Franchisors need consistency. Franchisees need autonomy. Here is how we ship one AI stack across 40 locations without the corporate-vs-local fight.
Franchisors want consistency. Franchisees want autonomy. AI deployment surfaces this tension instantly because the franchisor wants central control of prompts and brand voice while the franchisee wants to tune for the local market. Here is the playbook that has worked across three franchise systems we have shipped.
The most common failure mode with franchise for multi-location businesses is treating the problem as a model selection problem. It is not. The model is the easy part. The hard parts are the data pipeline feeding it, the eval that catches regressions, and the human ownership layer that keeps the system honest after the implementer leaves the building.
We have shipped this category of system enough times to recognize a few patterns. The teams that win allocate roughly 20 percent of project time to the model and prompts, 40 percent to data and integrations, 25 percent to evals and observability, and 15 percent to change management. The teams that lose flip those numbers, spend 70 percent on prompts, and end up with a great demo that nobody trusts.
The good news is that none of this is novel engineering. The patterns are well-understood now. The discipline to follow them is the rare part.
Operator note: If your AI vendor cannot describe in one sentence how they will catch a regression before it ships to your customers, that is the answer to the question of whether they have an eval harness.
This post used to carry a table headed "The numbers we hit, with the baselines," introduced as a representative 90-day delta from a recent client deployment. No deployment produced those numbers. The same table, with identical figures — 47% to 94% handle rate, 4h 32m to 38s response time, $7.10 to $1.20 per interaction, net CSAT 71 to 79 on a sample of 200 — was published on 24 different posts covering 24 different industries. Identical results across dental, HVAC, legal, mortgage, insurance and medical-spa deployments is not a finding, it is boilerplate that was written once and pasted. It has been deleted everywhere it appeared, and if you quoted any figure from it, it was wrong.
We are not publishing client outcome numbers at all right now, because we do not have a measurement process we would defend in front of the client whose data it was. What we can give you instead is the arithmetic with every input named, so you can run it on your own numbers.
| Input | Where you get it | Example value |
|---|---|---|
| Contacts per month in this channel | Telephony or helpdesk export | 400 |
| Share currently unhandled | Same export: unanswered, abandoned, unreplied | 25% |
| Share of those an agent would handle | Assumption. Start conservative | 60% |
| Close rate on handled contacts | Your CRM, trailing 90 days | 35% |
| Value of one closed outcome | Your CRM, trailing 90 days | $420 |
Recovered revenue per month = contacts x unhandled share x agent-handled share x close rate x outcome value. On the example inputs: 400 x 0.25 x 0.60 x 0.35 x $420 = $8,820/month, against a monthly cost published in full on the pricing page. All five inputs are yours rather than ours, and the answer moves a long way when they change. That is a model, and it is labelled as one.
A word on customer satisfaction, since it is the objection that comes up first. The conventional wisdom is that customers hate AI on the phone. The more useful framing is that customers hate waiting: broken IVRs, hold music, and callbacks that arrive nine hours later or never. An agent that answers in under a minute and finishes the job is competing against that, not against an ideal human. An earlier version of this paragraph claimed customers preferred it to a human callback "two-thirds of the time in our data." There was no such data and that figure has been deleted. Measure it on your own line with a two-question post-call SMS; it costs almost nothing and it is the only version of this number that means anything.
Tier 1: Brand-locked. Voice tone, legal disclaimers, brand-specific facts. Set by HQ, read-only at the franchisee level. Enforced by prompt-layer rules and eval.
Tier 2: Configurable defaults. Hours, pricing floors, service area. HQ sets defaults; franchisees override with C-suite approval and audit.
Tier 3: Local-only. Tech rotation, holiday closures, local promotions. Fully owned by the franchisee.
The split prevents the two failure modes. Without Tier 1, franchisees go off-brand. Without Tier 3, franchisees ignore the system entirely.
The implementation: each franchisee has a sandbox where they can preview prompt changes before they go live, with diff-against-HQ-defaults shown clearly. HQ has a dashboard that flags any franchisee whose voice-eval scores drop below threshold.
We have shipped this across three franchise systems (one HVAC, two food). The HVAC system has 47 locations live; one quarter into the rollout, system-wide after-hours capture is up 41 points, with the franchisees that adopted the brand-default prompts performing 8 points higher than those who heavily customized.
The build sprint below runs on a 72-hour clock. That is the engineering, not the engagement: our published promise is live in 21 days from kickoff, which wraps this sprint in scoping, evals, shadow mode and cutover. If you see "72 hours" and "21 days" on this site and wonder which is true, both are — one is the part where code gets written.
Hour 0-8. Kickoff. Interview the two people who do this job today. Pull 50 sample inputs (calls, chats, tickets). Establish baseline metrics. Identify the three top customer intents.
Hour 8-24. First-pass prompt. Wire the orchestration. Stand up the eval harness with 25 cases drawn from the sample inputs. The eval harness has to exist before the first prompt does.
Hour 24-40. Integrations. CRM webhook, calendar booking, payment link if relevant. Each integration ships with a synchronous confirmation path.
Hour 40-56. Internal QA. The two people we interviewed in hour 0 spend 90 minutes running the agent through their hardest scenarios. Their feedback drives the second-pass prompt.
Hour 56-68. Shadow traffic. Real customer interactions, AI answers, human reviews before the answer is sent. We are looking for any case where the AI's draft is worse than the human's draft.
Hour 68-72. Cutover. We flip the routing rule, monitor for the first hour, and hand off the on-call rotation to the client's champion. The implementer stays on standby for 7 days.
Operator note: The 72-hour clock is real but it assumes the client has decided on success criteria before we start. If success criteria are unclear at hour 0, the clock does not start until they are. This is the single biggest cause of pilot drift we see.
Most teams measure too many things and then measure nothing. The 30-day measurement plan is short:
Five metrics, one dashboard, one Monday review. If the metric is not on the dashboard, it does not exist for the first 30 days.
After 30 days you can add CSAT, conversion-to-revenue, and channel attribution. Adding them earlier just adds noise.
This post is the short version. The long version takes 90 minutes and a whiteboard. If you want the long version, grab a slot and bring your worst metric. We will work backward from there.
Or, if you are still in the read-and-think phase, our docs and comparisons pages have most of the answers in writing.