AIATS Insights
Technical notes, implementation lessons and production playbooks for ServiceNow, AWS and enterprise AI.
AgentCore short-term memory now bills by GB ingested, retrieved and stored, and long-term memory records can finally expire on a TTL. Here is how UK SRE and FinOps teams should re-cost agents and set retention that stands up to UK GDPR.
Build ServiceNow apps from Git: architecture, workstation, SDK/Fluent workflow and AI-agent guardrails.
4 parts · updated 26 Sept 2026
CAB-ready go-live checklists for new ServiceNow and AWS releases.
12 articles · updated 16 Oct 2026
Runtime, Gateway, Memory, Policy and Evaluations on Amazon Bedrock AgentCore.
15 articles · updated 16 Oct 2026
Governing agents and MCP tools on the Now Platform.
5 articles · updated 21 Sept 2026
AgentCore short-term memory now bills by GB ingested, retrieved and stored, and long-term memory records can finally expire on a TTL. Here is how UK SRE and FinOps teams should re-cost agents and set retention that stands up to UK GDPR.
ServiceNow's new AI Passport gives every agent and MCP server a signed, policy-bound scope that is checked at runtime, with a kill switch. Here is the production gate UK platform teams should build before it lands in Q4 2026.
As of 2 Oct 2026, Amazon Bedrock AgentCore Gateway trusts private CA certificates for MCP, OpenAPI and HTTP proxy targets on VPC Lattice endpoints. Here is the UK SRE production gate: where the PEM lives, how trust anchors are rotated, and what still needs an ALB.
AI Workflow Factory (globally available 6 Oct 2026) joins Process Mining, Autonomous Engineer, Build Agent and App Engine into one governed improvement loop. Here is the UK production gate: what you enable first, what stays human-gated, and how AI Control Tower stays the spine.
AWS's 21 Sep 2026 pattern turns Bedrock Guardrails interventions into OCSF Detection Findings in the CloudWatch unified data store. A UK SOC/SRE gate: transform locally, centralize sanitized findings, correlate with CloudTrail and VPC Flow Logs — without shipping prompt bodies.
Australia's Change Data Quality AI Agent now persists scores in ai_change_quality_score. A UK CAB production gate: policy documents, supervised vs autonomous versions, approval thresholds, and Platform Analytics — without letting agents rewrite RFC fields in PROD.
Code-first ServiceNow only works if the guardrails are as deliberate as the tooling. This part sets out environment tiers, an AI agent access model where agents work in LAB, PDI and DEV but never touch PROD without human approval, secret handling, audit evidence, and a balanced guide to when Fluent is right and when native ServiceNow development is the better tool.
What code-first ServiceNow development looks like day to day: a Fluent project layout, short TypeScript examples that compile with SDK 4.13.0, the build and deploy loop, branching and pull requests, CI quality gates, ATF, and a promotion path from DEV to TEST to PROD that keeps the SDK away from production.
Code-first ServiceNow development needs a workspace you can rebuild in minutes and trust with credentials. Here is how I set one up: an Ubuntu 24.04 host, Docker, a Coder workspace template, Node 24, a pinned ServiceNow SDK and instance authentication that never touches Git.
Building ServiceNow apps by clicking through forms works, but it is hard to review, hard to diff and hard to hand to an AI agent safely. This is the architecture I'm using instead: Coder workspaces, Node 24, the ServiceNow SDK with Fluent, Git, pull requests, ATF and gated promotion from DEV to TEST to PROD.
Zurich pairs Developer Sandboxes with ReleaseOps pipelines so UK teams can build in parallel and promote with CAB-grade evidence. A platform production gate covering MIM, analyzer checks, ATF hooks, and upgrade/clone sandbox hygiene.
AgentCore Runtime V2 GA (18 Sep 2026) reclaims session memory and holds P75 cold starts near 2s from 200 MB–2 GB images, including eu-west-1. A UK SRE canary and CAB checklist before flipping platformVersion to V2.