I built ContractAI because generating a contract is only one small part of actually dealing with contracts.

ContractAI brings the workflow into one place:

AI contract generation
AI risk analysis with severity levels and suggested fixes
AI negotiation with counter-proposals from your perspective
Rich contract editor
E-signatures with an audit trail
185+ contract templates
Bulk contract generation
Team collaboration
REST API
Stripe billing and template marketplace
5 AI providers: OpenAI, Anthropic, Gemini, Groq and xAI
8 languages

I also made the demo available without requiring an account, so you can see how it works before signing up.

Hey PH Community!

We ve all been there: A manager asks for "honest feedback," but everyone stays quiet because nobody wants to be the complainer or risk their neck. Traditional "anonymous" surveys usually feel like a trap or just get ignored.

Hello everyone, my name is Sirri, glad to be here

I'm one of the co-founders at FIND Services, an African talent platform that simplifies job searching and nurtures career growth, and currently building out our company's first MVP, which is an AI resume builder. Launch date will be announced soon. In the meantime, anticipate and join our waitlist here: https://tr.ee/jEsEwp9WZg

I ve built software for 14+ years. Somehow, we still make decisions with screenshots and spreadsheets.

Hi everyone!

Hello :)
We launched on here yesterday and didn't get very much traffic at all, we were 550+ in the list for most of the day.
I wanted to re-share the link in the hopes that some of you would see it, take a look and check out our product SimpleWebAPIs
https://www.producthunt.com/prod...

Hi Product Hunt community!

I m Malik Dixon, a U.S. Army veteran, security-focused technologist, and solo founder with more than 25 years of experience across software development, AWS, DevOps, DevSecOps, UX, and AI workflow design.

While building AI systems, I kept seeing teams choose RAG, MCP, agents, and other architectures because they were popular not because the added complexity was supported by evidence.

I built idemkit after cleaning up duplicate charges one too many times.

The version everyone writes checks whether a key has been seen and replays the stored response. Two requests a millisecond apart both find nothing and both charge the card. And if the worker dies between charging and recording it, the retry charges again. Neither reproduces locally.

idemkit does it properly: an atomic claim instead of check-then-act, a lease that expires on the storage server's clock, and a fencing token so a stalled worker can't overwrite a good result.

Hi Everyone!

@rudrendu_paul_ai and I are officially soft-launching a new OSS solution, agent-eval, today.

I keep a daily probe that asks the assistants the buying questions in my category and records every source behind every answer. Last week I pointed it at Google's two AI surfaces, the AI Overview box and the fuller AI Mode, and counted.

Thirteen answers. 168 citations. Every single answer used a different domain for each of its sources. Not one domain was cited twice, in any answer, the whole week. Thirteen of thirteen, no repeats.

That stopped me, because it is the opposite of how a normal search results page behaves. On the ten blue links, one strong site often takes three or four of the top spots. A page that ranks well ranks well repeatedly. Here, ranking well once seemed to use up the domain for that answer.

Why an AI answer looks like this
An assistant does not hand you a ranked list. It breaks your question into several smaller ones, runs those, and assembles an answer from the best source it found for each. Google's own patent on query variants (US11663201B2) describes dynamic control that "can often lead to a relatively large (e.g., more than 5, more than 10, or more than 15) quantity of variants."

Hello! I have a 12year old who plays multiple travel sports and we are traveling for them pretty much all the time. One of things that was driving me nuts was being on the interstate and having to find a good place to pull over and get food or gas.

We usually just ended up with random McDonalds or something. To help us out on our road trips I built Pit Stop. It tells you the next 10 upcoming exits and what food, gas, hotels and special attractions are at each exit so you don't have to guess. I also built in a search so if you have something specific you want ( for us it's usually chipotle) you can search for it and it will tell you all the upcoming exits that has a chipotle.
I figured we use it all the time so other families might find it useful to. It's on the app store if anyone is interested! Let me know if you have any issues or suggestions!