Like Kathy, i was curious, so i tried the free Greenlight Coverage and put in a script i wrote. It literally mirrored the words from my script in its "assessment": my narrotor character has a line, "Cultural clashes and the tensions of class paint a portrait of a town struggling to reconcile the old with the new."
It spits this out:
Plot Assessment and Enhancement
What's working well:
- The setting of 1890s small-town Wooster, Ohio provides an interesting historical backdrop of cultural clashes and tensions between old and new.
- The newsboy Nate character introduces some of these tensions and acts as a device to set events in motion.
- The conflict sparked by Italian Mike's attempted break-in and attack on George Massoni makes for a dramatic sequence. The escalating fight scene is intense.
- The various eyewitness accounts from different perspectives build mystery and intrigue around what exactly happened.
- The political motivations of the Mayor and police add an additional layer of complexity to the case.

It got so much wrong in this assessment and it's understanding of the script that i wouldn't pay to see what else it has to say. Of course my script could have just been really bad and it was just giving me back what i gave it: garbage.

Yep, I think at this point it basically regurgitates what's in your script in a complimentary way. Sometimes says you could add more.

Flatters you so you go back for more.  

Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)

Quoted from JackFromGreenlight Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)

Ahoy JackFromGreenlight - thanks for the clarification. -Andrea

Quoted from JackFromGreenlight Hey guys, thanks so much for the comments.  I am the founder of Greenlight Coverage and would love to clarify that - We do use some OpenAI functions, but our core model is actually proprietary, you will find OpenAI is much more generic than our output.   Happy to answer any other questions you guys have =)

So, how is it trained (for want of a better word) to be better and less generic?

Quoted from LC So, how is it trained (for want of a better word) to be better and less generic?

Yea, so we worked with many industry veterans when we trained and programed our system.  It is largely driven by their feedback and adapted to what a industry professional would want to see in a coverage report.

Quoted from ghost and_ghostie gal Ahoy JackFromGreenlight - thanks for the clarification. -Andrea

You are welcome =)

Quoted from LC I was quite busy automatically criticising this. I'm curious AJR what shocked you by way of accuracy or anything else?  And what impressed you?

Hi, Libby - as Kathy said, the "what's working" was pretty uncanny. Or was it easily discovered? Hard to tell. It does seem like it repeats the same adjectives. For example, I noticed 'intriguing' on this thread, and also in mine.

The characters are colorful, quirky, and compelling. Their dynamics and relationships are complex and intriguing.

- The dialogue is sharp, humorous, and reveals the distinct personalities.

- The time period details of the late 80s/early 90s are fun and nostalgic.

- The scavenger hunt plot device is a clever way to propel the characters into funny and surprising situations.

- The story explores meaningful themes about friendship, loss, life choices, and personal growth.

- The ending montage provides satisfying resolution for the main characters.

Question for Jack from Greenlight - I'm not so much interested in Greenlight's opinion on how to improve the script, as I've had attachments before and received a ton of notes and have rewritten it for certain people, etc. - as I am about how much industry cache a good score has.

You have a quote from Scott Mednick who is a pretty big-time producer. Does that mean if I get a good score, it's a marketing tool with which to approach someone like Scott?

Thanks,

AJR

Hi all. Since AI seems to be the flavor of the week, thought I’d post my own findings to maybe quell or stoke anyone’s interest should they be thinking of using an AI service for script feedback.

I recently used the Greenlight AI Feedback service, and to date… it is the only feedback service I’ve ever paid for regarding a screenplay. Human or AI. Considering the script is about 7 years old and I’ve never had feedback on the script in its entirety, I thought what the heck, let’s see what AI does with 130pgs of surreal dreamscape.

Anyway, the end result for what I paid is more than satisfactory for what I was looking for. Alot of groovy feedback for the price, and it (most importantly) showed me where the script is and is not working, err… optimally.

As well, it allowed 3 additional questions after feedback regarding areas of the script, areas that I was really curious to have detailed with another’s opinion to see if it would give me additional ideas for those scenes, or information that would allow me to build on or reconstruct similar scenes elsewhere in the script.

It even spit out a succinct logline that pretty much resonates with the script.

Original logline (that it never prompted for):

“Inspired by the surreal works of Lewis Carroll and L. Frank Baum: A small town girl who dreams of traveling to distant lands, suddenly finds herself on an epic quest to release her lost love from the prison of an underworld garden matrix.”

Greenlight AI Logline:

“After a young woman enters a magical realm to find her lost love, she must defeat the evil overlord who has imprisoned him and restore balance to the mystical gardens.”

So, yeah, anyway that feedback is here if anyone is curious what Greenlight AI Feedback looks like, as well as the original script if anyone’s curious as to what the AI is actually giving feedback on…

Feedback: https://www.dropbox.com/scl/fi.....dl5ja26vwcj&dl=0

Script ‘The Arpeggio Garden’: https://www.dropbox.com/scl/fi.....909wt35e0o2&dl=0

Hopefully this helps, best of luck…

Quoted from ajr Hi, Libby - as Kathy said, the "what's working" was pretty uncanny. Or was it easily discovered? Hard to tell. It does seem like it repeats the same adjectives. For example, I noticed 'intriguing' on this thread, and also in mine. The characters are colorful, quirky, and compelling. Their dynamics and relationships are complex and intriguing. - The dialogue is sharp, humorous, and reveals the distinct personalities. - The time period details of the late 80s/early 90s are fun and nostalgic. - The scavenger hunt plot device is a clever way to propel the characters into funny and surprising situations. - The story explores meaningful themes about friendship, loss, life choices, and personal growth. - The ending montage provides satisfying resolution for the main characters.

Thanks, AJR!
All of that just seems really generic to me.

Quoted from ajr Question for Jack from Greenlight - I'm not so much interested in Greenlight's opinion on how to improve the script, as I've had attachments before and received a ton of notes and have rewritten it for certain people, etc. - as I am about how much industry cache a good score has. You have a quote from Scott Mednick who is a pretty big-time producer. Does that mean if I get a good score, it's a marketing tool with which to approach someone like Scott? Thanks,

I'm interested in the answer to this question too.

I'm curious to know if this is going to become the way of the future e.g. getting a minimum score from AI before you can progress with certain things.

I still think the test of this would be to have AI access a really badly written script.

It looks like AI is programmed to spit back 5-7 answers about what's working, regardless.

I suppose the less effusive the comments, and the less complimentary the adjectives, the more AI thinks it's a bad script...?

AJR

Quoted from ajr It looks like AI is programmed to spit back 5-7 answers about what's working, regardless. I suppose the less effusive the comments, and the less complimentary the adjectives, the more AI thinks it's a bad script...? AJR

You mean if you can't say anything nice don't say anything at all?  

Just looked at Rick's (Gum) Coverage and that is way more impressive and detailed. Out of curiosity what did that cost, Rick?

Quoted from LC Just looked at Rick's (Gum) Coverage and that is way more impressive and detailed. Out of curiosity what did that cost, Rick?

Hey, Libby,

Yes, I agree… it’s quite detailed, and came with some bonus info that I didn’t even consider, like casting (personality types, etc) that could actually help someone flesh out a script if you were to base your scripts protagonist or antagonist on a certain actor’s screen personae. Then there’s the Comparative Film Analysis which could help to further drill down the plot or thesis-antithesis-synthesis of your own 3 act screenplay in some shape or form I would imagine.

I paid $45 (probably $45 USD online which equates to about $60 CAD on my end) for 1-time feedback on 1 script, and it was ready in about 2 hours for the full feedback, then allowed 3 additional questions that it answered in real time as I asked them.

I honestly don’t think I would have gotten that type of detailed feedback for less than a few hundred bucks from an online service where an actual person read it, and I certainly wouldn’t get that via quid pro quo… so, yeah, it was definitely worth it in this particular instance.

Hope this helps  

Very reasonable price. Just remember it ain't human.

I did love all the suggested casting it did.
That was cool.

Quoted from LC Very reasonable price. Just remember it ain't human.

True, and for what the feedback is worth I would only use it for features, not short scripts. I do have a couple other features that I might throw at it, just to see how the feedback would compare from one to the other.

Heck, even if I shell out another $120 CAD for feedback on a couple more scripts, that’s still less than I usually spend on a week’s supply of sugar, grease, nicotine, alcohol, and caffeine: my five basic food groups, lol.

Thanks for the input!