The Deska blog
Blog
Product notes, release highlights and how we build Deska: the one infinite canvas workspace for your editor, terminal, browser, notes and AI agents.
- Race Conditions: Debugging the Unreproducible With AI HelpLearn technical strategies for debugging the unreproducible race condition using stress testing and AI agents to identify concurrency bugs in your code.
- The Last Python 2 Stragglers: Agent-Assisted PortsStrategies for final Python 2 to 3 stragglers using AI agents and local development environments to modernize legacy code safely.
- Release Notes Prepared While You SleepDiscover how to automate release notes prepared while you sleep using AI coding agents and local developer tools for a seamless documentation workflow.
- Agents That Write PR Descriptions Reviewers ReadLearn how to use AI agents that write PR descriptions to improve code reviews, documentation flow, and developer velocity without manual overhead.
- Drafting Postmortems With an Agent While Memory Is FreshLearn a technical recipe for drafting postmortems with an agent to capture incident context and timeline data before the cognitive load fades away.
- Agent, Editor, Preview: The Core TrioExplore how the agent, editor, preview trio defines modern development workflows and how a spatial layout improves focus and productivity.
- Designing a Plugin System With Agent SparringLearn how to optimize your plugin system design by using multiple AI agents for architectural sparring and validation in a local workspace.
- Plan-Then-Execute Agents: Implementation NotesDeep dive into Plan-Then-Execute Agents for software engineering, covering state management, feedback loops, and local implementation strategies.
- When the Agent Edits the Wrong File: Prevention and RecoveryLearn why AI coding agents edit the wrong file and how to prevent context drift using better workspace management and tools like Deska.
- Modernizing Legacy PHP With an Agent, SafelyLearn to manage legacy PHP modernization with AI agents while ensuring code safety and local privacy using professional developer tools.
- Permission UX Across Coding Agents: Balancing Speed and SecurityExplore how permission UX across coding agents affects developer workflows. Compare manual approval, automated policies, and transparent execution models.
- Permission Prompts Are the New Bottleneck: Unsticking Idle AgentsLearn how to manage permission prompts to prevent idle agents and improve your AI coding workflow with visibility and mobile approval strategies.
- Profiling With an Agent: From Flamegraph to FixLearn how to master profiling with an agent to identify performance bottlenecks and automate fixes using flamegraphs in a modern developer workspace.
- An Agent per Worktree: Setup GuideLearn how to optimize your developer workflow using an agent per worktree setup to manage multiple feature branches with specialized AI coding agents.
- One Agent per Service in a Local StackLearn how to manage complex microservices architectures by deploying one agent per service in a local stack to improve autonomy and debugging.
- PDF Generation Approaches, Prototyped by AgentExplore PDF generation approaches using AI agents. Compare headless browsers and libraries with prototypes built in Deska.
- The Supervision Rhythm: Glance, Trust, VerifyMaster the agent supervision rhythm to improve feedback loops when running multiple AI coding agents like Claude Code and OpenCode in your workspace.
- Is Pairing With an Agent Faster? A Measured AttemptIs pairing with an agent faster than solo development? We analyze how tools like Claude Code and OpenCode impact developer speed and context switching.
- Premature Abstraction by AgentLearn how to manage premature abstraction by agent workflows to maintain code quality while using tools like Deska for local development.
- Drowning in Agent Output: Managing High-Volume Developer ContextLearn how to manage drowning in agent output using workspace strategies, local-first tools, and infinite canvas layouts for AI-driven development.