The 6-week pilot framework that avoids the most common ways AI projects die: scope creep, vendor lock, no champion, fuzzy success criteria.
AI pilots fail in the same three ways. The scope creeps from one workflow to four. The success criteria are vague. The pilot has no internal champion. Below: the six-week framework that avoids all three.
Every architecture choice in this category is a tradeoff. Here are the ones we have made consciously, and the alternative we did not pick.
We use Pipecat instead of building our own orchestration. The win is months of saved engineering. The cost is being a release behind on a few model integrations.
We use Anthropic as the default LLM with OpenAI failover, not the other way around. The win is consistently lower hallucination rates in our eval set. The cost is slightly higher cost-per-token at the equivalent model tier.
We run a custom eval harness instead of using a vendor product. The win is the eval set lives in the same Git repo as the prompts, so PRs that change prompts fail the build if they break an eval. The cost is we own the upkeep.
We use Twilio over a cheaper telephony provider. The win is concurrency ceiling and the depth of the diagnostic tools. The cost is roughly 18 percent more per minute.
We deploy on Fly.io, not Vercel. The win is real persistent connections and global edge POPs that survive long-lived voice sessions. The cost is more devops overhead.
These tradeoffs are not laws. They are starting points. If you tell us you have an existing GCP estate, we will adapt the stack. The principles do not move; the implementations do.
Looking back at the last six deployments in this category, three things we would do differently:
Start the eval harness on day zero. We have always said this and we have always slipped it. The first time we shipped without a regression eval, we caught a prompt change that silently degraded conversion by 11 percent for two weeks before anyone noticed. Now we treat the eval harness as the first deliverable, before the first prompt.
Get the executive sponsor in the first user-acceptance session. Not the project manager, not the ops lead. The owner or the C-suite person whose name is on the budget. Their reaction to the first live test changes the trajectory of the project. Their feedback in week four is too late.
Document the human escalation paths before the AI ships. Every project we have shipped that did not have written escalation procedures had a moment in week two when an unexpected case hit, the AI escalated, and nobody knew who was supposed to handle it. Documenting the human side before the AI ships is half a day of work that prevents a week of fire-fighting.
If you want to talk through how any of this applies to your specific situation, grab a 20-minute call. We do not pitch on the call. If you would rather read more first, the docs and our comparisons cover most of the underlying technology choices in writing.
Week 0. Pre-work. Write success criteria. Sign off from C-suite on the kill criteria. Pick the champion. Pick the use case (one, not three).
Week 1. Discovery. Interview the people doing the job today. Pull baseline data. Lock the scope.
Week 2. Build first iteration. Stand up the eval harness in parallel.
Week 3. Shadow traffic. AI generates draft answers; human still owns the customer. Compare quality.
Week 4. Live with 25% routing. Monitor daily. Iterate prompts in response to failures.
Week 5. Live with 75% routing if metrics hold. Hand off ops to the champion.
Week 6. Review. Did we hit the success criteria? Yes = scale. No = kill or refactor.
The kill criteria piece is the part everyone skips. Without it, pilots become zombies — neither alive nor dead, eating budget for 9 months. Write down what 'failed' looks like before you start.
The most common failure mode with pilot for framework 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.
If something here tripped a wire, grab time on the calendar. We do a free 20-minute working session where we map your current flow and circle the two places AI moves the needle this quarter.
You can also browse the rest of the blog for 40-plus posts in the same operator voice, no fluff.