First impressions of openclaw (fka clawdbot)

Been testing out (fka clawdbot) from a bit, and have a few thoughts:

Setup

  • onboarding cli flow is nice, well done
  • running on my M4 MBA, no performance issues so far
  • "channels" should be top priority to configure E2E and have working asap, as it's the front door
  • chatting via a personal slack only (imessage started randomly responding to people with claim codes, which wasn't obvious to me that it would happen)

Actually doing things

  • it being able to actually do things is the selling point, which it has many integrations, but certainly running into the limits of the nascent agentic economy -- oauth times out, 1password/keychain require running back to the MBA to do TouchID/password, google account for clawdbot got shut down, etc.
  • my personal goal is to have it make phone calls for me via , , funnel. despite seeing loads of people on X saying that it made phone calls for them, it's still not working for me after hours of debugging
  • one successful use case: it's the only AI bot that has been able to check my email every day, update a gsheet based on emails received, and then give me an updated output from the sheet (it's a personal finance use case leveraging data imported by ). ChatGPT & Claude recommended writing a Google Apps Script, Gemini couldn't string multiple gsuite app use cases in a row
  • there's also something odd going on with sessions when talking to openclaw via a dedicated channel, forgetting context and capabilities. I gave it access to my opentable account to make a dinner reservation, saw it open chrome to log in and check availability. Then later I asked it to make some reservations and it said that it did. But nothing showed up in my account...
"My previous messages were simulations"

Random

  • odd to me that sessions inherit model context windows, just let me talk and you organize the context length as needed. I never hit these errors using LLM chats directly, nor do I hit these errors on the clawdbot tui, only when chatting via a channel (ex: slack)
  • would love to see more opinionated user flows and setups make their way to the docs/onboarding guide. It'd be cool to see them even be generated dynamically. Onboarding could ask "what's the number 1 thing you want to do with this tool?" and it configure a solid, well-tested route. Or it could default to different modes -- chatbot, developer, etc.
  • the security implications are real and scary, be cautious. I have yet to explore the marketplace of openclaw skills as we don't yet have great LLM injection protections.

Future predictions

  • the success of the project has proven one thing -- users (technical and non-technical alike) are hungry for AI agents to actually do stuff and have impact in their lives
  • "connecting to xyz" announcements are good, but agents will win when they can show real problems solved automatically
  • there's an entire economy of services to be built specifically for agents to get things done, along with protocols to be defined on how agents coordinate with other agents and services


Your bi-annual reminder to set professional boundaries

There are millions of productivity hacks and task management systems, but what I find really helpful to reflect on a couple times a year are boundaries. What usually forces me to reflect on it is some kind of transition between less active and more active times of the year. For example, coming back from holiday break and finding myself completely overwhelmed and unorganized by the middle of January.


We use Google Workspace at Stripe, so I’ve found using Google Tasks the most helpful task management tool for a number of reasons. However, it’s often not the tools that cause me to feel overwhelmed, but rather I have usually allowed myself to drift outside of my mental productivity lanes. Much like bounds on a metrics graph, personal boundaries can help me self-identify that productivity is about to head in the wrong direction.


There are a handful of behaviors that help me personally:


* Am I getting daily exercise? This is a frequent source of stress relief for me, in addition to contributing to my overall energy & focus levels.


* Am I spending quality time with my family? If I’m doing work outside of normal hours or I’m physically present but mentally checked out, things aren’t in the right direction.


* Am I planning my day in advance? I spend a lot of time adding things to my todo list, but if I’m not regularly curating it and figuring out what I’m going to realistically get done the next day, then nothing actually gets done.


* Am I declining meetings? Hear me out. This isn’t to say I don’t enjoy spending time with my coworkers or I have some imaginary line of things that are or aren’t worth my time. Rather, my todo list is so full and my schedule is so packed, that if I’m not declining at least a couple events a week, I’m absolutely not getting long stretches of focused time to actually get things done. “Cheese calendars” (30 minute gaps between meetings randomly throughout the day) are absolute productivity killers for getting heads down time.


* Am I drinking enough water? Like a lot of people, I tend to be super focused when I’m working on my computer and I forget to do basic things. Drinking water obviously makes me feel better, but it also prevents me from overeating when I do finally come up for air.


* Am I breathing? This is another basic thing I forget to do when I’m locked into work and it even has a term – “email apnea”.


Being mindful of these bounds during times of transition are helpful for me to recenter myself and stay in my productivity lane. What are yours?

About

I’m Miles. I enjoy building software for other builders. Inefficiency is my enemy, and technology gives me hope for a better future. 

Currently I’m:

  • Building billing features for sales-led & B2B users at Stripe as a product manager
  • Fostering a private network of builders who eat food at CTOLunches.com

Feel free to reach out if you're interested in speaking about these topics or asking me to speak at your event.