Need help threading a needle with a client. Two owners, two different outreach plans, and neither one is clean on consent. I run a small AI automation shop. Just landed a solid client in the home repair space. They help homeowners after a major damage event, and the whole business runs on speed. There's a short window to reach people right after something happens, and whoever gets to the homeowner first usually wins the job. Time is everything in this niche. Here's where I'm stuck. There are two owners and they want to go two different directions. The first guy, call him Dan, is the operator. Younger, bought into the company in his early twenties, runs the day to day, super relationship driven. Dan wants me to build a system that blasts text messages out to a list of homeowners in the affected area. No opt in, no prior relationship, just hit the list fast. When I brought up the consent problem he basically said he's willing to eat the fines and wants to move forward anyway. His logic is that the whole industry is doing it and nobody seems to be getting hit, so why slow down. The second guy, call him Victor, is the money and the real power. Bought into the company recently, runs a whole portfolio of other businesses, master negotiator type. Victor doesn't want texts. He wants an AI voice receptionist and outbound calls. More of a robocall and live-routing approach. So I've got the operator pushing non-consented text blasts and the owner pushing voice and calls, and honestly neither path has a real consent foundation underneath it yet. They just have a list of people in an area who got hit. My questions for anyone who's actually built outreach at scale. How are you all handling the consent piece in a time-sensitive niche like this, where you can't realistically get opt in before you reach out? Is there a legitimate way to move fast and stay protected, or is everyone just accepting the risk? When a client tells you flat out they're willing to take the legal hit, how do you protect yourself as the builder so the exposure stays with them and not with you? Contract language, documentation, who owns the sending number, anything you've learned the hard way.

Hey everyone — hitting a wall with Retell AI and hoping someone here has solved this before. The Setup: I have an inbound voice agent (Amber) handling calls for a restoration company. The flow is: Caller calls in → Amber answers and collects info Amber calls a Custom Function (get_oncall_routing) that hits a Relay.app webhook Relay looks up who's on call, returns data back to Retell Amber does a Warm Transfer to the on-call PM's phone number Amber delivers a Whisper Debrief to the PM and a Three-Way Handoff to both parties What Works Perfectly: {{oncall_phone}} substitutes correctly in the Dynamic Routing field — Amber routes to the right phone number every single time ✅ {{caller_name}} and {{emergency_summary}} are being collected correctly during the call ✅ The full Relay JSON response (Step 6) includes both oncall_name and oncall_phone ✅ The Relay JSON response looks like this: json{ "assignedPerson": "Ryan Smith", "assignedPhone": "+12089707024", "region": "EAST", "oncall_name": "Ryan Smith", "oncall_phone": "+12089707024", "fallbackPerson": "Blake Hansen", "fallbackPhone": "+12085898887", "zipLookupSucceeded": true } Store Fields as Variables mapping in get_oncall_routing: oncall_name → oncall_name oncall_phone → oncall_phone caller_name → caller_name emergency_summary → emergency_summary assignedPerson → assignedPerson region → oncall_region The Problem: {{oncall_name}} is NOT substituting in either the Whisper Debrief Message or the Three-Way Debrief Message. In Prompt mode — Amber literally says "Oncall name" out loud. The LLM reads the placeholder as literal text. In Static Sentence mode — the variable doesn't substitute at all. Amber either skips it or says nothing where the name should be. What We've Tried: ✅ Confirmed oncall_name is in the Relay JSON response ✅ Confirmed Store Fields mapping is correct — oncall_name → oncall_name ✅ Tried Prompt mode with {{oncall_name}} directly in the sentence ✅ Tried Static Sentence mode with {{oncall_name}}

COMMUNITY REVIEW REQUEST AI Contractor Agreement — Redacted for Privacy I just landed my biggest client — a 19-location franchise — and they sent me a fully drafted Master Services Agreement tonight with their signature already on it. Before I sign I want experienced eyes on a few clauses that concern me. Here are the specific items I'm pushing back on and why. The full redacted contract follows below. ═══════════════════════════════════════════════════ THE THREE ITEMS IN QUESTION ═══════════════════════════════════════════════════ ───────────────────────────────────────────────── ITEM 1 — NON-COMPETE (Section 6.4) STATUS: Pushing back — too broad ───────────────────────────────────────────────── WHAT IT SAYS: For 24 months after the engagement ends, I cannot provide AI consulting, development, or implementation services to any business in the quick lube, oil change, or automotive preventive maintenance industry — in any state where the client currently operates or plans to operate. WHY IT'S A PROBLEM: - 24 months is a long time in a fast-moving industry - The automotive services space is one of my core target verticals - "Any state where they plan to operate" is vague — they're expanding, so this could cover more and more states over time - It's not just their direct competitors — it's the entire industry category MY PROPOSED COUNTER: Reduce to 12 months. Limit to direct quick lube and oil change competitors actively operating in the same specific markets as the client at the time of termination — not the entire industry across all states. QUESTIONS FOR THE COMMUNITY: - Is 12 months reasonable for this type of engagement? - Is market-specific language standard or will they push back hard? - Have any of you successfully negotiated non-competes down in service agreements? ───────────────────────────────────────────────── ITEM 2 — NO-REPLICATION CLAUSE (Section 6.5) STATUS: Pushing back — scope too wide ───────────────────────────────────────────────── WHAT IT SAYS:

Can someone please explain why I should use Cowork/ Code rather then Replit/Loveable/Base44? don’t see how, I’ve built several tools with Replit and to amazing detail. My concern with coworker is it’s only lives on my machine. How are other people gonna use it whereas with Replit they have a hosted website they can go to to use it.

Claude Code just dropped a hidden feature called Ultraplan. Instead of planning locally in your terminal, it sends your planning session to the cloud where multiple agents running Opus 4.6 work in parallel to build a much deeper, more structured plan. In this video, I break down how it works, run a side-by-side test building the same dashboard with local plan vs Ultraplan, and show you the speed and quality differences. I also dig into the technical details, including the multi-agent architecture, token usage, and what you need to know before trying it.