humanlayer
@humanlayer_dev
Followers
1K
Following
76
Media
3
Statuses
55
Building the post-IDE IDE @ https://t.co/70J65W4jSM AI THAT WORKS @ https://t.co/AEsDJ9NwM2
San Francisco, CA
Joined August 2024
👀
superthread of every resource I have published about advanced claude code usage, research-plan-implement, and advanced context engineering for coding agents 👇 (mostly chronological)
0
0
1
This example uses @humanlayer_dev which you should all check out -- great library for human in the loop workflows!
3 AM. Slack notifications exploding. Your AI agent just wiped the entire user uploads folder. You watch in horror as frantic messages pour in from customers who've lost years of files. What started as a simple "clean up duplicate files" request turned into a catastrophe because
0
1
5
🧑💻 @humanlayer_dev Best expressiveness and dev experience I’ve seen. You can annotate any tool for human approval. But it adds another layer to your agent stack. If you’re good with that, it’s absolutely worth it. https://t.co/Mi85D9c1PP
1
3
4
#100DaysOfLearning Day 7/100 12-Factor Agents: Patterns of reliable LLM applications — @dexhorthy , @humanlayer_dev
https://t.co/QK6Xbf7zJO now i have to actualy write some code also on @freeCodeCamp , lets codeup the legacy javascript course here #noAIuse
github.com
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
1
1
7
5 APIs you will love for AI integrations and automated workflows smoothly 1-: Bluesky Firehose API If you want to use social media posts to analyze public sentiment about a particular topic then Bluesky firehose api is best fits. It is already being used for hacking projects
0
2
6
4/ HumanLayer 🏅Most Practical LLM powered email classifier that dynamically updates detection rules based on human the loop notifications over Slack Human powered guardrails for AI @dexhorthy @humanlayer_dev
2
2
16
our team has been hustling super hard ever since the claude code sdk dropped - saw this tweet and couldn't help but show off some of the very dope work they've put in - early days but already looking very cool
I actually want to interact with my coding agent via email. Send a mail with instructions, get a thread with results and PR link back.
4
1
33
Claude Code SDK is a PERFECT example of 12-factor agents in action. They handed us the keys to the loop instead of having it be a black box owned by the `claude` CLI Now all the best hackers I know are building their own bash pipelines and custom loops, dropping in `claude -p`
2
3
16
If this tweet gets 1000 rts @pk_iv will grow a mustache for ai engineer worlds fair
2
4
14
Built an agent that logs into my twitter account with @browser_use + @humanlayer_dev so it can ask me for my password & a fresh 2FA code when needed. Bullish on systems that treat humans as peripherals for agents to accomplish things agents can't do alone (e.g. get a 2FA code)
1
1
6
since i am apparently back on twitter (more of an accident ofc), let's pick up the podcast ads last week i had the please to catch up with @dexhorthy my highlights: - some light swearing - some insights on mcp - lots of shit on how to build agents that actually do stuff
4
4
6
Also S/O to @humanlayer_dev -if you’re building human in the loop AI agents , definitely check them out!
0
2
1
1
2
6
everyone loves reasoning models...but did you know with a little prompt pipelining, you can get 4o-mini to perform in the same league as some beefy thinking models? come hang with me and @hellovai tomorrow to see it in action!
1
1
6
d) i'm in this picture and I like it
agentic ai is real. our inbox drafts replies, pings us in slack, learns from feedback, and only bugs us when needed. no busywork, just focused connection. diagram here: 👇
0
0
2
over 300 ai engineers came to our 3 hour workshops. They asked for another one. next 4 weeks, 1 hour every tuesday:🦄 ai that works First topic: large scale classification @dexhorthy @boundaryML
2
4
13
AI Agents with Parental Control using Eunomia + HumanLayer 👮♀️ 🚸 🚨 We're kicking off our authorization examples series with built-in parental control for any agent your children might interact with. LLM-powered products designed for learning, play, and interaction with
1
5
5
shipping AI agents to the enterprise? here's 3 challenges I'm seeing the most in working with AI startups 1. model data boundaries - many enterprises wont send data outside their environment to hosted models. That means you wanna support BYO models in AWS/Azure, or bundle an OSS
0
5
16
HumanLayer is an API that enables AI Agents to contact humans for help, feedback and approvals 👇👇👇
2
7
36