//
Technical Tutorials22 articles
Technical Tutorials
Hands-on guides for approval policies, shadow weeks, agent receipts, and other AI workflow controls.
Resource path
Implementation artifacts you can copy before the workflow gets permission.
Use this shelf when the AI idea has become specific enough to sketch. These tutorials turn approval policies, security reviews, shadow weeks, rollback paths, and queue designs into artifacts a teammate can inspect before the system acts.
Start here
Build the approval queue before the agentIt shows the core BaristaLabs sequence: proposed action, reviewer evidence, approval decision, receipt, and safe execution boundary.
Turn one workflow into reviewable proposal, evidence, decision, receipt, and rollback fields.
Sketch one approval queueSee where permission enters the workflow
Start with the point where an AI draft becomes a real action: update the CRM, send the email, refund the order, change the customer status. That boundary decides what the queue must show.
Sketch the policy, receipt, and rollback
Turn the candidate workflow into a written approval policy, a receipt template, and a rollback owner before the agent earns write access.
Run one safe rehearsal
If the artifact is still theoretical, run a shadow week: let AI produce work beside the current process, compare misses, and decide whether the next permission is earned.
Articles
Observed captureTechnical Tutorials
How to review an AI-built website change before publishing
A practical way to verify a versioned website change across code, browser behavior, accessibility, metadata, links, and performance before approval.
12 min read
Technical Tutorials
How to test duplicate-safe retries in an AI workflow
Run a Node.js fixture that drops the first acknowledgement after a destination write, replays the same request ID, rejects changed parameters, and checks the business-state count.
10 min read
Constructed diagramTechnical Tutorials
HTTP Terminator generated 30,000 attack ideas. The evaluator made them research.
PortSwigger generated 30,000 candidate HTTP attack vectors. The useful result came from the evaluator, deterministic proof, authorization boundary, and expert-guided cascade.
12 min read
Constructed diagramTechnical Tutorials
Trial Cloudflare Kitesurf for one-shot browser jobs; keep Chromium for stateful work
Cloudflare Kitesurf uses less CPU and memory but takes longer in vendor tests. Trial one-shot browser jobs and keep stateful work on Chromium.
8 min read
Constructed diagramTechnical Tutorials
Microsoft Agent Framework 1.17.0 fixes false success in one Foundry workflow path
A provider failure could look like a completed Microsoft Agent Framework workflow with an empty message. Version 1.17.0 restores the failure state.
7 min read
Constructed diagramTechnical Tutorials
Armature's MCP telemetry mixes observations with agent reports
Armature combines observed MCP execution with context supplied by the calling agent and judgments made later. Product and release decisions should keep those sources separate.
9 min read
Constructed diagramTechnical Tutorials
OneCLI changed its policy model. Diff access before upgrading.
OneCLI's grants migration converts expressible credential access, removes rules it cannot map, and resets one project default. A staged before-and-after access diff shows whether v1.45 is ready to promote.
8 min read
Constructed diagramTechnical Tutorials
A pentesting phone can infer the subnet. It cannot infer permission.
Nightcrawler makes autonomous mobile penetration testing concrete. Its auto-derived network scope also shows why a device's current subnet cannot define where an AI agent is authorized to act.
7 min read
Constructed diagramTechnical Tutorials
Sprocket v0.3.0: verify the design before agent checkout
Sprocket v0.3.0 documents a path from a bill of materials, pin map, schematic, and assembly notes toward checkout. Design acceptance must come before purchase authorization.
8 min read
Technical Tutorials
Start AI jailbreak triage with capability gain
Anthropic's early Cyber Jailbreak Severity proposal gives security teams a useful first question: what attacker capability did the AI output add beyond public tools and information?
10 min read
Technical Tutorials
Your AI agent can compile a beautiful chart. It can still answer the wrong question.
Microsoft Flint gives AI agents a compact chart language. Use a chart-intent diff and one-question/three-intents test to inspect fields, denominators, cohorts, and viewer inference before approval.
9 min read
Technical Tutorials
When Lighthouse blames your page, ask for the blocking-work receipt
A mobile Lighthouse score can look mostly healthy while Total Blocking Time says the browser is still too busy to answer a tap. Use a blocking-work receipt before changing the site.
9 min read
Explore Other Categories
AI Development
Implementation notes for building AI tools around real business data, handoffs, review queues, and safeguards.
133 articles
Announcements
Product notes, service updates, and BaristaLabs news that affect how small teams use AI at work.
9 articles
Industry Insights
AI market news translated into workflow decisions, risk boundaries, and practical next steps for small businesses.
382 articles
Machine Learning
Model concepts explained through thresholds, queues, and error costs that small teams can actually manage.
12 articles
Small Business AI
Plain-language guidance for owners and operators choosing one useful, reviewable AI workflow at a time.
92 articles