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. 11 min readSprint Reports Nobody Has to WriteLearn how to automate technical sprint reports and documentation using AI agents and local-first developer tools without manual writing.
  2. 10 min readAssigning Agents by Their Strengths: A Strategy for Multi-Agent WorkflowsLearn how to optimize developer workflows by assigning agents by their strengths using specialized models for coding, terminal tasks, and documentation.
  3. 12 min readWhen the Agent Is Slower Than Just Doing ItExplore why the agent is slower than just doing it in AI coding, and how a better workspace architecture can fix the overhead of autonomous workflows.
  4. 10 min readMissing Error Handling in Generated CodeLearn how to identify and fix missing error handling in generated code to build more resilient applications using AI agents and local-first workflows.
  5. 11 min readAuthoring Agent Skills: Playbooks the Model FollowsLearn technical strategies for authoring agent skills and playbooks to improve LLM autonomy and reliability in development workflows.
  6. 10 min readSitemaps and hreflang Without TearsMaster Sitemaps and hreflang configuration for international SEO. Learn how to automate XML tag generation and avoid common indexing errors.
  7. 10 min readGiving an Agent a Shell: Safety Layers That MatterLearn how to secure AI coding agents with shell access. Explore isolation, human-in-the-loop patterns, and defensive layers for agent shell tool safety.
  8. 12 min readPersisting Agent Sessions Across RestartsLearn how to manage and persist agent sessions across restarts to maintain context and continuity in AI-driven development workflows.
  9. 11 min readThe Sweet Spot Length for an Agent SessionLearn how to find the sweet spot length for an agent session to optimize context windows, token costs, and developer productivity in AI workflows.
  10. 11 min readHanding Off Work Between Agent Sessions Without Losing ContextLearn technical strategies for handing off work between agent sessions to maintain state, context, and developer productivity across multiple AI interactions.
  11. 10 min readAn Agent Pass Over Titles, Metas and OG TagsLearn how to use an agent pass over titles, metas and OG tags to automate SEO hygiene and improve search visibility using AI tools.
  12. 10 min readSelf-Verification Loops: Agents That Check Their WorkLearn how self-verification loops improve AI coding agent reliability by implementing automated testing and multi-step validation cycles.
  13. 10 min readA Security Pass Over Your Own CodeLearn how to conduct a thorough security pass over your own code using automated agents, manual review patterns, and local-first development environments.
  14. 11 min readScanning Git History for Leaked SecretsLearn how to secure your workflow by scanning Git history for leaked secrets using industry standard tools and AI agents in the Deska canvas.
  15. 10 min readThe Second Opinion Pattern: One Agent Reviews AnotherLearn how the second opinion pattern improves LLM reliability by using one agent to review another agent's code in a side-by-side developer workspace.
  16. 10 min readSDK Ergonomics: An Agent Review Before v1Learn critical SDK ergonomics principles for AI agents to ensure your library is developer friendly before reaching v1 stability.
  17. 10 min readAgent Scope Creep: When the Fix Touches Forty FilesLearn how to detect and prevent agent scope creep in your development workflow by using better context management and hybrid agent strategies.
  18. 9 min readJSON-LD for a Blog: The Structured Data PassLearn how to implement JSON-LD for a Blog to improve SEO and discover how developer tools like Deska streamline technical content workflows.
  19. 9 min readSafe Defaults for Running Agents: A Defensive ChecklistLearn how to implement safe defaults for running agents in your development workflow. A technical checklist for sandbox security and autonomous execution.
  20. 10 min readThe Test Loop: Making Agents Verify Their Own WorkLearn how to implement a robust test loop to ensure AI coding agents produce reliable code and avoid hallucinations through automated verification.