←
Qodo1,865 posts
Qodo avatar

Qodo

@QodoAI

The AI code quality and governance platform for developers.

◷ Joined December 2022▧ 628 Photos and videos
Qodo avatar
Qodo@QodoAI·19m

Launching today for your software factory: auto-approve PRs under team-defined rules + review an agent’s related PRs as one work package.

You can now automate low-risk PR approvals under team rules + review an agent’s related work together in your software factory. New at @QodoAI: Auto Approval Workflows (beta) Agent Session Review (research preview) More intelligent, more deterministic, more governance.

1:48
Filip Hric avatar
⟳ Qodo retweeted
Filip Hric@filip_hric·19m

Teams building a software factory need to move fast and still control what they accept. For me, that means being explicit about which approvals they delegate and which changes need a person. The new Auto Approval Workflows released by @QodoAI let your team define those rules. PRs that qualify can be approved automatically after review, while work outside those rules stays with a person. If a new commit means a PR no longer qualifies, Qodo withdraws its approval.

You can now automate low-risk PR approvals under team rules + review an agent’s related work together in your software factory. New at @QodoAI: Auto Approval Workflows (beta) Agent Session Review (research preview) More intelligent, more deterministic, more governance.

1:48
Qodo avatar
Qodo@QodoAI·Nov 16

Cloud communications provider LoopUp faced code review delays across three time zones. CTO Chris Howard says Qodo now handles about 90% of the initial review, giving engineers more time for architecture and design.

Post attachment
Qodo avatar
Qodo@QodoAI·Nov 13

What should an AI code reviewer learn from your team's review history? Fine-tuning has shown value in turning comments into fixes. In the research we reviewed, evidence of better real-world bug detection is still limited.

Itamar Friedman avatar
⟳ Qodo retweeted
Itamar Friedman@itamar_mar·Nov 13

Eval driven development is real

Qodo@QodoAINov 13

An agent can meet most requirements and still leave the task unfinished. In Co-Design Bench's 273 difficult web-app tasks, the strongest model passed 69.9% of criteria per task but completed 26.4% of tasks. Qodo examines the implications for PR review.

Post attachment
Qodo avatar
Qodo@QodoAI·Nov 13

An agent can meet most requirements and still leave the task unfinished. In Co-Design Bench's 273 difficult web-app tasks, the strongest model passed 69.9% of criteria per task but completed 26.4% of tasks. Qodo examines the implications for PR review.

Post attachment
Filip Hric avatar
⟳ Qodo retweeted
Filip Hric@filip_hric·Nov 12

Hey everyone, here's the solution for Software Hackathon Day 8: Join us: hackathon.qodo.ai

1:09
Qodo avatar
Qodo@QodoAI·Nov 12

Headed to AWS re:Invent? Join Qodo, the AI code quality and governance platform, at House of Kube on Nov 30. VIP entry, our VIP section, a signature cocktail, and a swag bag. Request VIP access: qodo.ai/reinvent/#form #AWSreInvent

Post attachment
Qodo avatar
Qodo@QodoAI·Nov 12

A steady change failure rate can hide more failures as shipping volume grows. Momentic CEO Wei-Wei Wu argues for metrics tied to customers' experience on The Agentic Review podcast.

0:45