Viewing profile — luodaint

We launched Feedjolt last week, It's a Feedback tool like Canny without any price surprise.

Jujutsu is trending on the homepage, and the topic is using discipline when dealing with version control. Six months into working agentially on a daily basis, something changed for…

Agentic development transforms the scope of work. Once a session is committed to having one topic from the get-go — one move, one service, one abstraction — the diff generated from…

For organizations that make this an operational reality rather than a slogan, there is likely to be at least one individual for each product development cycle that has had recent c…

Data from six months of production from one SaaS codebase provides a more limited response. Maintainability doesn't depend on the level of AI usage. Maintainability depends on the …

Not those carefully designed constraints that I set up from the beginning, but short-term ones that I came up with after an agent failed in some way: "Validate JWT at the route lev…

[dead]

[dead]

Your extensions in VSCode have ambient access to your filesystem, your tokens, and your environment. The servers of tools like Claude Code or Cursor have that ambient access too. T…

In any case, once the agent session finishes, the constraint file for the next session is written by the same individual. In this case, if the individual didn't read every output l…

When it comes to the business logic of production use, this particular failure type is less obvious compared to benchmarking tasks. Benchmarking involves having the answer already …

It’s getting easier to run two agent sessions in parallel over the same codebase. Avoiding them from making inconsistent assumptions, not so much. My observations: parallel session…

Benchmarks measure turn-level capabilities: you feed a task into the system and then grade the result. Capability for production-level usage concerns session-level decision making:…

If you don't know what exactly the user needs, the AI feature is the pitch itself. "Powered by AI" is something to say when you do not know how to sell the outcome. It's also somet…

[flagged]

Metric that measures the quality beyond simple tokens count: correction loop frequency. When grep does not find a file of interest, the agent does not fail; it will continue workin…

"The problem is that there are several bottlenecks internally," which include the requirements, specs, and testing. Another one not mentioned in the article. Before you had faster …

Bearer tokens using mcp-remote are the pragmatic way forward out of the authentication mess. Spec-based implementations of OAuth 2.0/2.1, including dynamic client registration and …

The difference that affected my approach: CLAUDE.md includes three types of content, which function differently. Facts (directory organization, commands, references in docs), alway…

When an agent writes a component, the styles come along with the JSX. "flex items-center gap-4 bg-purple-600 rounded-lg" doesn’t require any mental context switch to a separate sty…

[dead]

[flagged]

[dead]

Those sessions which stayed together had something in common: singularity of concern. 1 session = 1 feature, 1 bug, 1 migration. As soon as you have a session covering several subs…