Skip to content

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.

  1. 12 min readClosing the Loop: Agents That Run the Test SuiteLearn how agents that run the test suite improve software reliability by providing immediate feedback loops and autonomous bug fixing in AI workflows.
  2. 10 min readRunbooks by Agent: Capture the 3am KnowledgeLearn how to use AI agents to automate runbook writing and maintenance during production incidents to preserve critical operational knowledge.
  3. 11 min readTelemetry for Agent Runs: Designing Observability for AI CodingLearn how to design telemetry for agent runs to debug complex AI interactions, monitor token usage, and ensure reliable autonomous coding workflows.
  4. 11 min readStoring Agent Run ArtifactsLearn technical strategies for storing agent run artifacts, managing ephemeral files, and using local-first workspaces for better agent operations.
  5. 10 min readThe Agent Rewrote Code That Already WorkedLearn why AI agents rewrite working code and how to prevent it using local-first tools like Deska with multi-agent visibility.
  6. 9 min readAsking an Agent to Review Your Own CodeLearn how to effectively improve code quality by asking an agent to review your own code within a local-first development environment.
  7. 11 min readOne Agent Reviewing Another's Work: Strategies for Automated Code QualityExplore how one agent reviewing another improves code reliability through multi-agent workflows, self-correction, and specialized validation panels.
  8. 11 min readRetry Strategies When the Model Returns GarbageLearn effective retry strategies when the model returns garbage, focusing on structured output, validation loops, and multi-agent debugging for LLM reliability.
  9. 11 min readSession Resume Across AgentsExplore how session resume across agents affects developer productivity and how local-first environments like Deska manage persistent context for AI workflows.
  10. 10 min readTurning a Vague Bug Report Into a ReproLearn how to go from a vague bug report into a repro using automated workflows and AI agents within your development environment.
  11. 11 min readFrom Bug Report to Repro Script With an AgentLearn how to automate bug reproduction using AI agents. Convert bug reports into reliable repro scripts with Deska, Claude Code, and local-first workflows.
  12. 10 min readRelease Notes From Commits, Minus the NoiseLearn how to generate release notes from commits for your next deployment. Automate clean, readable logs using conventional commits and developer tools.
  13. 10 min readRegex You Inherited, Explained by AgentLearn a comprehension recipe for regex you inherited explained by agent tools, using Deska to visualize and refactor complex legacy patterns safely.
  14. 11 min readRefactoring a 3000-Line File With an AI AgentLearn how to refactor a 3000-line file with an AI agent. Master decomposition strategies and multi-agent workflows for massive legacy codebases.
  15. 10 min readRedirect Maps for a Site Migration, Agent-CheckedLearn how to build and validate redirect maps for a site migration using AI agents to ensure SEO stability and link equity during technical transitions.
  16. 10 min readLetting an Agent Read the API Docs: Streamlining Integration WorkflowsLearn how letting an agent read the API docs can accelerate development by automating endpoint discovery and schema parsing within a unified workspace.
  17. 10 min readThe README Refresh: An Agent Pass With TasteLearn how to perform a README refresh using AI coding agents. Improve your documentation with technical taste and the right developer tools.
  18. 10 min readWhen Your Agent Reads Untrusted Content: Safe HandlingLearn best practices for agent reading untrusted content to prevent prompt injection and data exfiltration while using AI coding assistants.
  19. 11 min readWhat Happens When Your Agent Reads a Hostile RepoLearn the security risks and defensive patterns to adopt when your AI agent reads a hostile repo containing prompt injections or malicious code.
  20. 10 min readAdding Rate Limits Before You Need ThemLearn strategies for adding rate limits to your developer tools and AI agents to prevent API cost spikes and infrastructure exhaustion before they happen.