James Chambers

It took us almost exactly 2 years to reach 10K MRR. I'm not saying that's particularly good, but I do think it's representative of the grit required to get something off the ground. Success is so often willing to be bored for longer than other people. If anything less than 1MM ARR in 12 months is a failure to you, you'll jump from project to project indefinitely and never make anything that has the opportunity to compound.

@helloitsolly I think we use the same referral partner currently

@jameschambers Sorry what do you mean?

We've generated over $220,000 from affiliates But we need a new affiliate software to take it to $1,000,000 Who should we try?

How to route work through three tiers of model, then bring it all together to deliver complex features. jameschambers.co.uk/orchestrated-b…

@aarondfrancis I run a similar process - currently using herdr to manage all this, perhaps time to give soloterm a run jameschambers.co.uk/orchestrated-b…

This is the main way I build anything big now. First, I have a nice long conversation with an agent and arrive at a plan I feel good about. That agent writes the plan to a Solo scratchpad (durable markdown doc, via MCP) Then I have that lead agent spawn new agents to review the scratchpad looking for gaps. They all write back to that same shared doc, via MCP. (That's what's happening in the images below) The lead agent sets a wakeup timer so that it doesn't busy-loop or bother the subagents. Solo will wake it up. When all the agents are done, the lead agent gets woken up to synthesize. Then we chat some more about what they found. After I feel super confident in the plan, the lead agent takes over in an "orchestration" role. I don't need worktrees, and I don't care how many agents get spawned. That's up to the lead agent to make sure everyone stays in their own lanes. The agents are smart enough to do this! Using Solo's MCP, it just interacts with the terminals and tells all the subagents what to do, based on our plan. It's reading and writing directly from/to the terminal panes. When we're all done, I run a round of reviews comparing what was built versus the planning doc to see if we covered it all.

@jonnyburch Nice! I built a similar tool for our marketing team

Yesterday alongside in under an hour alongside other work, I built a markdown email composer that it's impossible to mess up. Always on brand. It made me think about where designers should be looking to build: not just for ourselves but for teams.

I just solved a problem I've had for ~15 years in under an hour. We talk a lot about new tools now in design circles, mostly for ourselves. Tools for asset generation, copywriting, component management, creative coding (shaders and wotnot).

He did what now?

@Shpigford 5.5 / fast / high

what's the current consensus on thinking level for gpt 5.5? i'm already in /fast mode so speed isn't really a consideration nor is cost.

PB incoming...

Site idea

Little icon and drawer animation for the new notifications sidebar Boords

Colour picker component. I initially had the "sweep" animation on exit, too, but it felt a bit busy - simple scale and fade on the way out instead. Also I think the active states when selecting an item really lifted this.

@emilkowalski 🙏Appreciate the feedback, thanks for the course, so valueable

@jameschambers Good stuff, wouldn’t mind if it was slightly quicker.

Comment box interaction prototyping for Boords. A little bit of motion makes a huge difference. Highly recommend @emilkowalski's course if you're looking to level up your UI animation skills.

@helloitsolly Interested

I’m thinking of starting a SaaS mastermind ✨ Other SaaS founders ✨ Over $40,000 MRR ✨ Bootstrapped or seed only ✨ High intent / dialed in Any #buildinpublic people interested?

@howells @figma @claudeai Oh bravo

I made @figma, but everything is text. Create a quick wireframe, export as markdown, and chuck it into @claudeai. Try it out at wiretext.app

I've spent SO much time setting up and then abandoning productivity systems over the years. There is more to the current wave of AI capabilities, but I think we must acknowledge the appeal of "setting things up" is a big part of it.

"now let's try px-6 py-4"

All these openclaw wrappers are still so focused on the technology. There are literally billions of people who want what openclaw offers, but have no idea about the technology (and will never need to). There are almost limitless possibilities to position it for different audiences/use cases. Huge blue ocean.

@Austen Discord channels is the closest I've seen

Who has figured out the ideal UX to work with OpenClaw agents on dozens of things simultaneously without having them trip over themselves? I don't care for Kanban style. I imagine a giant multi-column layout where each column is an ongoing thread with its own context

@heroku We've been Enterprise customers for 10 years. This is the final push to migrate to Railway.

Heroku is transitioning to a sustaining engineering model focused on stability, security, reliability, and support. Heroku remains an actively supported, production-ready platform, with an emphasis on maintaining quality and operational excellence rather than introducing new features. We know changes like this can raise questions, and we want to be clear about what this means for customers. There is no change for customers using Heroku today. Customers who pay via credit card in the Heroku dashboard—both existing and new—can continue to use Heroku with no changes to pricing, billing, service, or day-to-day usage. Core platform functionality, including applications, pipelines, teams, and add-ons, is unaffected, and customers can continue to rely on Heroku for their production, business-critical workloads. Enterprise Account contracts will no longer be offered to new customers. Existing Enterprise subscriptions and support contracts will continue to be fully honored and may renew as usual. Why this change We’re focusing our product and engineering investments on areas where we can deliver the greatest long-term customer value, including helping organizations build and deploy enterprise-grade AI in a secure and trusted way.