The company brain AI runs on. Your team's knowledge, skills, and workflows in one place, working across Claude, ChatGPT, Codex, and Cursor.
San Francisco, CA
Joined May 2024
- Tweets146
- Following287
- Followers1.4K
- Likes1.1K
HQ retweeted
Ok, these achievement badges from @hqforwork are pretty damn cool.
Nice work, @jacob_posel, @coreyepstein and the HQ crew. 🤝
HQ retweeted
I ran a $3M/year agency and sold it.
Here’s the client onboarding system I’d build today with Claude + @HQforwork.
Take a paid ads agency.
The goal: turn a signed client into an audited account and a launch plan your strategist can review before kickoff.
1. Put the agency playbook in HQ.
Your onboarding checklist.
Your audit criteria.
Your scope rules.
Examples of great briefs and delivery plans.
HQ gives the team shared context and reusable skills. Claude works from that context.
2. Build a reusable onboarding skill.
Give it a defined sequence:
Review the scope → identify missing inputs → audit the account → prepare the delivery plan.
Specify the files each step should produce, the evidence required, and where a human needs to approve.
Save it in HQ so the team can reuse it.
3. Run it against the new client’s documents.
Supply the signed contract, proposal, and sales call transcript.
Claude compares them against your agency’s rules.
Three brands discussed on the call. One covered in the contract.
That becomes a question for the account lead before anyone starts delivery.
The output is a client brief with sources and unresolved decisions.
4. Build the intake from those gaps.
Have Claude pre-fill what the client has already answered.
Then draft a request for the missing assets, account access, and approval contacts.
Keep a client status file showing what’s received, missing, and approved.
5. Audit the account against the client’s goals.
Provide campaign exports, CRM outcomes, and landing page content through approved connections or files.
Have Claude calculate performance and investigate the gaps.
The client wants enterprise customers, but the campaigns reward every form submission.
Cheap leads look great until you connect them to closed sales.
Where the data doesn’t support a conclusion, the audit should say so.
6. Turn the findings into the kickoff package.
Claude prepares the proposed tests, creative briefs, tracking fixes, and task dependencies.
Each recommendation includes its evidence.
Your strategist reviews the package before anything becomes a client commitment.
7. Save what the team learns.
When the strategist catches a missing check, update the shared onboarding skill.
The next client starts with a better process.
That’s the system I’d build: shared agency knowledge, a repeatable workflow, and concrete work ready for review.
I’m partnering with HQ. If you run an agency or digital service business and want to explore implementing AI, join the webinar.
Sign up here: dub.sh/aib-w1-x
HQ retweeted
My AI stack right now.
LHG-OS is our homemade ops layer. Tasks, CRM, portal, request programs. Humans and agents hit the same surface. Anything you can do in the app, you can do through the CLI.
@HQForWork is the company brain. Knowledge in one place, kept up to date.
Daily driver: Claude Opus 5.5. GPT-6.1 Sol for computer use.
New this month: Instinct for anything personal and quick. And @bot . About a dozen bots covering email, internal marketing, finance, ops, and sales.
Feels weird but I have a sentimental attachment to Hepha my first openclaw, I replaced 95% of his tasks with @bot but I dont want to pull the plug lol
HQ retweeted
Show me sir.
I’ve been testing across:
- different models
- workflows
- taste profile MDs
- premade Figma template library
- prompt construction
- photography language
- composition templates
- email design references
- etc
It’s a long running PRD in @HQForWork project.
HQ retweeted
We do these training sessions for free
Please come join us: hqforwork.com/training
You need to be doing weekly, full company wide ai training.
In the past 3 weeks we have seen astra make 3d renders child play, grok bot one shot all admin tasks, fable 5.1 build complete reports with its own data research, and Gemini almost answer a question correctly
The pace of change is accelerating.
Don’t let your team be left behind.
As a leader, you need to be driving this.
HQ retweeted
LFG @jacob_posel
Today in the Inner Circle we're having on @jacob_posel.
Jacob is the co-founder and co-CEO of @HQForWork.
He's breaking down what he's building right now, how he's selling it, who's buying, and what's actually working w/ a live Q&A at the end.
Let's get it.
HQ retweeted
Pika didn't have a good redact tool and took too long
So i built one you can use for free (for chrome)
coreyepstein.github.io/shotg…
HQ retweeted
Please share this with your team if you are trying to get them to use Claude Code, Codex or HQ
I go over the core, basic principles of agentic tools
HQ retweeted
Can attest to this. We’ve been on hq for almost 2 weeks and it has completely transformed how I work and how context is shared across our team
HQ retweeted
HQ is growing too fast
We have service demand we cannot handle
If you're an AI consultancy, freelancer or service business, we want to work with you
We will train you, enable you and send you business
If you're interested, please apply here:
hqforwork.com/partners/apply
HQ retweeted
ISO:
HQ users+front-end peeps who want to help me make a killer Grok Build HQ Desktop App
HQ retweeted
long overdue appreciation post for @HQForWork
i've been using HQ since its inception, and it still amazes me every day. revamped my dev setup recently and it really drove that home.
i've been testing & living across five different AI apps lately - claude, codex, opencode, cursor, and a few CLI sessions in random terminals. multiple sessions, three remote dev machines, different companies, all from one laptop.
HQ makes all of this painless - context, knowledge, skills, secrets, integrations, and new learnings stay in sync across every machine, app, and teammate in the background, each company walled off on its own.
this sync would be enough, but it's way more than that. everything i or a teammate figures out compounds and gets shared across the whole team - humans and agents alike. the thing genuinely gets smarter the more any of us use it. and honestly, this is just scratching the surface.
most people still don't realize this is how work can feel now.
HQ retweeted
When you get setup with @HQForWork and realize what the hype was about @jacob_posel
HQ retweeted
This is great.
If you’d like to build this for your company, use @HQForWork
HQ retweeted
lets talk HQ...
Ok I've been on HQ for three days. Here are my honest thoughts:
- I won't bury the lead. Overall it's cracked. @jacob_posel tried to get me on it for a while but I was too busy. I thought I didn't need it because I was already using github/vercel/supabase and had a bunch of skills made plus obsidian wiki. I was wrong.
- They might not agree, but it clicked for me when I thought of it as hermes for claude code. It's a harness for claude/codex that makes it easier to work across teams, devices, and models
How? Here's a few features i've noticed and liked so far and some other thoughts:
- Files live locally; I work in a HQ folder now on each device that automatically pushes to cloud. It feels pretty realtime. This has helped work between devices and models easily.
I've been heavily using Codex this weekend since 5.6 came out but subbing some stuff out to Claude and it's helped me go between well. I've also been using remote mostly since I I've been on the run and it's been near seamless.
- The secrets management is worth the price of admission alone. I've wasted so much time in the pastsetting up API keys. It's a pain to do normally, and you don't want to do it incorrectly. Hq makes this essentially one click.
- I can't prove it but I have to imagine it saves tokens. The context layer feels really smart; so it finds things really quickly. Normally in a fresh claude session you can waste a lot of tokens getting it up to speed if you don't have a handover or are starting fresh. This feels quick. This is what I mean what I say it feels like Hermes; if you have used it or Openclaw you likely get it.
- I also have seen some self learning subagents be automatically called upon, which I love. Helps to make your work better without you having to always manually create new skills.
- I had previous /handover and /resume skills I used a lot, but HQ has /handoff skills which are similiar but functionally a bit different so I'm trying to figure out the place for each so I don't have to track both. Likely user error.
- I have had some new skills not auto sync to codex when creating in claude. Likely user error.
- I'm also a bit unclear on what needs to push to github when. I used to use it heavily for even non-code stuff just to push and pull between devices but hq can do a lot of that. Also unclear on how obsidian will fit into play here and if it's redundant but I'm going to keep going with it.
- Apparently there's a way to start new claude remote control sessions on local folders using it but I haven't tried yet. That's been my biggest frustration with claude remote control and one reason I've been using codes more. Hope this helps it.
- Jacob showed me that you can run other models from Claude desktop so I build a /bakeoff skill that subs the same task out to GPT 5.6 and Grok 4.5 and compares or lets me compare. I'll share this as a hq pack once I figure out how.
- It also auto-deployes to what looks like AWS hosting which is nice and saves time. Trying to get them to auto-create databases as well.
- Overall I really like it. Definitely a learning curve first few days, especially for non-technical users. And I've just been using it solo; so excited to start using it with others. I set up a few "companies" for some of my new projects and will use them to collaborate with others on.
Hope this helps! Not getting paid, just a nerd with this stuff and have a bunch of extra time on my hands now. (No job and at in laws for the weekend so have built in babysitters).
If you try it and hate it, it's @NotZainAgain 's fault.