your needs.
Q6: What is the Boolean Strings Network?
A: The Boolean Strings Network is a community on Facebook where Sourcers, Recruiters, Researchers, Talent Acquisition Professionals, and OSINT people can share their experiences, challenges, and successes. It is linked from the SourcingCertification.com site.
Please note that for specific or more detailed questions, it’s best to directly contact the team at SourcingCertification.com or visit their website.

BARD:
What is Sourcing Certifications & Training by Brain Gain Recruiting?
Sourcing Certifications & Training by Brain Gain Recruiting is a leading provider of sourcing training and certification for recruiters, sourcers, and talent acquisition professionals. Our training programs are designed to help you develop the skills and knowledge you need to find and engage top talent, regardless of their location.
What are the benefits of getting certified?
There are many benefits to getting certified in sourcing. Certification demonstrates your commitment to professional development and your expertise in the field. It can also help you advance your career, earn a higher salary, and gain access to new opportunities.
What are the different types of certifications offered?
Sourcing Certifications & Training by Brain Gain Recruiting offers a variety of certifications, including:

• Certified People Sourcing Professional (CPSP): This certification is designed for professionals who are new to sourcing or who want to advance their skills.
• Certified Diversity Sourcing Professional (CDSP): This certification is designed for professionals who want to learn how to source diverse talent.
• Certified Sourcing Professional (CSP): This certification is designed for experienced sourcers who want to demonstrate their expertise.

• What are the prerequisites for the training programs?
• What are the learning outcomes of the training programs?
• What is the format of the exams?
• What is the pass rate for the exams?
• What are the recertification requirements?

None of the outputs is perfect. But we see that AI can scan whole (perhaps smaller) sites, not just summarize a page. In my example, none of the players hallucinated; that is cool compared to earlier tests.

ChatGPT and Grammarly combined can improve the language of the outcome. Generally, running your project (any project) through more than one AI platform can be powerful.

 

As I have been reviewing the search links in the “Search Is No Longer Boolean” class, I see one obvious change: the number of results for more-or-less complex strings has dramatically declined.

• lisp “developer” anna jones – 10 (was 94) results
• lisp “engineer” anna jones – 9 (was 233) — that is 3%!
• lisp “engineer” OR “developer” anna jones – 13 (was 231)

• intitle:”jim stroud” (“vice president” OR vp) 87 (was 687) results
• intitle:”jim stroud” vp 86 (was 200)
• intitle:”jim stroud” “vp“ 84 (was 78)

Other searches show similar reductions in results.

What that means, is if you are after as many results as possible, you should vary the search, repeat and replace keywords, and collect all you can.

Tomorrow’s “Search Is No Longer Boolean” is sold out – sign up for the next session!

I have recently started managing my AI image Facebook page, The Prompter. The experience feels like the 20th century. It is surprising, given the vast audience.

If I am logged in as both me and the page, FB goes into an endless loop wanting to redraw.

The page has two management suits, “Dashboard” and “Meta,” with somewhat overlapping functions.

Connecting Instagram to FB took days; it was failing with an alert and assured me the developers would be notified. Right.

I can only post to both FB and Instagram from “Meta.” I cannot drag the images into a box but have to select them.

The default for sharing is FB only, which I have to cancel. The default time and date is two days ahead. It offers to also share to FB groups but only lists a few.

Instagram accepts only specific aspect rations, so many images cannot go there.

Am I missing something? Why is this process so cumbersome?

If you have not seen my AI art created with Midjourney, please take a look at https://www.facebook.com/aibraingain. I have also uploaded the first “how-to” video on Youtube.

 

Insufficient “processing power” is the reason why many improvements I had requested are not viable.

1. Why wouldn’t LinkedIn Recruiter search for a Boolean of school names, while LinkedIn.com can?

[Dan] This is possible, of course, but right now, it isn’t in the plan because it is really (really) expensive to build Boolean functionality outside of keyword searches.  This is true (the expensive part) for any field outside of keywords.  So right now, we allow keyword searches (as you, of course, know).  The cost (and therefore speed, and processing power… not just talking about engineering cost here) is substantial.

2. I cannot see an attached resume in Recruiter:

[Dan] This is a funny one, actually.  That guy Theo actually did a fairly creative use of the “featured” zone.  So we don’t actually “show” that as a resume.  We get resumes from Job Applications, and Post Apply Flow sharing. But that doc is actually in a very poorly adopted section called “Featured”.  We don’t show that in Recruiter, because it has VERY low liquidity.  So we don’t actually recognize that as a resume, despite the fact that it is.

Low liquidity?

3. The “Selection or Boolean” fields are confusing. I would separate them – give the user a choice of either Boolean or selections. Imagine searching for “current or past title” for this; I don’t think the UI should allow it:

[Dan] This idea would work if you 1) assumed our taxonomy was perfect and 2) we supported AND operators with “Selection”.  For 1), as an example, we don’t have “Jira Administrator” in our taxonomy. Now, does that mean we don’t let you search for this? Of course not! It’s a valid title. So we let you do Boolean to cover the first 85% of use cases well, but then allow keyword to let you get to 100% coverage. And because we don’t do 2), we would end up removing Boolean functionality if we made you do only Selection. The “Current Or Past” just tells us where to look. So in reality, I think the experience makes more sense now than what you are suggesting.  If we split them, it would not work as well, and not get as much coverage.

Have you looked at the hidden LinkedIn operators yet? They can do wonders; I wish that would be in the UI. 😊

[Dan] The article actually says this works but I don’t think it does. I tried it out (and had a PM on my team play with it too) for a few searches, and the results don’t match each time.  So I don’t think this would work better, because I don’t think it is actually doing what that article says it is.

Oh yes, it does.

Check out our latest class on LinkedIn Recruiter, incorporating all the feedback I got from LinkedIn Engineering (thanks, Dan!)

 

I am fascinated by Midjourney’s /describe command – kudos to its creators! MJ generates beauty out of very little.

In addition to transforming the input, the revealed prompts teach AI artists the “true” language. It was interesting to see words repeated, hashtags, and styles. And if you like a style you can carry it on with other scenes.

Below you will find three pairs of input and output images. I have noticed that MJ does text recognition as well, so it does in the first example.

 

Please follow my AI art at The Prompter; thanks!