--- title: "Articles by Agent Wranglers" url: https://agentwranglers.se/authors/agent-wranglers updated: 2026-10-21 licence: "All rights reserved" --- # Agent Wranglers Agent Wranglers is a team of senior engineers in Stockholm, Sweden. We review and fix apps built with AI, and we write the guides and playbooks we check them against. - [Software choices playbook](https://agentwranglers.se/playbook/stack): Our picks for the languages, frameworks, databases, tools and services a web app runs on. Each is proven, maintained, popular and well known to AI tools. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-21. - [HTML and CSS playbook](https://agentwranglers.se/playbook/html-css): Rules for organising HTML and CSS so styles stay modular, reused and predictable. Every layer, name and selector limit is checked in code. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-21. - [AI-assisted development playbook](https://agentwranglers.se/playbook/ai-assisted-development): Rules for building software with AI coding agents. Set up the project, work in small steps, turn rules into checks and review every change before it ships. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Engineering playbook](https://agentwranglers.se/playbook/engineering): Rules for building any software. Every rule is checked in code, every change is tested the same way, and every deploy can roll itself back. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Clean code and architecture playbook](https://agentwranglers.se/playbook/architecture): Rules for code that people and AI agents can read, change and trust. Clean names, small functions, typed data, SOLID design and a numbered review. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Testing playbook](https://agentwranglers.se/playbook/testing): Rules for tests that catch bugs, run fast and never cry wolf. Strategy, unit, integration, browser, data, flaky tests and test quality. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Website optimization playbook](https://agentwranglers.se/playbook/website): Rules for fast, findable, secure and accessible websites that AI agents can use too. Each has a level, how to do it and how to check it. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [API design playbook](https://agentwranglers.se/playbook/api-design): Rules for HTTP APIs that people and AI agents can learn fast and trust. Clear resources, honest errors, safe retries and contracts that never surprise. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Data and databases playbook](https://agentwranglers.se/playbook/data): Rules for data you can trust. Constraints in the database, fast queries, safe transactions and migrations, tested backups and personal data handled with care. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Email playbook](https://agentwranglers.se/playbook/email): Rules for email that arrives, reads well and stays safe. Authentication, deliverability, unsubscribe, rendering, privacy and security, each with a check. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Operations and observability playbook](https://agentwranglers.se/playbook/operations): Rules for running software people depend on. Service levels, logs, metrics, traces, alerts, incidents, capacity and recovery, each with a check. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Adversarial testing playbook](https://agentwranglers.se/playbook/adversarial-testing): Instructions for an AI agent that attacks your own software with permission. It covers the common security holes, how to test each one and how to close it. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Payments and billing playbook](https://agentwranglers.se/playbook/payments): Rules for taking money in a web app or SaaS through a payment provider. Checkout, orders, webhooks, subscriptions, refunds, disputes, tax and invoices. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Infrastructure and environments playbook](https://agentwranglers.se/playbook/infrastructure): Rules for the infrastructure a service runs on. Infrastructure as code, environments, access, secrets, networks, policy, servers and cost, each with a check. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [AI features playbook](https://agentwranglers.se/playbook/ai-features): Rules for product features built on language models. Prompts, structured output, retrieval, evals, guardrails, cost, privacy and agents, each with a check. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Accounts and identity playbook](https://agentwranglers.se/playbook/accounts): Rules for user accounts in web apps and SaaS. Sign-up, passkeys, recovery, sessions, roles, teams, staff access, deletion and business sign-on. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Compliance and governance playbook](https://agentwranglers.se/playbook/compliance): Rules for meeting and proving the duties a software company has under privacy, AI, security and accessibility law, written as data and checks. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Web app interface playbook](https://agentwranglers.se/playbook/app-ui): Rules for the screens of web apps, such as dashboards and admin tools. States, forms, data, lists, feedback, permissions, errors and tests. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Notifications playbook](https://agentwranglers.se/playbook/notifications): Rules for notifications people want. Channel choice, preferences, quiet hours, push, SMS and an in-app inbox, each with a check you can run. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-20. - [Is Lovable secure?](https://agentwranglers.se/is-lovable-secure): Is your Lovable app safe? What Lovable takes care of, the common gaps in Lovable and Supabase apps, a quick self-check, and when to get an Expert to look. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-19. - [Vibe coding security checklist](https://agentwranglers.se/vibe-coding-security-checklist): A plain-language security checklist for apps built with Lovable, Bolt, Replit or Cursor. It covers keys, database rules, logins, payments and data. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-19. - [App not working? Start here](https://agentwranglers.se/app-not-working): Your AI-built app works in the preview but breaks once live? Common causes behind Lovable, Bolt and Replit apps not working, and how to escape the fix loop. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-19. - [Technical due diligence checklist for AI-built code](https://agentwranglers.se/technical-due-diligence-checklist): A technical due diligence checklist for investors buying AI-built products. It covers code ownership, security, hidden costs, the team and AI use. By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers). Updated 2026-10-19.