rileyt

ai >>> sales people or hubspot

yes and yes. in the meantime, there's a list of use cases to start from here: https://docs.charlielabs.ai/daemons/choosing-daemons

DAEMONS.md is meant to be an open spec, like skills.

there's details on how other platforms can support it here: https://ai-daemons.com/spec/#provider-guide

here are a few more resources:

- example daemon files: https://github.com/charlie-labs/daemons

- reference docs: https://docs.charlielabs.ai/daemons

happy to answer questions. all feedback appreciated.

simonw is right, daemons are closer to routines.

compared to routines:

- daemons are specified by a DAEMON.md file in the repo (like skills). it's version-controlled and team-owned, not hidden in a dashboard or linked to a single developers account.

- daemons have a specialized event pipeline that joins similar webhooks events into a single daemon activation and can inject late arriving events into a daemon that's already running (this is key to avoid duplicate work and noisy actions).

- the watch conditions are a more powerful activation method because they use semantic matching and can be mixed with cron schedules.

- daemons have access to the logs from their past runs (and soon proper memory) so they can learn from their own mistakes.

hadn't seen this before, but it looks like the daemon schedules and watch conditions could be helpful for activating openprose contracts.

it's similar to triggers, but with a routing layer that combines semantic triggers and memory. the magic is defining them as files in the repo (like skills) and not worrying about the execution.

the working spec is files like `.agents/daemons/<name>/DAEMON.md` and they have access to skills and rules in the repo so you don't need to duplicate them.

you could even have a daemon that just says to run an existing skill.

seems like and appropriate way to share.

It was less than $2 to embed all 100+ episodes with the new OpenAI embeddings and was as easy as just making a bunch of API calls. Pretty hard to beat that experience.

It's not fine tuned. You literally just add something like "if the answer to the question isn't in the context, say 'I don't know'" It's wild.

Thanks a lot. It's nice when people appreciate the stuff I build for fun.

The UI is my own design system that I will open source at some point. The app is Remix with a Redis cache to keep things snappy.

Old version? Works on latest for me, but the CSS uses @layer which doesn't have great support with older browsers.

The embeddings cost less than $2 for all 100+ episodes. The cost for the answering calls to davinci are around $30 so far.

It uses Whisper for transcripts, which I believe are better than the YouTube generated ones.

My guess is that there are more relevant results from the semantic search than I'm including in the context (to reduce costs) and that exact snippet isn't being given to the answering model as context.

You're welcome :)

Ha, nice work getting ChatGPT to do it. I started down the same route, but wanted to get it done fast so I'm just grabbing the relevant HTML and then adding a few styles to clean up things like controls.

Ryan never asked me to clean anything. However, I find it hard to work in messy spaces, so my workspace rarely looks like a "real" one.

My list:

1. Salary range

2. Remote work policy

3. Tech stack

4. The product/team the role is for

Im building an easy way to convert your LinkedIn profile to a PDF and web resume: https://standardresume.co/linkedin-resume-builder

Making a resume sucks, but it doesn't have to. With Standard Resume you can import your LinkedIn in one click, pick from 12 templates, and share it as a PDF, or web resume (great for casual applications and referrals).

It's a lightweight tech stack that I maintain myself. It's Firebase+React+Next, combined with a custom written PDF layout engine.

Web example: https://rsm.io/sidney-template

PDF example: https://assets.standardresume.co/image/upload/v1607879981/re...

If anyone who lost their job at Dropbox (or anywhere else) is reading this and needs help making a resume, email me and I'll give you a free month of https://standardresume.co.

riley@standardresume.co

That all makes sense, but people should be aware that what you are saying isn't backed by your terms, so they have to trust you.

Beware of the terms of service before sharing any information with this service:

"You hereby grant to Leet Resumes a non-exclusive, perpetual, irrevocable, royalty-free, fully paid-up, worldwide license (including the right to sublicense through multiple tiers) to use, reproduce, process, adapt, publicly perform, publicly display, modify, prepare compilations and derivative works of, publish, transmit and distribute your User Content, or any portion thereof, and to publish, transmit, distribute and sell compilations and derivative works of your User Content, in any form, medium or distribution method now known or hereafter existing, known or developed, without compensation to you."

Check out https://standardresume.co. It has web resumes/profiles that allow you to set noindex. Disclaimer: I'm one of the founders and it isn't completely free, although it sounds like you might appreciate that :).

Most of these templates are poor choices for a developer. This book has an excellent section on what you should look for in a developer resume template: https://thetechresume.com/

Sure, automatic ranking is also "possible". The point is that it isn't being used in practice.

Those questions aren't related to what is being discussed: ATSs filtering people based on the contents of their resume.

It's crazy how widely spread this misunderstanding is.

You can normally find the ATS for a job application by taking a quick peak at the source. Most companies are using a handful of ATSs and if you check their offerings, they don't include automated rejections.

This is a fantastic resource for developers looking for work. I run a company that helps people make resumes and even I learned a few things!

That's a fair analysis. We are working on better sample resume content, to match the quality of the template designs. That copy was from our very first sample resume, when we created the app as a side project, five years ago.

What resources have you been using to help you write your resume?

The best move is to get referrals. A referral almost always allows you to bypass the nonsensical "AI/ML tool", as well as many clueless recruiters.