//
Search articles, pages, and resources across BaristaLabs.
Start typing to search...

Implementation notes for building AI tools around real business data, handoffs, review queues, and safeguards.
Bedrock's prompt attacks filter needs tagged input, and the Claude apps gateway adds none unless you set input_tagging, new in Claude Code 2.1.316. Which value to set.
The Claude Code 2.1.316 changelog lists pooled group budgets for the Claude apps gateway: one monthly budget a group shares. The spend limits docs don't cover it yet.
New Claude usage and cost endpoints break spend down by user, key and model, but typically refresh within 4 hours. Console's legacy API typically reports within 5 minutes.
Eligible ChatGPT Pro and Business plans now include up to $500 a month in OpenAI API credits. The API organization you link is the choice that is hard to undo.
GitHub made Copilot Fusion GA on Oct. 28. Admins can now make it the default model and set its tier, which can change how many models a task uses and what it costs.
Anthropic removes fast mode for Claude Opus 4.8 on November 30, 2026. Opus 5.5 fast costs less per token, but always-on thinking can raise cost per request.
Gemini API Computer Use reached general availability on Oct. 30. The safety system stays on, but screenshot prompt injection checks are opt-in.
AWS Step Functions workflows can now be AI agent tools through AgentCore Gateway. Pinning fixes which workflow starts; IAM still has to limit the runs and task tokens.
Amazon Quick now lets a classifier approve routine agent actions. Actions set to Ask each time may run without a prompt, so pin the critical ones first.
GitHub's Copilot app security extension explains and fixes code scanning alerts in your local copy. Fixes aren't pushed, and dismissals still reach GitHub.

Product notes, service updates, and BaristaLabs news that affect how small teams use AI at work.

AI market news translated into workflow decisions, risk boundaries, and practical next steps for small businesses.

Model concepts explained through thresholds, queues, and error costs that small teams can actually manage.

Plain-language guidance for owners and operators choosing one useful, reviewable AI workflow at a time.

Hands-on guides for approval policies, shadow weeks, agent receipts, and other AI workflow controls.