What changed in legal AI workflows
Daily automation tracks trusted OpenAI, Claude, GitHub, and legal-tech sources so tutorials stay current and useful for legal work.
Latest verified: May 12, 2026
Claude Code 2.1.139 updates agent, hook, and MCP controls
Claude Code 2.1.139 adds agent view, `/goal`, direct hook argument execution, PostToolUse continuation, MCP project-directory environment support, and subagent telemetry headers.
Sources checked
Affected pages
Recommended action
Before using Claude Code on client or privileged workflows, retest hooks, MCP configs, and goal-driven sessions in a sandbox with audit logging and human review.
Codex Auto-review and repair-loop guidance for legal repositories
OpenAI expanded Codex Auto-review documentation and published Codex cookbook examples for iterative repair and agent-improvement loops using traces and evals.
Sources checked
Affected pages
Recommended action
Treat Auto-review as an additional approval signal, not legal sign-off; keep sandbox boundaries, eval criteria, source checks, and human diff review explicit.
GitHub MCP and Agentic Workflows backfill for legal repository agents
GitHub's MCP Server gained Projects tooling, HTTP server mode, and permission-aware tool filtering, while Agentic Workflows entered technical preview for AI agents inside GitHub Actions.
Sources checked
Affected pages
Recommended action
For legal repository agents, require repository secrets, least-necessary workflow permissions, explicit MCP tool allowlists, and human merge review before production changes.
GitHub MCP secret scanning controls for legal repository agents
GitHub MCP Server secret scanning is generally available for repositories with GitHub Secret Protection, giving MCP-compatible agents and IDEs a pre-commit and pre-PR credential check.
Sources checked
Affected pages
Recommended action
Before agent-authored legal repository changes, keep push protection enabled, scan for secrets through approved MCP-compatible tooling, and require human review before merge.
MCP research workflows now require source-coverage checks
Research guidance now separates model knowledge from current source access and requires jurisdiction, date, treatment, and MCP tool-scope checks before legal reliance.
Sources checked
Affected pages
Recommended action
For current-law research, confirm the connected source set, jurisdiction/date coverage, treatment/status data, and tool allowlist before drafting conclusions.
OpenAI model, plan, and Responses API documentation refresh
OpenAI docs now emphasize current GPT-5.5/GPT-5.4-era model guidance, updated ChatGPT plan naming, and Responses API plus built-in tools as the starting point for new API workflows.
Sources checked
Affected pages
Recommended action
For legal workflows, avoid stale GPT-4 or fixed-price plan advice; verify the current model, plan, tool, retention, and review controls before piloting client-facing automation.
Claude Code 2.1.133 automation reliability changes
Claude Code added worktree base controls, effort-aware hooks, managed sandbox settings, and fixes for MCP OAuth, subagent skill discovery, and concurrent sessions.
Sources checked
Affected pages
Recommended action
For legal automation agents, pin worktree behavior deliberately and retest hooks, MCP auth, and subagent skill discovery before production runs.
Codex app automation backfill for legal workflows
Codex docs now emphasize recurring app automations, linked-repo worktrees, browser permissions, subagents, plugins, and CLI sandbox or approval profile controls.
Sources checked
Affected pages
Recommended action
Before running unattended legal agents, pin sandbox and approval settings, keep source allowlists explicit, and route Codex automation changes through reviewable PRs.
OpenAI Realtime and Codex plugin refresh
OpenAI released Realtime 2, streaming translation and transcription updates, and the OpenAI Developers plugin for Codex.
Sources checked
Affected pages
Recommended action
For legal intake or multilingual voice workflows, verify realtime model and API guidance before piloting client-facing automations.
Claude Code automation patterns for legal content workflows
Claude Code GitHub Actions supports scheduled and event-driven coding workflows, including skills and prompt-driven automation that can help maintain tutorial quality.
Sources checked
Affected pages
Recommended action
Keep Claude tutorials aligned with current GitHub Action and skill behavior before translation waves run.
Daily Codex automation loop for legal AI tutorials
We are adding a source-backed automation workflow that researches Codex and Claude changes, proposes tutorial updates, and hands approved changes to translation agents.
Sources checked
Affected pages
Recommended action
Use the updates page to track what changed, which sources were checked, and which tutorials need refresh work.