Software Engineering 2026

Automate everything you do

If you do something more than twice, an agent should do it. Automation only pays off when it has an owner and fails loudly. A silently broken release-notes generator is worse than a human writing them.

Pick targets by frequency times pain, not by what is fun to automate:

ArtifactHow agents handle itReview needed
CodeClaude Code, Cursor, CopilotAlways
DocumentationGenerated from code, types, and testsLight, spot-check
DiagramsMermaid, PlantUML, D2 from the actual codeCheck against reality
API specsOpenAPI from code, or code from OpenAPIFull, other teams consume it
Database migrationsScripts from schema changesFull, irreversible
Commit messages, PR descriptions/commit, /pr skillsLight
Release notesFrom commits and merged PRsLight, customers read them
RunbooksFrom incident history and infra codeFull, used under pressure
Test dataSynthetic data with Faker plus AICheck for real PII
Code reviewsClaude GitHub app on every PRHumans still own approval
RefactoringAgent-proposed, human-approvedFull
Translations, alt text, ARIAGenerated per changeSpot-check
Slides, meeting notes, email draftsClaude, NotebookLM, GammaYour name is on it

The shift in practice:

Before: "I need to write documentation for this API"
After:  "Generate the OpenAPI spec from src/routes/, then markdown docs from the spec"

Before: "I need an architecture diagram"
After:  "Read the infrastructure code and generate a Mermaid diagram of it"

Before: "I need slides for the team meeting"
After:  "Summarize this week's merged PRs into a 5-slide update"

Example prompts:

Documentation:
"Document every endpoint in src/routes/: request and response examples, error codes,
auth requirements. Output markdown."

Release notes:
"Release notes for v2.4.0 from commits since v2.3.0. Sections: Features, Fixes,
Breaking Changes."

Runbooks:
"Write the database failover runbook: commands, expected output, escalation contacts.
Optimize for scanning during an incident."

Tools for non-code artifacts:

CategoryTools
DiagramsMermaid, PlantUML, D2, Excalidraw
PresentationsGamma, Claude plus reveal.js
ImagesGemini, OpenAI image models, Midjourney, Flux
Video and audioRunway, HeyGen, ElevenLabs, Descript
DocsNotion AI, Mintlify
Synthetic dataFaker plus an LLM, Gretel, Mostly.ai

Staff rules for automation:

  • Every automation has an owner and a failure signal
  • Artifacts other teams consume (specs, migrations, release notes) get code-level review
  • Consolidate on a few vetted tools with known data-handling terms. Don't add a new SaaS for each task
  • Never automate a process nobody has run by hand. If you do, you scale its mistakes