k
keynews.ai
keynews.ai
WorkThe story, in brief

Agentic Testing: Where Agents Fit in the E2E Testing Stack

Slack ran 200+ agentic E2E tests. Here's what actually works—and what doesn't replace deterministic testing.

Reporting by Slack Engineering 1 min brief
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

As AI agents move into production QA workflows, engineering leaders need practical guidance on where agents add value vs. where traditional testing remains essential. Slack's large-scale experiment provides rare empirical data on agent-driven testing at scale.

The key facts

11 to know

  1. 200+ agentic E2E workflows tested

  2. Used Playwright MCP, Playwright CLI, and agent-generated tests

  3. Tests run on non-production data in isolated workspaces

  4. Agentic testing positioned as exploratory layer, not replacement for deterministic tests

  5. Published by Slack Engineering (credible first-party data)

  6. Focus on practical integration into existing E2E testing stack

  7. 200+ agentic E2E test workflows executed

  8. Tested using Playwright MCP, Playwright CLI, agent-generated Playwright tests

  9. Non-production test environment

  10. Focus: exploratory layer vs. deterministic test replacement

  11. Slack engineering case study on agent integration in QA stack

Go to the source

Slack Engineeringslack.engineering

Publisher excerpt: Abstract Agent-driven end-to-end (E2E) tests add a new exploratory layer to testing, but should they replace traditional deterministic tests? We ran more than 200 agentic E2E workflows using the Playwright MCP, Playwright CLI, and agent-generated Playwright tests in test workspaces using…
Read original report
Back to today's editionMore work news

The wider picture

View all
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Work01

The Emerging M&A Map For AI Agent Security

As agents move from pilots to production with real system access, enterprise security models are breaking. The M&A map is forming around who controls agent permissions, monitoring, and governance — a new class of identity management problem that practitioners need to architect for now.

Crunchbase News
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work02

AI privacy budgets: Ask for the calculation, not the claim

Enterprise AI buyers are accepting privacy budget numbers without verification. This deep dive explains what questions to ask vendors about federated learning privacy claims, and why the gap between contractual promises and operational evidence is where real exposure lives.

CIO
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work03

Andrew Kelley Interview: Why He Built Zig, Banned AI Contributions, and Moved Zig off GitHub

Open-source governance is shifting in response to AI-generated contributions. Zig's formal ban and migration off GitHub signals broader industry concern about code quality, maintainer burden, and the cultural impact of automated submissions — a flashpoint for how AI changes the work of software development.

InfoQ AI/ML