Worked example of a forward-deployed AI pilot Prepared by Salt Technologies A distributor’s support team wants to spend less time answering “Where is my order?” This fictional four-week pilot shows what a forward-deployed Salt engineer and a client reviewer would test together. The ticket, costs and results below are illustrative. Before and after the pilot The support lead selects 100 anonymized historical tickets spanning ordinary shipments, partial orders, missing scans and conflicting records. These cases are held back from development. Reviewers replay each ticket using only the records available when the customer asked. During this evaluation, all replies stay in a test queue. Step | Manual baseline | AI-assisted workflow Find the order | An agent matches the requester and order number, then opens the order system and carrier record. | The integration checks the same account and order, then retrieves the timestamped status and carrier events using approved read-only access. A failed match goes to the agent. Prepare a reply | The agent reconciles the records, writes a reply and decides whether a delivery date is supported. | The system drafts a reply with links to the evidence. If the sources are missing or conflict, the intended behavior is to return the task to the agent. Resolve the ticket | The agent sends the reply and logs the disposition. The baseline averages six minutes per resolved ticket. | The reviewer checks the draft against the sources, accepts it, edits wording or rejects it. The log records the decision, reason and time through final handling, including manual fallback. Salt’s engineer observes the work, connects the approved records, implements fallback and delivers the evaluation log. The client’s support lead owns the definition of a correct reply and authorizes any live release. A draft the reviewer rejects Ticket 047 asks whether an order will arrive Friday. The order system says “packed.” The carrier record says “label created” and contains neither a pickup scan nor a delivery estimate. Review record | What happened Generated draft | “Your order has shipped and will arrive on Friday.” Reviewer decision | Reject. A shipping label establishes neither carrier possession nor a Friday delivery. The reviewer records an unsupported delivery promise and takes over the ticket. Manual replacement | “Your order is packed and a shipping label has been created. We’re waiting for the carrier’s first scan. We don’t have a confirmed delivery date yet.” Ticket 047 counts as a rejection even though the reviewer ultimately resolves it. Its full handling time is included in pilot cost. What does one accepted task cost? An accepted task is a draft the reviewer can use as written or after a wording-only edit. A factual rewrite counts as a rejection. In this example the client measures through final resolution, so the rejected drafts and cases that received no draft still incur labor. Reviewer outcome | Tickets | Minutes per ticket | Total minutes Approved as drafted | 70 | 2 | 140 Approved after a wording edit | 10 | 4 | 40 Rejected and completed manually | 12 | 8 | 96 No draft; completed manually | 8 | 8 | 64 Of 100 tickets, 80 produce accepted drafts. Total handling time is 340 minutes. At $36 per hour, labor costs $204.00. Model and retrieval usage adds $12.00 across the full batch. Cost per accepted task = $216.00 ÷ 80 = $2.70. How does that compare with the manual queue? Use all resolved tickets as the common denominator. The manual team spends 600 minutes at $36 per hour, or $360.00 for 100 tickets ($3.60 each). The assisted team resolves the same 100 tickets for $216.00 ($2.16 each), including every manual fallback. These are variable operating costs. For a rollout budget, add the pilot fee, integration maintenance, monitoring and ongoing evaluation. At this workload the illustrated difference is $1.44 per resolved ticket before those costs. The client would need its own volume and fixed-cost estimate to calculate payback. Would the client roll this out? The support lead holds the live rollout. Before testing, the support lead set four gates. All four must pass. The reviewer caught the bad promise before a customer saw it, but producing it still fails the quality gate. Gate set before evaluation | Observed | Decision At least 80% of eligible tickets produce an accepted draft | 80 of 100 tickets (80%) | Pass Average handling time at most 4 minutes | 3.4 minutes across all resolved tickets | Pass Variable cost at most $3.00 per accepted task | $2.70 | Pass Zero unsupported delivery promises in drafts shown to reviewers | One in 100 tickets, on ticket 047 | Hold Salt’s engineer changes the shipping-status check so a delivery promise requires a carrier estimate and a label-only record stays pending. The client runs a fresh held-out batch of 100, including label-only cases. If every gate passes, the support lead may authorize 10% of eligible tickets with human approval on every reply. After 50 live tickets the lead reviews errors, cost and time before expanding. A new unsupported promise pauses drafting and returns the queue to manual handling. If the revised pilot still misses a gate, the client keeps the manual process and decides whether another iteration is worth funding. Source — https://www.salttechno.com/forward-deployed-ai-engineering#ai-pilot-worked-example Discuss a paid pilot for your workflow — https://www.salttechno.com/contact-us?source=%2Fforward-deployed-ai-engineering&interest=Forward-deployed+AI+pilot&resource=ai-pilot-worked-example