Lastline
As long-running coding agents autonoumously ship larger and larger pull requests, the bottleneck shifts from writing code to reviewing it.
Core trick
A GitHub webhook triggers Playwright to record user flows, stitch them into one video, and convert timestamped Telegram comments into GitHub issues.
Description
As long-running coding agents autonoumously ship larger and larger pull requests, the bottleneck shifts from writing code to reviewing it. These agents make product decisions across entire user flows, not just single screens. They decide how a modal behaves, how a page looks in light mode, and how users move through the product.
Today, reviewing that work is still painfully manual. A human has to open the preview, walk through the app step by step, compare what they see against what they expected, capture screenshots, and file bugs.
We built Lastline, an QA agent for AI-generated pull-requests.
When a pull request hits a repo, Lastline is triggered by a GitHub webhook. It creates a QA plan, runs the product with Playwright, records the important user flows, and stitches them into one review video.
That video is sent to the human reviewer on Telegram. The reviewer can leave simple timestamped feedback, and Lastline turns that into structured GitHub issues with screenshots, timestamps, and PR context.
README excerpt
# Lastline Lastline turns pull requests into review-ready evidence. Instead of asking stakeholders to pull code, run branches, or interpret diffs, Lastline generates a guided QA walkthrough of the actual product experience, packages it into a single review artifact, and routes that artifact into the team communication loop where feedback already happens. For engineering teams, that means faster feedback with less back-and-forth. For non-technical reviewers, it means they can evaluate a change by watching what changed, leaving timestamped comments in plain language, and seeing those comments turn into structured follow-up work. ## Why it matters Most teams have a gap between code review and product review. Engineers can inspect a diff, but founders, designers, operators, and QA partners often care about something else: - What changed in the experience? - Does the interface feel correct? - Did the workflow regress? - Is the copy, state, or visual polish right? That gap slows shipping because the people with the strongest product instincts are often the least likely to pull a branch and test it locally. Lastline closes that gap by converting implementation changes into an observable walkthrough: - it listens for PR activity - it generates a focused QA plan from the actual implementation changes - it runs those checks against the app - it produces a stitched review video - it delivers that artifact into Slack - it turns timestamped human feedback into structured issues