Sessions. A first session usually runs around 2 hours, and setup and installation eat into that if it is not already done. After that it genuinely varies with your background and with the problem. Someone coming from analytics, from programming or from marketing all start at a different place, and so does someone already working in VS Code or a command-line tool versus someone who has never opened one. Some things get resolved in a single sitting, others run across several sessions.
Execution is scope-based. You work out what you want built, he comes back with an estimate in hours, and every sprint is capped and approved before it starts.
Some examples from real engagements. These are brain-time hours, so the calendar time is longer and is given alongside:
- Paid scoping prototype, fully clickable with dummy data, built to make a proposed system concrete before anyone commits to it - about 2 hours.
- Operational monitoring dashboard, live operational parameters and activity tracking pulled into one view - about 15 hours of brain time, over about a week.
- Response model delivered as a tool. The model was built offline; the tool is what the team runs afterwards to pull current data, score it, and set the new run against the previous one so a shift in the population splits or the decile table surfaces on its own - about 25 hours of brain time, over about 2.5 weeks.
- Full-stack AI-based tool built into a client's existing stack, where records go from their database to an AI for review and correction and are written back after checks, wired to their existing auth with role-based access and full logging - about 70 hours of brain time over 4 to 6 weeks. The client took it over at around the 90 per cent mark and finished the tweaks themselves.
Sessions, some examples: a CEO working on Claude Cowork and Claude in Excel and PowerPoint, 90 minutes plus a 1 hour deep dive later. A head of analytics building ML and statistical models with Claude Code, about 2.5 hours. A CFO new to all of this, working through what an API is, subscription versus API cost, build versus buy, model routing and how an agentic setup works, about 5 hours over 2 to 3 sessions. A founder moving from a chat AI to Claude Code with an automated deploy path, 8 to 10 hours across several sessions.
These are indicative, not a scale. Each number belongs to that one piece of work. The spread runs wide in both directions: he has done scoping work and dummy-data prototypes that ran a lot longer than the two hours above, and built small full-stack apps in far less time than the larger ones here. Two projects that read alike on paper can land a long way apart once the detail turns up. The real number comes out of scoping, and every sprint is capped and approved before it starts.
Rates are on how much does Amar Harolikar charge, the engagement mechanics on what working with him looks like, and the full page at https://www.tigzig.com/how-i-work. For an estimate on your own project, email amar@harolikar.com.
← All Agents FAQ