Welcome to the Agentic Age. No question is bad. No topic is off limits. We are here for you — to help every engineer ship faster, think bigger, and build with confidence.
/goal: Claude works across turns until a condition is met
/scroll-speed: tune scroll rate with live preview
/mcp reconnect picks up .mcp.json edits without restart
alwaysLoad config keeps MCP tools always available
Stdio servers receive CLAUDE_PROJECT_DIR in env
continueOnBlock: PostToolUse feeds rejection back to Claude
ANTHROPIC_BEDROCK_SERVICE_TIER: flex/priority support
Fixed Bedrock 400 with ENABLE_PROMPT_CACHING_1H
Fixed multi-GB memory growth from image-heavy sessions
Claude asking if it’s okay too much?
Ask it to help you with your settings.json
permissions.allow/deny — what Claude does without asking
defaultMode — default, acceptEdits, or plan
env — inject AWS region, Node env, proxy
~/.claude/settings.json — your global defaults.claude/settings.json — per-project rules (commit it).claude/settings.local.json — personal overrides
/update-config — describe what you want in plain English
/fewer-permission-prompts — Claude reads your history and suggests the right allow rules
As Claude Code moves to GA, we're consolidating support into a dedicated Claude Code team on Microsoft Teams. The POC chat will be shutting down — please join the new channels below. Search "Claude Code" in Teams to find the team.
One stop shop for all things Ally Claude Code. Links to resources, process guides, and support channels.
Main channelFor MCP integrations, skills, and agents. Plugin questions, installation help, and contribution guidance.
RecommendedInformation and discussion specific to MCP servers — building, hosting, and connecting them.
Installation support, troubleshooting questions, and incident tickets. Your first stop for issues.
Techniques, prompts, and patterns to get the most out of Claude Code. Learn from each other.
RecommendedGeneral chat — migrating the Claude Code Lobby from Slack to our official community. All topics welcome.
RecommendedPrivate sub-channel reserved for Claude Code Champions program members.
Private • By invitationDescription of monitoring patterns, dashboards, or alerting strategies.
Description of logging best practices, tracing, or SLO updates.
Description of debugging workflows, incident analysis, or tooling tips.
Checks that your graph actually compiles, your edges go somewhere real, and your model integration won’t blow up in production. Scaffolds new tools with tests so you don’t ship untested code. Includes 12 labs if you want to learn LangGraph properly.
/allyai:learn • /allyai:scaffold • /allyai:validate • /allyai:visualize • /allyai:deploy
GenAI Platform & Enablement — Adric Saxon • v0.3.0
Everything above, plus forge handles the rest of your workflow. You describe a feature, it plans, implements, then throws 14 reviewers at your diff—none of whom have seen your code before. They find the stuff you stopped noticing three commits ago.
/explore → /plan → /implement → /review → /ship
claude plugin marketplace add ally-claude-plugins-officialclaude plugin install allyai — optionally add forgeYou built a skill that works great in Claude Code — now what? Adric Saxon walks us through the full journey of taking an interactive skill and turning it into a fully autonomous, productionized agent on the Ally AI Platform.
Claude Code skills are great for prototyping logic — they give you fast iteration, tool access, and a human in the loop. But they require a developer at the keyboard.
Identify the decision graph inside your skill. Map prompts to nodes, tool calls to edges, and human checkpoints to conditional branches — this is your LangGraph blueprint.
Package the agent for the Ally AI Platform. Add observability, error recovery, and scheduling — now it runs autonomously without anyone at the keyboard.
Brief description of what the next COE session will cover.
Have a topic you'd like covered? A tool you want demonstrated? Let us know.