HQ @HQForWork

Ok, these achievement badges from @HQForWork are pretty damn cool. Nice work, @jacob_posel, @coreyepstein and the HQ crew. 🤝

keyboard_arrow_left Previous keyboard_arrow_right Next

@jacob_posel @coreyganim You’ll have a lot of fun in me

@ImChaseMohseni The possibilities are endless

HQ Dev Day x.com/i/broadcasts/1…

Catch the live walkthrough today at 1 PM PT, right here on X and on YouTube. Want to stay up to date on the latest from HQ? We’ll be right back here next Friday for another Dev Day.

5/ Badges HQ keeps score now 😏 We’ve designed new badges to celebrate what you’ve actually done in HQ. Each one adds a holographic flip card to your account, and your avatar wears a ring for your top badge. Check your profile... we bet you’ve already earned a couple.

200+ changes merged. 8 desktop releases. 7 days. That’s just another week at HQ 😮‍💨 We decided it was too much to fit in a changelog, so we’re doing it live instead! Catch @jacob_posel and @coreyepstein on livestream at 1PM to walk through the 5 biggest things that shipped and take your questions. Here’s what’s coming:

@kes11av nice

HQ is the shared AI context layer for your Humans, Agents, Dots, Bots and everything in between. Over 1000 business run on HQ, including our own. The feedback has been phenomenal.

HQ is the shared AI context layer for your Humans, Agents, Dots, Bots and everything in between. Over 1000 business run on HQ, including our own. The feedback has been phenomenal. Sign up now: hqforwork.com

/super-conductor is live! Turn one Claude Code session into the supervisor for every other session you have open, plus your team's messages. The best way to manage multiple agents. → Every open session reports to one board → It spots collisions before they happen and puts merges in order → It answers routine questions from your team → Merges, deploys and anything risky wait for your go → It keeps running until you tell it to stop x.com/coreyepstein/s…

HQ Core v16 is live. Conduct on by default: every task goes to a background worker on Claude, Codex, or Grok. Your session stays fast and free for the next question. Faster tool calls: hooks no longer boot Node on every call. About 40% less CPU per tool call. Policy lifecycle and aging: the right rule shows up next to the action it governs, and stale rules retire themselves. Smarter rules, cleaner memory. Better integration awareness: HQ knows which of your connected apps it can use and routes through them first. Multi-company session bindings: work across several companies in one session with each company’s context and credentials kept separate. Built for agencies and service businesses. New skills: /handoff-all saves every open session in one step /resume-all brings them all back Full notes: github.com/indigoai-us/hq…

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 Bots are live! Always on, cloud assistants that connect to your HQ Brain, Secrets and Integrations. Talk to them in Slack or the HQ Desktop App. Bring your own keys or subscriptions! We don't charge for tokens 😁

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.

Antoine Lescun @AntoineLescun

2 weeks ago

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

0 0 0 199 0