Search: mendral.com | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

We gave terabytes of CI logs to an LLM (mendral.com)

233 points

3 months ago

2.

The agent harness belongs outside the sandbox (mendral.com)

182 points

a month ago

3.

We decreased our LLM costs with Opus (mendral.com)

106 points

a month ago

4.

What CI looks like at a 100-person team (PostHog) (mendral.com)

56 points

3 months ago

5.

LLMs Are Good at SQL. We Gave Ours Terabytes of CI Logs (mendral.com)

19 points

4 months ago

6.

How we know if our agent is right (mendral.com)

5 points

a month ago

7.

Our Agent's Most Important Job Is Deciding Not to Think (mendral.com)

4 points

3 months ago

8.

What CI looks like at a 100-person team (mendral.com)

4 points

4 months ago

9.

Supply chain attacks don't wait for CVEs (mendral.com)

3 points

13 days ago

10.

Agent Harness: Inside vs. Outside the Sandbox (mendral.com)

3 points

2 months ago

11.

Agent Harness: Inside vs. Outside the Sandbox (mendral.com)

3 points

2 months ago

12.

Same LLM, Different Agent: What Changes When You Specialize for CI (mendral.com)

3 points

2 months ago

13.

What CI Looks Like at a 100-Person Team (mendral.com)

3 points

3 months ago

14.

We built an agent for CI despite using Claude Code for everything else (mendral.com)

2 points

14 days ago

15.

We built an agent specialized for CI (using the 3 Claude models) (mendral.com)

2 points

20 days ago

16.

How we know if our agent is right (mendral.com)

2 points

25 days ago

17.

Multi-player agents don't fit in the sandbox (mendral.com)

2 points

a month ago

18.

Same LLM, different agent: a CI debugger built on Claude (mendral.com)

2 points

2 months ago

19.

We upgraded our agent to Opus and our costs went down (mendral.com)

2 points

2 months ago

20.

We decreased our LLM costs by switching to Opus (mendral.com)

2 points

3 months ago

21.

We Built Our AI Agent (mendral.com)

2 points

3 months ago

22.

Anatomy of a Production AI Agent (mendral.com)

2 points

3 months ago

23.

We built our AI agent, for analyzing CI logs (mendral.com)

1 point

2 months ago

24.

Same LLM but different output: we built a CI specialist (mendral.com)

1 point

2 months ago

25.

We upgraded to a frontier model and our costs went down (mendral.com)

1 point

3 months ago