Leonid Bugaev
@buger
Followers
6K
Following
6K
Media
101
Statuses
3K
Dad. Maker. Nomad. Building next gen QA tooling - https://t.co/o8O9vLRGOF Open-Source contributor - https://t.co/zV2pWqmV6J Head of Engineering at https://t.co/Or8yfwDeZt
Istanbul
Joined October 2007
RT @aryanXmahajan: HOLY SH*T!! This AI Agent just FIRED my entire sales team. while your sales reps burn 80% of their time on research mā¦.
0
289
0
RT @johnrushx: .@nikitabier & @elonmusk . My 10 cents on how to make X great:. 1. Limit tweets from the same profiles in my feed to one inā¦.
0
10
0
For 100% reliability, limit to 1 tool use per ai call, and make it run in agentic loop until it complete task, each time calling one tool, and in the end special complete_job tool. Plus own tool calling format, some simple xml syntax. Code editors like Cline/Roo do it like that.
Always remember, if tool calling isnāt working well for your task, try giving your model access to a code interpreter with functions pre-loaded. Most models are trained on a ton of Python, so often times, youāll find this will perform better than built-in tool calling!.
0
1
4
This. But single markdown file is too limiting for big projects. I found elegant solution, where you can turn docs of any size to mcp, and chat with them locally. It actually works very well with code chat too! Inside it elastic search like engine, working locally. Link below.
Tired: elaborate docs pages for your product/service/library with fancy color palettes, branding, animations, transitions, dark mode, ā¦. Wired: one single docs .md file and a ācopy to clipboardā button.
2
1
7
It probably also creates a whole new economy for competitors in those business, where you offer product mainly via APIs, and Agents, without even offering classical UI experience.
0
0
1
Current MCP trend is killing seat-based SaaS economy. Why pay of seat, if I can have amazing UX via MCP. We moving to the future of limiting public API access, value based pricing, and official "virtual employee" agents, from every major SaaS vendor.
1
1
5
The recent agent-to-agent protocol more than just a technological solution, it is attempt to "fix" the SaaS economy and API market, and moving to value based pricing. First of all, the recent agent-to-agent (A2A) protocol that Google introduced isnāt really some massive tech.
0
1
4
RT @buger: @levelsio @featurebase This. I have UX and PMs sending PRs and fixing bugs, all with tests and security checks. And its not someā¦.
0
1
0
RT @thedankoe: You can't focus because you aren't alone, physically and mentally, with the work you need to do. You may think you aren't diā¦.
0
91
0
I'm building OSS tooling to make AI agents natively understand the code, and it worked really well with Claude/Gemini 2.5, but I found that recent Quasar Model **very capable** and follow instructions very well as well! . More over I recently added support for native Github.
0
0
1
Here is the guide on how you can add super capable AI agent triaging your Github issues and reviewing PRs, for free. It leverage new Quasar Alpha model from OpenRouter, which is very capable! š.
1
1
2