Practical notes from the engineers who build agents, copilots and AI products.
Investors want real users, an AI capability with an eval score, usage analytics and a roadmap, not a slide deck with screenshots. A clever demo proves nothing now that anyone can build one in a weekend; evidence that real people use it, and that the AI part is measured, is what earns a second meeting.
Sovereign AI keeps models, data and operations under Indian jurisdiction; for enterprises it means private deployment and local providers. In practice: open-weight or Indian models served in Indian regions or your own data centre, Indian contracts, and operations you control. It is a procurement stance, not a tool.
Indian delivery at senior quality runs a fraction of US rates; the gap narrows for AI specialists, and outcome-based pricing matters more than hourly. Compare vendors on what a finished, evaluated system costs and who owns it afterwards, not on the rate card, since rates hide seniority, rework and management overhead.
A useful SLA states response and resolution by severity, cover hours, escalation path and what happens when it is missed. It also defines the severities in plain language, says whose clock is used, and reports performance against itself every month, so both sides can see whether the promise is being kept.
Launch agents in shadow mode where they propose and humans approve, then grant autonomy intent by intent as evaluation evidence accumulates. The agent earns each permission with a record of accepted proposals, not with a demo, and the people whose work it touches decide when it is ready.
Lock one segment, one workflow and one AI capability by day five; everything else goes to a priced v1.1 backlog. That single decision, made early and defended weekly, is what lets a six-week MVP ship on the date, and it is the decision most teams delay until the date has already gone.
A production multi-tenant SaaS starts around $31,000 for a focused product and scales with modules, integrations and design. The budget splits into the tenant and billing foundation, the core workflow that customers pay for, integrations, design, and the running and care costs that begin the day you launch.
Dispatch rules and area batching deliver most of the gain; pure route optimisation matters only after the operation runs on data. Fix how work is grouped and assigned first, capture actual addresses, times and outcomes, and only then buy or build a routing algorithm, which is only as good as the data beneath it.
Agents approve returns within policy, generate labels and update the customer, escalating damage and disputes to people. The policy is a table the operations team owns, the agent is allowed to act only where the table says yes, and every decision is logged with the order, rule and outcome so finance can audit it.