Calling for an Immediate and Total Shutdown of running clubs, which are an affront to normal sidewalk users, whose paths are continually disrupted by hordes of heaving, barreling runners, who ram into passersby and generally are a Disruption To The Peace. Thank you

Needham on $AXON (Buy, PT $750): "Below, we highlight in detail challenges that have emerged in recent months around the fixed ALPR (Automatic License Plate Reading) camera market on a nationwide basis following public outcry related to data sharing and governance policies for law enforcement's use of these cameras. The net result is we expect the fixed ALPR market to dry up for 2026 and likely 2027 until vendors and law enforcement can convince citizens their data sharing and governance strategies protect individuals' rights and liberties consistent with the US Constitution. Importantly, we don't view ALPR as key for Axon to hit their 2026 guidance or 2028 financial targets. Flock ALPR contract cancellations have surged in 2026 following public outcry. Our research indicates switching to Axon fixed ALPR cameras is limited; the greater signal is a total shutdown of cameras. Based on our research, we believe only a handful of customers have actually switched to Axon ALPR cameras. Will fixed ALPR challenges bleed into concern over RTCC? We don't expect there to be a carryover impact to the rapid rise in RTCC software nationwide, but it will remain a risk to monitor. ALPR is not needed for Axon to hit their 2028 targets. In our view, we believe the fixed ALPR opportunity was a relatively modest calculus to the company's latest three-year model. Axon's diversification positions for competitive strengthening vs. Flock Safety. We believe Axon can accelerate market share gains relative to Flock Safety in products like RTCC and drones where they overlap due to Axon's stronger brand reputation and ecosystem diversification that can serve a range of customer needs." Analyst: Joshua Reilly

# Practices for Embedding AI Agents in Software # Tool Gateway / MCP Broker 🎯 The Hook Your AI agent calls multiple tools directly? That's a distributed security nightmare waiting to happen. A single gateway layer turns chaos into a controlled chokepoint. 🔥 The Problem When agents call external tools and MCP servers directly, authorization, rate limiting, and logging scatter across every integration. Prompt injection can sneak malicious arguments past individual tools, and audit trails become impossible to reconstruct when logs are spread across a dozen services. 💡 The Pattern Route all tool calls through a single gateway that enforces authorization, input sanitization, rate limiting, and audit logging in one place. Use dynamic scoping to expose only the tools relevant to the current task and user permissions, keeping the LLM's selection space narrow. Apply asymmetric policies: write operations get fine-grained per-operation authorization and HITL approval, while read operations use lighter category-level checks. Adding or removing tools becomes a configuration change, not a code deployment. ✅ When to Use Use when: - The agent calls multiple tools, at least one with side effects - User input or external data flows into tool arguments (low input trust) - You need an audit trail of who called what, with which arguments, and under whose authority Don't use when: - There's only one read-only tool and gateway overhead isn't justified - All tools are trusted internal services in an experimental environment where prototype speed matters more ⚠️ Pitfalls - The gateway itself becomes a single point of failure. Design health checks and a degraded mode (e.g., read-only fallback) - Never enforce authorization or sanitization via prompts. "Don't use this tool" instructions are trivially bypassed by injection - Session-level rate limits alone won't stop distributed attacks. Add a global rate limit layer on top 🔧 Implementation Approach - Define gateway policies declaratively (e.g., YAML), specifying type (read/write), authorization granularity, rate limits, sanitization rules, and log levels per tool - Dynamically scope tools exposed to the LLM based on task type, user permissions, and conversation phase, excluding irrelevant tools from the selection space - Design health checks and a degraded mode (read-only fallback) so the system survives gateway failures without total shutdown - Normalize schemas across MCP servers at the gateway layer, presenting a consistent interface to agents regardless of backend differences - Route high-risk code execution to sandboxed environments and use short-lived permission leases for long-running sessions #AIAgents# #SoftwareArchitecture#