dispencer

The smarter the model the better querybear gets. I'm happy with that.

I've been building QueryBear (https://querybear.com) to fix the database part of this: instead of giving an agent your raw connection string, you give it a read-only MCP URL that only exposes the tables you approve and logs every query. The agent can still query your DB, answer business questions, help debug — it just can't delete anything.

Companies need to rely on sandboxing tools built for agents like querybear (https://querybear.com). This kind of thing should never happen.

This wild, one of the pieces I was lacking for a very openclaw-esque future. Now I think I have all the mcp tools I need (github, linear, slack, gmail, querybear), all the skills I need, and now can run these on a loop.

Am I needed anymore?

This is massive. Arguably will be the start of the move to openclaw-style AI.

I bet anthropic wants to be there already but doesn't have the compute to support it yet.

I've been building this at https://querybear.com.

Engineers are adopting AI agents faster than any other group. They connect these coding agents to github, slack, linear, jira, datadog, sentry, everything. I saw the limiting factor being the database so sought to build a solution.

But obviously there's a lot that can go wrong giving a raw access point into the database. Querybear is the security layer to protect from anything bad happening.

Been using it for months and we have multiple startups using it and loving it. Have had no issues yet!

https://www.querybear.com - basically retool but make creating tools SUPPPPER easy

querybear.com - basically retool but make the learning curve waaaaay lower

Actively looking for a full time frontend/full stack SWE role.

|

About me:

- Building and growing a paid B2B SaaS tool around Notion - at $4000/year revenue (https://engine.so/)

- Building and growing a cross-platform app to 12,000+ users using React, Ionic, cross-platform (https://skiwise-app.com/).

- Working as a L4 Software Engineer at Target

|

Looking for: Full-time

Location: USA (Minneapolis, MN)

Remote: Yes

Willing to relocate: No

Technologies: Deep experience with TypeScript / JavaScriptReact, Next.js, React, Redux, TailwindCSS, Node.js, Serverless, GraphQL, AWS, Docker, Github Actions, Postgres, SQL

Resume/CV: Email me

Website: https://spencerpauly.com/tech

Contact: https://www.linkedin.com/in/spencerpauly/

|

I'd love to chat sometime, feel free to reach out if you have an opportunity.

One add-on to Notion I can recommend: Engine.so (https://engine.so) (full disclosure I run this).

But many of the drawbacks I've seen mentioned in this thread are solved by my addon tool. It adds full-text searching to Notion pages, discoverability, and the ability to use Notion docs externally as-well as internally.

I agree, it won't solve all problems for all teams but it's an option if you haven't heard of it.

As a developer, I love Notion. It's my favorite way to write documentation, help-guides and tutorials.

I'm building Engine.so because I want to make it easy to share these pages to your customers. Engine.so gives you a custom domain, full-text search and prebuilt widgets for feedback and questions!

Let me know what you think!